JP7670293B2 - Information Processing System - Google Patents

Description

Article 30, paragraph 2 of the Patent Act applies. Content related to the function of the present invention will be published on a web page on March 10, 2021 (URL: https://txpmedical.jp/pharma/#clinical-trial)

Article 30, paragraph 2 of the Patent Act applies. Content related to the function of the present invention will be published at the 6th A2 Webinar on March 10, 2021.

Article 30, paragraph 2 of the Patent Act applies. On February 18, 2021, February 26, March 5, March 24, March 25, March 30, April 9, and May 20, 2021, the company explained the contents related to the function of the present invention to each individual company.

This invention is an information processing system that supports the selection of patients who are candidates for clinical trials.

When developing a new drug, clinical trials are conducted to confirm the effectiveness of the new drug and whether or not there are any side effects. In a clinical trial, the doctor in charge of the clinical trial (clinical trial investigator) selects patients who meet the criteria for the clinical trial as candidate subjects, based on criteria set in advance by the pharmaceutical company. The clinical trial is then explained to the candidate patients, and after their consent is obtained, an ethical committee within the medical institution reviews the case, and if approved, the clinical trial is carried out with the patient as a subject.

Therefore, when a clinical trial is conducted on a new drug, the investigator will select patients who are candidates for the trial by comparing the information recorded in the patient's medical record (e.g., electronic medical record) with the information in the guidelines that state the criteria for clinical trials, etc.

Traditionally, the selection of patients who are candidates for clinical trials has been done manually by the investigator, but because this task is burdensome, attempts have been made to systematize it. One example of a system for selecting clinical trial subjects is the one described in Patent Document 1 below.

JP 2014-194595 A

The standards in the guidelines published by pharmaceutical companies when conducting clinical trials generally include "clinical diagnosis," "age," "presence or absence of comorbid diseases (medical history)," "presence or absence of regularly taken medications," "ADL (health level) before the onset of the disease," "significance of the disease (scoring)," and "imaging findings." As much of this information is recorded in the patient's medical record, when the clinical trial physician selects patients who are candidates for clinical trial subjects, he or she refers to the information in the patient's medical record. Note that the clinical trial physician is often not the patient's doctor.

One of the most important criteria for clinical trials is the "clinical diagnosis." However, the clinical diagnosis (clinical disease name) is often not recorded in the medical record. Even if it is recorded in the medical record, it is often not immediately clear where the clinical diagnosis is recorded.

This is because there is no obligation to record clinical diagnoses in medical records. Medical records are broadly divided into sections for displaying and recording standard information such as the patient's attributes, free-form sections for displaying and recording information obtained by the doctor when examining the patient and the doctor's own findings, and ordering sections for displaying and recording information on instructions for the patient, such as procedures, tests, and prescribed medications.

The free-entry section of the medical record is a display and recording section in which the doctor can freely and unrestrictedly enter information and findings he or she has heard from the patient in free text format, and so the doctor may or may not enter the name of a clinical diagnosis there. Even if the doctor enters a clinical diagnosis, there is no rule as to where in the free-entry section the doctor enters it, and this is at the discretion of each doctor. In this way, since the free-entry section is, so to speak, a memorandum for the doctor, the doctor often writes down information that the doctor can understand, and the clinical diagnosis is not necessarily expressed accurately, and may be entered as an abbreviation, etc., as appropriate.

Therefore, if a patient is under the doctor's care, he or she can immediately identify whether or not the patient has a clinical diagnosis according to the criteria of the clinical trial. However, if a clinical trial doctor who is not the doctor in charge of the patient in question views the medical record, he or she must search for the clinical diagnosis written in the free-form entry section of the medical record, or infer the clinical diagnosis by reading the information written in the free-form entry section of the medical record. However, such work is a heavy burden for busy clinical trial doctors.

In addition, since many medical institutions have introduced electronic medical records as medical records, it is possible to search for the target disease name by matching the electronic medical record with the clinical trial criteria in the pharmaceutical company's guidelines. However, conventional electronic medical records simply store the text information entered in the free-text field of the electronic medical record, so even if you try to search for and match the corresponding disease name in the electronic medical record using the clinical diagnosis name in the clinical trial criteria as a search key, it is not possible to distinguish whether it is the patient's current clinical diagnosis name or a clinical diagnosis name from their medical history.

Therefore, even in this case, the clinical trial physician will still need to interpret the information in the electronic medical records.

Assuming that matching will be performed, asking doctors to enter patients' clinical diagnoses, symptoms, and commonly used medications in standardized language into electronic medical records places a heavy burden on doctors. This burden is particularly heavy for doctors in emergency rooms where every minute counts. Furthermore, doctors want to be able to fill out electronic medical records in their own style, so asking them to enter information in standardized language and sentences places a psychological burden on them.

In addition, the ordering section of the electronic medical record contains information about the receipt for insurance claims, and the receipt lists the diagnosis given to the patient. However, the diagnosis listed on the receipt is a diagnosis (insurance diagnosis, insured disease) given for the convenience of insurance claims, and does not necessarily match the clinical diagnosis determined by a doctor to identify the patient's actual illness. Therefore, the patient's actual illness (clinical diagnosis) cannot necessarily be determined by simply referring to the receipt.

Furthermore, when selecting potential clinical trial subjects based on a clinical diagnosis, a patient cannot be selected as a potential clinical trial subject until he or she has been given a confirmed clinical diagnosis. Therefore, this method is not applicable to the selection of potential clinical trial subjects for new drugs for acute illnesses.

For example, when a patient complaining of symptoms such as paralysis, numbness, or limb weakness is transported by ambulance to an emergency room, a definitive clinical diagnosis, such as cerebral infarction, is not given to the patient until several hours after the patient is transported to the medical institution. Until then, the patient has not been given a definitive clinical diagnosis. On the other hand, when selecting candidates for clinical trials of a new drug for acute diseases such as cerebral infarction, it is necessary to immediately select whether the patient can be a candidate after transport, but conventional systems cannot handle this.

Therefore, when selecting candidates for clinical trials of new drugs for acute illnesses, emergency room doctors can voluntarily contact the clinical trial physician, who can then become aware of the existence of candidate patients, but this places a heavy burden on the emergency room doctor.

In view of the above problems, the inventor invented an information processing system that assists in identifying patients who are candidates for clinical trials.

A first invention is an information processing system that assists in the selection of patients who are candidates for clinical trial subjects, the information processing system having a structuring processing unit that structures text information inputted to a specified screen, and a candidate processing unit that identifies patients who are candidates for clinical trial subjects using the structured information of the input text information and information on clinical trial criteria, wherein the candidate processing unit identifies patients who are candidates for clinical trial subjects using a portion of the information on the clinical trial criteria, excluding at least a clinical diagnosis from the information on the clinical trial criteria, and identifies patients who are candidates for the clinical trial subjects by excluding from the candidates, among the identified patients, patients whose clinical diagnosis includes a clinical diagnosis other than a clinical diagnosis in the information on the clinical trial criteria .

The free-text field of the electronic medical record is an input field in which doctors freely enter text, so there is variation in the notation of clinical diagnoses, symptoms, etc. Therefore, simply matching the information entered in the free-text field of the electronic medical record with the information of the clinical trial criteria does not allow appropriate identification of patients who are candidates for clinical trial subjects. Therefore, as in the present invention, by structuring the text information entered in the free-text field of the electronic medical record or in a screen such as the input screen of the input support processing unit, it is possible to appropriately determine differences in disease attributes, such as whether it is a clinical diagnosis or a pre-existing condition, and identify patients who are candidates for clinical trial subjects. In addition, since the input method is not changed when entering information, the freedom of doctors to enter text information is not impaired.
When selecting patients who are candidates for clinical trials, they are usually selected from patients who have been assigned a confirmed clinical diagnosis to which the new drug is applicable. Therefore, patients who are candidates for clinical trials are selected using a confirmed clinical diagnosis, and patients who have not been assigned a confirmed clinical diagnosis are not selected. However, in the case of acute illnesses, it may be desirable to administer a new drug as part of a clinical trial before a confirmed clinical diagnosis is assigned. Therefore, by using these inventions, it is possible to appropriately select patients who are candidates for clinical trials before a confirmed clinical diagnosis is assigned.

In the above-mentioned invention, the information processing system can be configured as an information processing system having a notification processing unit that outputs, on a screen that displays information about a patient identified by the candidate processing unit, an indication that the patient is a candidate for a clinical trial.

A third invention is an information processing system that assists in the selection of patients who are candidates for clinical trial subjects, the information processing system having a candidate processing unit that identifies patients who are candidates for clinical trial subjects using text information about the patient's disease entered into a specified screen and information about the clinical trial criteria, and a notification processing unit that outputs an indication that the identified patient is a candidate for the clinical trial on a screen displaying information about the identified patient, the candidate processing unit identifying patients who are candidates for the clinical trial subjects using a portion of the information about the clinical trial criteria, excluding at least a clinical diagnosis from the information about the clinical trial criteria, and identifying patients who are candidates for the clinical trial subjects by excluding from the candidates, among the identified patients, patients whose clinical diagnosis includes a clinical diagnosis other than a clinical diagnosis in the information about the clinical trial criteria.

As in these inventions, when a patient who is a candidate for a clinical trial is identified, it is preferable to output an indication that the patient is a candidate for the clinical trial when displaying the patient's information on a specific screen, so that the doctor who examines the patient can recognize that the patient is a clinical trial subject.
When selecting patients who are candidates for clinical trials, they are usually selected from patients who have been assigned a confirmed clinical diagnosis to which the new drug is applicable. Therefore, patients who are candidates for clinical trials are selected using a confirmed clinical diagnosis, and patients who have not been assigned a confirmed clinical diagnosis are not selected. However, in the case of acute illnesses, it may be desirable to administer a new drug as part of a clinical trial before a confirmed clinical diagnosis is assigned. Therefore, by using these inventions, it is possible to appropriately select patients who are candidates for clinical trials before a confirmed clinical diagnosis is assigned.

In the above-mentioned invention, the notification processing unit can be configured as an information processing system that displays information related to the clinical trial on a screen that displays information about the patient identified by the candidate processing unit.

The notification processing unit may display information related to the clinical trial. This allows, for example, a doctor who examined the patient to immediately contact the clinical trial coordinator or the clinical trial physician if a question arises regarding the clinical trial.

In the above-mentioned invention, the notification processing unit can be configured as an information processing system that displays the criteria for the clinical trial and an input field for indicating whether the criteria are met on a screen that displays information about patients identified by the candidate processing unit, and notifies a specified person of the information entered in the input field and information about patients who are candidates for the clinical trial.

When patients who are candidates for clinical trial subjects are automatically selected, there is a possibility that the selection will be incorrect. For this reason, as in the present invention, by displaying a screen including an input field for whether the criteria for the clinical trial are met, a doctor can check and the accuracy can be improved. In addition, by notifying a designated person, such as the clinical trial doctor, after inputting information into the input field, the accuracy of patient selection can be improved.

In the above-mentioned invention, the notification processing unit can be configured as an information processing system that outputs different values: an output indicating that the person is a candidate for a clinical trial based on identification by the candidate processing unit, and an output indicating that the person is a candidate for a clinical trial after an entry has been made in the input field.

This invention makes it easy to distinguish between patients who have been automatically selected as candidates for clinical trials and those whose wishes have been confirmed.

In the above-mentioned invention, the candidate processing unit can be configured as an information processing system that determines whether or not the patient has been given a confirmed clinical diagnosis, and if the patient has been given a confirmed clinical diagnosis, identifies the patient as a candidate for the clinical trial using the clinical diagnosis in the clinical trial criteria information, and if the patient has not been given a confirmed clinical diagnosis, identifies the patient as a candidate for the clinical trial using a part of the clinical trial criteria information excluding at least the clinical diagnosis in the clinical trial criteria information, and identifies the patient as a candidate for the clinical trial by excluding from the candidates those identified whose clinical diagnosis includes a clinical diagnosis other than the clinical diagnosis in the clinical trial criteria information.

When selecting patients who are candidates for clinical trials, they are usually selected from patients who have been assigned a confirmed clinical diagnosis to which the new drug is applicable. Therefore, patients who are candidates for clinical trials are selected using a confirmed clinical diagnosis, and patients who have not been assigned a confirmed clinical diagnosis are not selected. However, in the case of acute illnesses, it may be desirable to administer a new drug as part of a clinical trial before a confirmed clinical diagnosis is assigned. Therefore, by using these inventions, it is possible to appropriately select patients who are candidates for clinical trials before a confirmed clinical diagnosis is assigned.

An eighth invention is an information processing system for supporting the selection of patients who are candidates for clinical trial subjects, the information processing system having a structuring processing unit that structures text information inputted to a specified screen, and a candidate processing unit that identifies patients who are candidates for clinical trial subjects using the structured information of the input text information and information on clinical trial criteria, and when the patient has not been given a definitive clinical diagnosis, the candidate processing unit identifies patients who are candidates for clinical trial subjects using at least the patient's symptoms and disease-related symptoms corresponding to the clinical diagnosis.
A ninth invention is an information processing system that assists in the selection of patients who are candidates for clinical trial subjects, the information processing system having a candidate processing unit that identifies patients who are candidates for clinical trial subjects using text information about the patient's disease entered into a specified screen and information on the clinical trial criteria, and a notification processing unit that outputs an indication that the identified patient is a candidate for the clinical trial on a screen displaying information about the patient, and the candidate processing unit identifies patients who are candidates for clinical trial subjects using at least the patient's symptoms and the disease-related symptoms corresponding to the clinical diagnosis when the patient has not been given a confirmed clinical diagnosis.

In the above-mentioned invention, the candidate processing unit can be configured as an information processing system that, if the patient has not been assigned a confirmed clinical diagnosis, estimates the accuracy of the patient's clinical diagnosis using at least the patient's symptoms and the disease-related symptoms corresponding to the clinical diagnosis, and, if this satisfies a predetermined condition, determines that the patient meets the clinical diagnosis in the clinical trial criteria.

An eleventh invention is an information processing system that assists in the selection of patients who are candidates for clinical trial subjects, the information processing system having a structuring processing unit that structures text information input to a specified screen, and a candidate processing unit that identifies patients who are candidates for clinical trial subjects using the structured information of the input text information and information on clinical trial criteria, wherein if the patient has not been given a confirmed clinical diagnosis, the candidate processing unit outputs the accuracy of the clinical diagnosis of the patient by inputting at least the patient's symptoms as input values into a specified deep learning or machine learning learning model, and if the accuracy of the output clinical diagnosis satisfies specified conditions, the information processing system determines that the patient satisfies the clinical diagnosis in the clinical trial criteria.
A twelfth invention is an information processing system that supports the selection of patients who are candidates for clinical trial subjects, the information processing system having a candidate processing unit that identifies patients who are candidates for clinical trial subjects using text information about the patient's disease inputted into a specified screen and information on clinical trial criteria, and a notification processing unit that outputs an indication that the patient is a candidate for the clinical trial subject on a screen displaying information of the identified patient, wherein, if the patient has not been given a confirmed clinical diagnosis, the candidate processing unit outputs the accuracy of the clinical diagnosis of the patient by inputting at least the patient's symptoms as input values into a specified deep learning or machine learning learning model, and if the accuracy of the output clinical diagnosis satisfies specified conditions, the information processing system determines that the patient satisfies the clinical diagnosis in the clinical trial criteria.

In the eighth and eleventh inventions, the free-text field of the electronic medical record is an input field in which a doctor freely inputs text, so there is variation in the notation of clinical diagnosis names, symptoms, etc. Therefore, simply matching the information input in the free-text field of the electronic medical record with the information of the clinical trial criteria does not allow appropriate identification of patients who are candidates for clinical trial subjects. Therefore, as in the present invention, by structuring the text information input in the free-text field of the electronic medical record or the input screen of the input support processing unit, it is possible to appropriately determine differences in the attributes of the disease, such as whether it is a clinical diagnosis name or a pre-existing condition, and identify patients who are candidates for clinical trial subjects. In addition, since the input method is not changed when inputting, the freedom of input of text information by doctors is not impaired.
In the ninth and twelfth inventions, when a patient who is a candidate for a clinical trial is identified, it is preferable to output an indication that the patient is a candidate for the clinical trial when displaying the patient's information on a specific screen, so that the doctor in charge of the examination can recognize that the patient is a clinical trial subject.
Each of the above mentioned inventions can be used to identify patients who are candidates for clinical trials before they have been given a definitive clinical diagnosis.

The first invention can be realized by loading the program of the present invention into a computer and executing it. That is, the information processing program causes a computer to function as a structuring processing unit that structures text information inputted to a predetermined screen, and a candidate processing unit that identifies patients who are candidates for clinical trial subjects using the structured information of the input text information and information on clinical trial criteria, the candidate processing unit identifying patients who are candidates for clinical trial subjects using part of information on the clinical trial criteria excluding at least a clinical diagnosis from the information on the clinical trial criteria, and excluding from the candidates, from the identified patients, patients whose clinical diagnosis includes a clinical diagnosis other than a clinical diagnosis in the information on the clinical trial criteria, thereby identifying patients who are candidates for the clinical trial subjects .
The third invention can be realized by loading the program of the present invention into a computer and executing it. That is, the information processing program causes a computer to function as a candidate processing unit that identifies a patient who is a candidate for a clinical trial using text information about the patient's disease inputted to a predetermined screen and information about the clinical trial criteria, and as a notification processing unit that outputs, on a screen displaying information about the identified patient, an indication that the patient is a candidate for the clinical trial, and the candidate processing unit identifies a patient who is a candidate for the clinical trial using information about a part of the clinical trial criteria, excluding at least a clinical diagnosis from the information about the clinical trial criteria, and identifies a patient who is a candidate for the clinical trial by excluding from the candidates, among the identified patients, patients whose clinical diagnosis includes a clinical diagnosis other than a clinical diagnosis in the information about the clinical trial criteria.

The eighth invention can be realized by loading the program of the present invention into a computer and executing it. That is, the information processing program causes a computer to function as a structuring processing unit that structures text information inputted to a predetermined screen, and a candidate processing unit that identifies patients who are candidates for clinical trial subjects using information obtained by structuring the input text information and information on clinical trial criteria, and the candidate processing unit identifies patients who are candidates for clinical trial subjects using at least the patient's symptoms and disease-related symptoms corresponding to the clinical diagnosis when the patient has not been given a confirmed clinical diagnosis.
The ninth invention can be realized by loading the program of the present invention into a computer and executing it. That is, the information processing program causes a computer to function as a candidate processing unit that identifies patients who are candidates for clinical trial subjects using text information about the patient's disease entered on a predetermined screen and information about the clinical trial criteria, and as a notification processing unit that outputs, on a screen displaying information about the identified patient, an indication that the patient is a candidate for the clinical trial, and the candidate processing unit is an information processing program that, when the patient has not been given a confirmed clinical diagnosis, identifies patients who are candidates for clinical trial subjects using at least the patient's symptoms and disease-related symptoms corresponding to the clinical diagnosis.
The eleventh invention can be realized by loading and executing the program of the present invention into a computer. That is, the information processing program causes a computer to function as a structuring processing unit that structures text information input to a predetermined screen, and a candidate processing unit that identifies patients who are candidates for clinical trial subjects using the structured information of the input text information and information on clinical trial criteria, and the candidate processing unit is an information processing program that , when a definite clinical diagnosis has not been given to the patient, outputs the accuracy of the clinical diagnosis of the patient by inputting at least the symptoms of the patient as input values into a predetermined deep learning or machine learning learning model, and, when the accuracy of the output clinical diagnosis satisfies a predetermined condition, determines that the patient satisfies the clinical diagnosis in the clinical trial criteria.
The twelfth invention can be realized by loading and executing the program of the present invention into a computer. That is, the information processing program causes a computer to function as a candidate processing unit that identifies a patient who is a candidate for a clinical trial using text information about the patient's disease inputted into a predetermined screen and information about the clinical trial criteria, and a notification processing unit that outputs, on a screen displaying information about the identified patient, an indication that the patient is a candidate for the clinical trial, and the candidate processing unit outputs the accuracy of the clinical diagnosis of the patient by inputting at least the symptoms of the patient as input values into a predetermined deep learning or machine learning learning model when the accuracy of the output clinical diagnosis satisfies a predetermined condition, and determines that the patient satisfies the clinical diagnosis in the clinical trial criteria.

In the information processing system of the present invention, information such as clinical diagnoses entered on a specified input screen is structured and stored, and variations in notation are absorbed, making it possible to select patients who are suitable candidates for clinical trials according to their current clinical diagnoses without interfering with the freedom of doctors to enter information into electronic medical records. In addition, even if a patient does not have a confirmed clinical diagnosis, they can be selected as a candidate for a clinical trial, making this system particularly effective in clinical trials of new drugs for acute illnesses.

1 is a block diagram illustrating an example of the overall processing function of an information processing system according to the present invention. FIG. 2 is a block diagram illustrating an example of a hardware configuration of a computer on which the information processing system of the present invention functions. 4 is a flowchart showing an example of an overall process of the information processing system of the present invention. 1A and 1B are diagrams showing an example of text information entered in a free text field of an electronic medical record and structured information obtained as a result of structuring processing performed on the text information. FIG. 13 is a diagram showing an example of a spelling variation dictionary for disease names. FIG. 13 is a diagram showing an example of a notation variation dictionary for drug names. FIG. 11 is a diagram showing an example of structured information. FIG. 13 is a diagram showing an example of an electronic medical record screen. FIG. 13 is a diagram showing an example of an electronic medical record screen in which information about a clinical trial is extracted from a clinical trial-related information storage unit and displayed as a pop-up window. FIG. 13 is a diagram showing another example of an electronic medical record screen in which information about a clinical trial is extracted from a clinical trial-related information storage unit and displayed as a pop-up window. FIG. 11 is a block diagram illustrating an example of the overall processing function of an information processing system according to a second embodiment. 13 is a flowchart illustrating an example of an overall process of an information processing system according to a second embodiment. 13 is a flowchart illustrating an example of a processing process of a candidate processing unit according to the third embodiment. FIG. 13 is a diagram showing an example of an electronic medical record screen in the third embodiment. FIG. 13 is a diagram showing another example of the electronic medical record screen in the third embodiment. FIG. 13 is a diagram showing another example of the electronic medical record screen in the third embodiment. FIG. 13 is a diagram showing another example of the electronic medical record screen in the third embodiment.

An example of the overall processing function of the information processing system 1 of the present invention is shown in the block diagram of FIG. 1. Also, an example of the hardware configuration of a computer that realizes the information processing system 1 of the present invention is shown in FIG. 2. Note that in the following explanation, an example is given in which the medical professional is a doctor, but the same can be realized in the case of other medical professionals such as dentists.

The information processing system 1 of the present invention is a computer (including portable communication terminals such as smartphones and tablet computers) that executes the processing of the present invention, and is preferably a computer system that is primarily used in medical institutions and research institutions (universities, laboratories, etc.), but is not limited to this.

The computer used in the information processing system 1 has a calculation device 70 such as a CPU that executes the calculation processing of a program, a storage device 71 such as a RAM or a hard disk that stores information, a display device 72 such as a display (screen), an input device 73 such as a keyboard or a pointing device (mouse, numeric keypad, etc.), and a communication device 74 that transmits and receives the processing results of the calculation device 70 and the information stored in the storage device 71 via a network such as the Internet or a LAN. Each function (each means) realized on the computer is executed by loading the means (programs, modules, etc.) that executes the process into the calculation device 70. When each function uses information stored in the storage device 71 in its processing, it reads the corresponding information from the storage device 71 and uses the read information appropriately for the processing in the calculation device 70. In addition, although the information processing system 1 in FIG. 1 is shown as being realized by one computer, the functions may be distributed and arranged on multiple computers. The computer includes various information processing devices such as servers, personal computers, and workstations. It may also be in a so-called cloud format.

If the computer is equipped with a touch panel display, the display device 72 and the input device 73 may be configured as one unit. Touch panel displays are often used in portable communication terminals such as tablet computers and smartphones, but are not limited to this. A touch panel display is a device that integrates the functions of the display device 72 and the input device 73 in that input can be made directly on the display using a specified input device (such as a touch panel pen) or a finger.

The functions of each means in the present invention are only logically distinct, and may be physically or practically the same area. In addition, the processing described in the present invention is merely an example, and the processing process can be changed as appropriate.

The information processing system 1 of the present invention may also be installed in other computer systems used in medical institutions, research institutions, etc., such as electronic medical record systems, and implemented as part of their functions.

The information processing system 1 has a target information storage unit 20, a structuring processing unit 21, a candidate processing unit 22, and a notification processing unit 23.

The subject information storage unit 20 stores information used for processing in the candidate processing unit 22 described below. The subject information storage unit 20 may include, for example, an electronic medical record information storage unit 201, a test information storage unit 202, and a clinical trial-related information storage unit 203, but is not limited to these.

The electronic medical record information storage unit 201 stores information on the electronic medical record of a patient. In addition to the attributes of the patient (personal information on the patient such as name, age, and sex), various information such as information on vital signs, information on the free entry field of the electronic medical record, and severity of the disease (severity score information) are preferably stored. Examples of information on vital signs include, but are not limited to, diastolic blood pressure, systolic blood pressure, body temperature, pulse rate, respiratory rate, and _SpO2 (percutaneous arterial oxygen saturation). Examples of attributes of the patient include, for example, name, age, and sex. Furthermore, the electronic medical record information may further include, for example, JTAS (Japan Triage and Acuity Scale: urgency).

In the free-text section of the electronic medical record, medical staff can freely enter information they have gathered from patients and information from their examinations, for example as text information.

The electronic medical record information storage unit 201 may also store information on nursing records recorded by nurses. The electronic medical record information storage unit 201 may also store information that has been structured from the doctor's free-form comment field in the electronic medical record by the structuring processing unit 21 described below, in association with the electronic medical record information of the patient, preferably the information in the free-form comment field.

The examination information storage unit 202 stores information on various examinations of the patient. The examination information includes, for example, various examination results such as blood tests, electrocardiograms, ultrasound tests, catheter tests, and genetic tests. Image information of examination results from X-rays, CT scans, MRI scans, and the like may also be stored. Furthermore, sound information collected by a stethoscope, sound information of organs, etc. may also be stored. In addition, genetic information from genetic tests may also be stored.

The clinical trial-related information storage unit 203 stores guideline information for selecting subjects for clinical trials of new drugs. For example, criteria indicating what kind of patients should be selected are stored in association with the type of new drug, the type of clinical trial, and the like. The criteria include, for example, "clinical diagnosis name," "age," "comorbid disease (presence or absence of medical history," "presence or absence of regular medication," "ADL (healthiness) before the onset of the disease)," "severity of the disease," and "image findings," but are not limited to these and other criteria may be set. Furthermore, the clinical trial-related information storage unit 203 may include information such as contact information for related parties in addition to the clinical trial criteria, as well as a checklist indicating whether the clinical trial criteria are met. Related parties include, but are not limited to, the clinical trial coordinator and the clinical trial physician.

The information stored in the target information storage unit 20 may include information on electronic medical records managed by the medical institution stored in the electronic medical record information storage unit 201, information on tests stored in the test information storage unit 202, information on clinical trials stored in the clinical trial-related information storage unit 203, and information acquired from outside the medical institution (such as service systems and application systems used by local governments, companies, public institutions, individuals, etc.). For example, the electronic medical record information, test information, health check information, and billing (receipt) information of the patient may be acquired and stored from other medical institutions, local governments, companies, etc. in the region via a regional medical cooperation network. In addition, personal health, medical care, and nursing care information recorded for each medical institution or pharmacy may be acquired from other medical institutions or pharmacies, or from the patient's own computer or external application. Furthermore, vital information of a patient during emergency transport may be acquired and stored from a computer system used by an ambulance team. When information is acquired from an external computer, it is stored in the target information storage unit 20 via an information acquisition unit not shown.

The structuring processing unit 21 structures unstructured information stored in the target information storage unit 20. In particular, it structures text information written in free text fields of electronic medical records stored in the electronic medical record information storage unit 201.

The information recorded in the electronic medical record stored in the electronic medical record information storage unit 201 is roughly divided into "free entry" information and "ordering" information, in addition to the attribute information of the patient. The "free entry" information is information when the doctor examines the patient, and generally includes the chief complaint, current medical history, past medical history, oral medication, etc., obtained from the patient, as well as clinical disease (clinical diagnosis), findings, progress, etc. The chief complaint is the patient's complaint of symptoms, and the current medical history is information indicating when and how the chief complaint started and what progress it has made, and is information accompanying the chief complaint. The past medical history is the patient's past medical history, and oral medication is information indicating the medications the patient regularly takes. The clinical disease (clinical diagnosis) is the name of the disease that the doctor thinks is optimal for the patient's condition and recorded in the free entry field, or a disease name that accurately reflects the patient's disease name. Findings are information that indicates the opinion of the doctor who examined the patient, and history is information that indicates what procedures and prescriptions were given to the patient.

The "ordering" information recorded in electronic medical records is information on the insured disease (insured diagnosis name, insured disease name), instructions given by doctors to nurses and pharmacists regarding procedures and tests for patients, and prescribed medications, and is information that has the same meaning as information on medical receipts. The procedures and tests given to patients are the performed procedures, and the information on prescribed medication is the performed prescription. Insured diseases (insured diagnosis name, insured disease name) are diseases that are given to patients for the sake of convenience in order to provide insured medical treatment. Insured diseases (insured diagnosis name, insured disease name) do not necessarily match clinical diseases (clinical diagnosis names), and are often far removed. For this reason, even doctors often cannot accurately identify a patient's actual disease (clinical disease) from the insured disease alone.

Electronic medical records contain "free text" information, which includes clinically important information, and "ordering" information, which is important from the perspective of insurance claims. However, because the information in the "free text" section is recorded by doctors entering it freely, the information is not structured. For example, free text can be entered in any form of expression using text entry.

The structuring processing unit 21 structures the freely entered text information stored in the target information storage unit 20, for example, text information recorded in the "free text field" of an electronic medical record, by referencing natural language analysis processes such as dependency analysis and context analysis, and dictionary information (not shown), to generate structured information. The structured information may be stored in the electronic medical record information storage unit 201 in association with the free text field of the electronic medical record of the patient. Various technologies can be used for structuring the text information in the structuring processing unit 21, and there are no limitations to these.

The structuring processing unit 21 may also refer to dictionary information to perform spelling variation processing. When there are multiple spellings for the same event, spelling variation processing is a process of unifying them into a standard spelling.

As a computer system used for natural language analysis processing, for example, Microsoft Azure LUIS (Language Understanding) provided by Microsoft Corporation can be used, but it is not limited to this.

Structuring text information means taking freely entered text information and putting it into a standardized form for each predefined information type. For example, it is stored in a table format. One process for structuring text information is as follows:

Based on the text information recorded in the "free text field" of the electronic medical record in the electronic medical record information storage unit 201, tags assigned to predetermined units of text information such as sentences, clauses, and paragraphs are divided into text information with standardized tags (classification of text information by information type) using natural language analysis processing such as referencing dictionary information and context analysis. Since the target information to be extracted for each information type is determined in a medical term dictionary that stores a dictionary of medical terms, the medical term dictionary in the dictionary information is referenced in the text information of each information type to extract the predetermined target information to be extracted. Then, a search is made to see if there is "highly relevant information" (hereinafter referred to as "relevant information") within a predetermined range before and after the extracted target information, for example within 15 characters before and after. If there is, this is extracted as positive and negative expressions for symptoms and disease names described below or additional information (remarks field), and stored in a standardized table as structured information in association with each other.

For example, information types include "history of current illness", "past medical history", "oral medication", "physical findings", and "post-hospital progress", and the corresponding target information includes "symptoms" for the information type "history of current illness", "disease name" as past medical history for the information type "past medical history", "drug name" for the information type "oral medication", and "disease name" as diagnosis for the information type "post-hospital progress". For each target information of an information type, the type of related information to be extracted is stored in advance in correspondence with the information type. Note that the related information can be set arbitrarily, and for example, the above-mentioned LUIS may be used to automatically extract related information for each target information of the information type. A table is then generated for each information type, and the target information and related information are stored in this table. For example, the table for the information type "history of current illness" stores "symptoms" in correspondence with the corresponding positive and negative expressions. It is possible to arbitrarily set what information types to set and how to set the target information and related information for each information type, but there is a set of information types that is generally unified to a certain extent for the records of general doctors and nurses.

By performing the above-mentioned processing in the structuring processing unit 21, it is possible to structure the text information entered in the free-text field, etc. Note that the processing for structuring the free-text field is not limited to the processing described above.

When the structuring processing unit 21 detects an information type in the text information of the "free text field" of the electronic medical record in the electronic medical record information storage unit 201 by natural language analysis processing such as referring to medical terms in the medical term dictionary in the dictionary information, referring to tags indicating the information type stored in the dictionary of the tag pattern of the dictionary information, and context analysis of the text information entered in the "free text field", the structuring processing unit 21 determines whether a table corresponding to the information type, for example, a table of the information type "current illness history", a table of the information type "medical history", a table of the information type "oral medication", a table of the information type "physical findings", and a table of the information type "progress after visit" have already been generated. Then, if a table corresponding to the detected information type has not been generated, the table is generated. In addition, for each text information of the information type, natural language analysis processing and a medical term dictionary in the dictionary information are used to extract target information, and related information is searched for and extracted based on the target information. Then, the target information and related information are sorted and stored in the generated information type table.

On the other hand, if a table corresponding to the detected information type already exists, natural language analysis processing is performed for each text information of the information type, and the medical terminology dictionary in the dictionary information is referenced to extract the target information, and related information is searched for and extracted based on the target information. The extracted target information and related information are then sorted and stored in the table corresponding to the detected information type. The presence or absence of a table corresponding to the information type can be determined by setting a correspondence between the information type and a table in advance, and determining whether or not a table has been generated based on that correspondence.

For the detected target information and related information, the dictionary information is referenced to determine whether the target information or related information contains expressions indicating the names of symptoms, diseases, or medications. If the target information or related information contains any of these, a matching character string is identified in the dictionary information, and the detected target information or related information may be standardized by adding or changing standard notations or codes predetermined in the dictionary information.

For example, if natural language analysis processing technology is used to detect "headache" as target information for text information of the information type "history of current illness," dictionary information is referenced and the standard symptom name is changed to "headache," and the positive/negative expression is determined to be "+," and "headache" and "+" are stored in association with each other in the table of the information type "history of current illness." Similarly, if natural language analysis processing technology is used to detect "aspirin" and "statin" as target information for text information of the information type "oral medication," dictionary information is referenced and the standard drug names are changed to "bay aspirin" and "statin," and their codes (pharmaceutical classification codes) are added, and the information is stored in association with the table of the information type "oral medication."

The structuring processing unit 21 converts the target information and related information for each information type extracted from the text information recorded in the "free text field" as described above into standard notation, adds codes, and stores them in tables for each information type.

For example, when text information is entered in the free text field of the electronic medical record as shown in FIG. 4(a), the structuring processing unit 21 detects the information type "history of current illness" with "S:", the information type "oral medication" with "oral medication:", the information type "physical findings" with "O:", and the information type "progress after hospital visit" with "A/P:" as tags indicating the information type. In addition, the information type "medical history" is detected by contextual analysis of the text information "After catheter treatment for myocardial infarction." Then, the text information between the detected information type and the next information type is extracted as the text information of the information type detected first (including physical extraction and identification as the processing target). That is, the information type "history of current illness" is detected by detecting "S:", and the information type "medical history" is detected by contextual analysis of the text information "After catheter treatment for myocardial infarction." Then, the text information between the information type "history of current illness" and the information type "medical history" is divided as text information corresponding to the information type "history of current illness". Figure 4(b) shows a schematic diagram of text information extracted by information type.

In addition to the above, tags indicating the type of information may be any character string or symbol, such as representing "current medical history" with "#".

Target information is extracted from the text information corresponding to the divided information type "history of current illness" by natural language analysis processing and by referencing the medical term dictionary in the dictionary information. Since target information is associated with each information type, for example, target information "symptoms" is extracted from the information type "history of current illness". At this time, the medical term dictionary in the dictionary information is referenced to extract whether there is a medical term equivalent to "symptoms", rather than whether "symptoms" is included as specific text information. Positive and negative expressions within a specified range are then extracted from the extracted target information "symptoms". The positive and negative expressions are then associated with the extracted "symptoms" and stored in a table.

By dividing the target information into the different information types in this way and storing it in a table as structured information, a table for each information type can be created, as shown in Figure 4 (c).

The processing in the structuring processing unit 21 is not limited to the above-mentioned processing, and can be realized by various natural language analysis processing. For example, natural language analysis processing by deep learning, which executes machine learning by referring to a learning model in which the weighting coefficients between neurons in each layer of a neural network consisting of many intermediate layers are optimized, may be used. In this case, text information recorded in the "free text field" of the electronic medical record in the electronic medical record information storage unit 201 may be input to the learning model, and structured information may be output as the output value. As a learning model, it is possible to use one in which the text information in the "free text field" of the electronic medical record is used as the input value, and the corresponding structured information is given as the correct answer information.

Natural language analysis processing may also be performed using AI (artificial intelligence) that uses deep learning or machine learning, or AI that does not use these. Machine learning such as SVM (support vector machine) may also be used.

The above-mentioned dictionary information stores a notation variation dictionary for determining notation variation for symptom names, disease names, drug names, etc., a pattern table dictionary for negative expressions and ambiguous expressions, a dictionary of frequently occurring abbreviations and specific tag patterns (e.g., "Chief complaint:", "A/P", etc.) according to the purpose of the information processing system 1 such as electronic medical records and nursing records, a medical term dictionary for medical terms, etc. The medical term dictionary may store medical terms that are the target information, and conditions, expressions, and notations for extracting related information that corresponds to the medical terms that are the target information.

In particular, the structuring processing unit 21 extracts target information to be structured information by referring to a medical term dictionary in the dictionary information. The medical term dictionary is a dictionary that stores standard medical terms, and furthermore extracts highly relevant surrounding text information. Therefore, the information extracted through structuring does not include information that is obviously non-medical, such as patient attribute information for the purpose of sharing information among staff at a medical institution.

The notation variation dictionary for symptom names, disease names, and drug names stores, for example, standard notations, codes, and notation patterns for symptom names, disease names, and drug names. Figure 5 shows an example of a notation variation dictionary for disease names, showing a case where standard disease names, ICD codes (international standard codes), disease name conversion codes (domestic general-purpose medical record codes), and notation patterns are stored in correspondence with each other. Figure 6 shows an example of a notation variation dictionary for drug names, showing a case where standard drug names, generic names, pharmacological classification codes, and notation patterns are stored in correspondence with each other.

The dictionary information is not limited to the above, and any dictionary necessary to perform structuring processing based on text information should be provided as appropriate.

An example of information structured by the structuring processing unit 21 is shown in FIG. 7. The structured information is preferably stored in a table format, but is not limited to this. It may also be stored in a database or in some other storage format. FIG. 7(a) is a table of structured information indicating standard symptom names and their presence or absence, FIG. 7(b) is a table of structured information indicating standardized medical history names and corresponding information (remarks), FIG. 7(c) is a table of structured information indicating standardized commonly used drug names and corresponding pharmacological classification codes, and FIG. 7(d) is a table of structured information indicating standardized diagnosis names (clinical diagnosis names) and corresponding information (remarks).

In Figure 7(a), the system is structured by storing the patient's current standardized symptoms (symptoms that have absorbed spelling variations) in association with information indicating their presence or absence, while in Figure 7(b), the system is structured by storing the standardized medical history names (medical history names that have absorbed spelling variations) in association with information regarding them, and in Figure 7(c), the system is structured by storing the standardized commonly used medication names (commonly used medication names that have absorbed spelling variations) in association with codes indicating them. Also, in Figure 7(d), the system is structured by storing the standardized clinical diagnosis names in association with information regarding them (whether a suspected (undetermined) clinical diagnosis name or a confirmed clinical diagnosis name).

In the structuring process in the structuring processing unit 21 described above, the information type does not include "chief complaint", but the information type "chief complaint" may be included. In that case, as in the processing for other information types, a tag corresponding to the information type "chief complaint", for example "#", is set, and by executing the same processing as for other information types, the text information related to the chief complaint can be made into structured information.

The candidate processing unit 22 uses the clinical trial criteria information stored in the clinical trial related information storage unit 203, refers to the electronic medical record information stored in the electronic medical record information storage unit 201 and the test information stored in the test information storage unit 202, and identifies (selects) patients who meet the clinical trial criteria as candidates for clinical trial subjects. For example, as criteria information to be stored in the clinical trial related information storage unit 203, "clinical diagnosis name," "age," "comorbid illness (presence or absence of medical history)," "presence or absence of regular medication," "ADL (healthiness) before the onset of the disease," "severity of the disease," "imaging findings," and the like are extracted, and patients who meet each of these criteria are identified by referring to the electronic medical record information and test information.

As an example, if the criteria stored in the clinical trial-related information storage unit 203 are "cerebral infarction" as the "clinical diagnosis," "60 to 85 years old" as the age, "none" as the "comorbid disease (presence or absence of medical history)," "none" as the "presence or absence of regular medication," "1 or less" (able to walk independently) as the "ADL (health level) before the onset of the disease," and "NIHSS score (stroke severity) 8 to 22 points" as the "severity of the disease," patients who meet each of these criteria are identified as candidates for the clinical trial by referring to the electronic medical record information in the electronic medical record information storage unit 201 and the test information stored in the test information storage unit 202.

When the candidate processing unit 22 identifies a patient as a candidate for a clinical trial, the notification processing unit 23 displays the fact that the patient is a candidate for the clinical trial in the patient's electronic medical record, or notifies the clinical trial physician by email, message, or the like. When making a notification on the identified patient's electronic medical record, information related to the clinical trial information stored in the clinical trial related information storage unit 203, such as the clinical trial criteria, contact information for related parties, and inquiries, may be extracted and displayed. Figure 8 shows an example of a notification of a patient's identification as a candidate for a clinical trial being displayed on the patient's electronic medical record. Figure 8(a) is a part of a normal electronic medical record screen 100, and Figure 8(b) is a part of the electronic medical record screen 100 when a notification 101 of the patient's identification as a candidate for a clinical trial is displayed.

Next, an example of the processing process of the information processing system 1 of the present invention will be explained using the flowchart in Figure 3.

The doctor starts the information processing system 1 of the present invention by performing a predetermined operation. Then, the doctor sequentially inputs the information obtained by interviewing the patient and checking predetermined vital signs into a predetermined input field in the electronic medical record, such as a free-form entry field (S100). Note that test information may be input into the test information input field as necessary.

The information entered in this manner is sequentially stored in the electronic medical record information storage unit 201, the test information storage unit 202, etc. Note that information may be entered automatically from testing equipment, etc. Also, information may be entered into free-form fields and input fields in the electronic medical record by voice, etc.

The structuring processing unit 21 executes structuring processing on the text information entered in the free-text field of the electronic medical record (S110) to generate structured information. For example, "headache" is stored as structured information in the electronic medical record information storage unit 201 as the "chief complaint." The structured information, "headache" associated with the information type "chief complaint," is stored sequentially in the electronic medical record information storage unit 201. Similarly, the structuring processing unit 21 executes structuring processing sequentially on the text information entered in the free-text field of the electronic medical record, and stores it in the electronic medical record information storage unit 201.

At a predetermined timing, the candidate processing unit 22 executes a process to identify candidates for clinical trial subjects who meet the criteria for each clinical trial stored in the clinical trial-related information storage unit 203 (S120). For example, the candidate processing unit 22 uses the information on the clinical trial criteria stored in the clinical trial-related information storage unit 203 to refer to the electronic medical record information stored in the electronic medical record information storage unit 201 and the test information stored in the test information storage unit 202, and identifies patients who meet the clinical trial criteria as candidates for clinical trial subjects.

The candidate processing unit 22 may identify candidates for clinical trial subjects periodically, or may perform the process at any time, such as when new information is entered into the electronic medical record, or when the electronic medical record file of the patient is opened, closed, or saved.

When the electronic medical record of a patient identified by the candidate processing unit 22 is opened, the notification processing unit 23 displays a mark 101 on the screen 100 of the electronic medical record of that patient, indicating that the patient is a candidate for the clinical trial (Figure 8 (b)). Note that the indication of the patient being a candidate for the clinical trial is not limited to a mark, but may be a pop-up window, or any output indicating that the patient is a candidate for the clinical trial, such as outputting a specified sound or changing the display of a specified part of the electronic medical record.

In addition, the notification processing unit 23 may notify the investigator by sending a message indicating that a patient is a candidate for the clinical trial, or by outputting a list, rather than displaying the information on the electronic medical record screen 100. Furthermore, when the indication that the patient is a candidate for the clinical trial is selected, information about the clinical trial may be extracted from the clinical trial-related information storage unit 203 and displayed in a pop-up window 102 as shown in FIG. 9.

In addition, in a display such as the pop-up window 102 shown in FIG. 9, the criteria for clinical trial subjects may be displayed, and an input field such as a check box or text box may be provided for each criterion, and the doctor may check the input field again. After the check is entered, a specific operation, for example, pressing a button 103, may be performed to notify the doctor in charge of the clinical trial. In other words, the notification processing unit 23 may first display in the electronic medical record that the patient is a candidate for the clinical trial, and in the pop-up window 102 or the like displayed there, the doctor in charge of the patient may check again whether the patient meets the criteria for the clinical trial by entering the check box or the like, and then by pressing a button 103 such as "send", a notification may be sent to the doctor in charge of the clinical trial indicating that there is a patient who is a candidate for the clinical trial. An example of the electronic medical record screen in this case is shown in FIG. 10.

In this way, the pop-up window 102 or the like can be provided with an input field such as a checkbox to indicate whether the criteria for the clinical trial are met, and when the doctor makes an input, a display indicating that the patient has become a candidate for the clinical trial due to automatic identification by the candidate processing unit 22 can be output, or a different display can be output. For example, by outputting different information such as changing the display color or displaying "checked by doctor," it becomes easy to distinguish whether the patient was automatically selected or has been checked by a doctor.

By executing the above-mentioned processing, the doctor who examines the patient can immediately recognize that the patient is a candidate for the clinical trial, and the clinical trial can be started quickly. Furthermore, the information processing system 1 of the present invention structures and stores the clinical diagnosis names entered in the free-text fields of the electronic medical record, and absorbs variations in notation, so that patients who are candidates for clinical trial subjects can be appropriately identified without compromising the freedom of doctors to enter information in the free-text fields of the electronic medical record.

In the first embodiment, the processing is performed using text information entered in the free text field of the electronic medical record. However, the processing can also be performed using an input support system (input support processing unit 24 described later) that supports input to the electronic medical record. An example of the system configuration of the information processing system 1 in this case is shown in FIG. 11.

In this case, the information processing system 1 has an input support processing unit 24 and an input information storage unit 204. The input support processing unit 24 is a system that supports text input. When the input support processing unit 24 receives text input, the received text information is reflected, for example, in a free entry field or an ordering field of the electronic medical record. That is, the text information received by the input support processing unit 24 is stored in the electronic medical record information storage unit 201. Here, the text information input on the input screen of the input support processing unit 24 is reflected in which field of the electronic medical record by providing an input field in advance on the input screen of the input support processing unit 24 and corresponding the input field to each field of the electronic medical record. In addition, the text information input on the input screen of the input support processing unit 24 may be reflected in the electronic medical record automatically, or may be reflected manually by, for example, pressing a button provided on the input screen, outputting it as text data, and cutting and pasting it into a free entry field of the electronic medical record.

The text information input by the input support processing unit 24 may be stored in the electronic medical record information storage unit 201, and then the structuring processing unit 21 may execute structuring processing. Alternatively, the structured information (e.g., the tables in FIG. 7 ) obtained after the structuring processing unit 21 executes structuring processing on the text information input by the input support processing unit 24 may be stored in the electronic medical record information storage unit 201. In addition, the text information input by the input support processing unit 24 may be stored in the electronic medical record information storage unit 201, and the structured information (e.g., the tables in FIG. 7 ) obtained after the structuring processing unit 21 executes structuring processing on the text information input by the input support processing unit 24 may be stored in the electronic medical record information storage unit 201.

The input information storage unit 204 stores the text information that is accepted as input by the input support processing unit 24. It may also store structured information after structuring processing is performed by the structuring processing unit 21.

In this embodiment, information is not directly entered into the electronic medical record, but text information entered via an input screen (not shown) of the input support processing unit 24 is reflected in the electronic medical record. Therefore, the input to the input support processing unit 24 may be, for example, entered by a doctor, or may be reflected in the electronic medical record from an input support processing unit 24 provided on a portable communication terminal such as a smartphone used by a medical professional such as a doctor or an emergency medical staff member.

The input screen used by the input support processing unit 24 may be capable of inputting and displaying some or all of the patient's attribute information, information in the free text fields of the electronic medical record, information in the ordering fields, etc., in the same way as the electronic medical record. When displaying electronic medical record information on this input screen, the electronic medical record information of the patient may be sequentially extracted from the electronic medical record information storage unit 201 and displayed.

In addition, when the candidate processing unit 22 identifies a patient open on an input screen used by the input support processing unit 24 as a candidate for a clinical trial, the notification processing unit 23 may display a mark 101 indicating that the patient is a candidate for a clinical trial on the input screen. In this case, when the display indicating that the patient is a candidate for a clinical trial is selected, information regarding the clinical trial may be extracted from the clinical trial-related information storage unit 203, and a pop-up window 102 such as that shown in FIG. 9 may be displayed on the input screen used by the input support processing unit 24.

As in the first embodiment, the pop-up window 102 or the like may display the criteria for the clinical trial subjects, provide an input field such as a check box or text box for each criterion, and the doctor may check the input field again. As in FIG. 10, after the check is entered in the input field of the pop-up window 102, a predetermined operation, for example, pressing a button 103, may be performed to notify the clinical trial doctor. In other words, the notification processing unit 23 may first display on the input screen used by the input support processing unit 24 that the patient is a candidate for the clinical trial subject, and in the pop-up window 102 or the like displayed there, the doctor in charge of the patient may check again whether the patient meets the criteria for the clinical trial by entering the check box or the like, and then press a button 103 such as "send" to send a notification to the clinical trial doctor indicating that there is a patient who is a candidate for the clinical trial subject.

Next, an example of the processing process in this embodiment will be explained using the flowchart in Figure 12.

The doctor starts the information processing system 1 of the present invention by performing a specified operation. Then, the input support processing unit 24 extracts electronic medical record information, such as the attribute information of the patient to be input from the electronic medical record information storage unit 201, and displays it on a specified input screen. Information obtained by interviewing the patient and checking specified vital signs is input sequentially into specified input fields on the input screen of the input support processing unit 24 (S200). The input screen may or may not be divided into patient attribute information, a free entry field, an ordering field, etc.

The information thus input is stored in the input information storage unit 204, as well as in the electronic medical record information storage unit 201, the test information storage unit 202, etc. (S210). As in the first embodiment, information may be input automatically from a test device, etc. Also, input into the free-form entry field and input fields corresponding to the input fields of the electronic medical record may be input by voice, etc.

The structuring processing unit 21 performs structuring processing on the information stored in the input information storage unit 204 or the text information entered in the free text field of the electronic medical record stored in the electronic medical record information storage unit 201 (S220) to generate structured information. This processing is the same as in Example 1.

At a predetermined timing, the candidate processing unit 22 executes a process of identifying candidates for clinical trial subjects who meet the criteria for each clinical trial stored in the clinical trial-related information storage unit 203 (S230). For example, the candidate processing unit 22 uses the information on the clinical trial criteria stored in the clinical trial-related information storage unit 203 to refer to one or more of the electronic medical record information stored in the electronic medical record information storage unit 201, the test information stored in the test information storage unit 202, and the text information entered on the input screen stored in the input information storage unit 204, and identifies patients who meet the criteria for the clinical trial as candidates for clinical trial subjects.

The process by the candidate processing unit 22 to identify candidates for clinical trial subjects may be performed periodically, or may be performed at any time, such as when new information is entered into the electronic medical record or the input screen used by the input support processing unit 24, or when a file of the electronic medical record of the patient or the input screen used by the input support processing unit 24 is opened, closed, or saved.

When the electronic medical record of a patient identified by the candidate processing unit 22 is opened, the notification processing unit 23 displays a mark 101 indicating that the patient is a candidate for the clinical trial on the input screen of the input support processing unit 24 of that patient. Note that the indication of the candidate for the clinical trial is not limited to a mark, but may be a pop-up window, or may output a specified sound, change the display at a specified location on the input screen, or any other output indicating that the patient is a candidate for the clinical trial, as in the first embodiment.

In addition, the notification processing unit 23 may notify the investigator by sending a message indicating that a patient is a candidate for the clinical trial, or by outputting a list, instead of displaying the information on the input screen of the input support processing unit 24. Furthermore, when the indication that the patient is a candidate for the clinical trial is selected, information about the clinical trial may be extracted from the clinical trial-related information storage unit 203 and displayed in a pop-up window 102 as shown in FIG. 9.

In addition, in a display such as the pop-up window 102 shown in FIG. 9, the criteria for the clinical trial subjects may be displayed, and an input field such as a check box or text box may be provided for each criterion, and the doctor may check the input field again. After the check is entered, a specific operation, for example, pressing a button 103, may be performed to notify the clinical trial doctor. In other words, the notification processing unit 23 may first display on the input screen of the input support processing unit 24 that the patient is a candidate for the clinical trial, as in FIG. 10, and in the pop-up window 102 displayed there, the doctor in charge of the patient may check again whether the patient meets the clinical trial criteria by entering the check boxes or the like, and then by pressing a button 103 such as "send", a notification may be sent to the clinical trial doctor indicating that there is a patient who is a candidate for the clinical trial.

In this way, the pop-up window 102 or the like can be provided with an input field such as a checkbox to indicate whether the criteria for the clinical trial are met, and when the doctor makes an input, a display indicating that the patient has become a candidate for the clinical trial due to automatic identification by the candidate processing unit 22 can be output, or a different display can be output. For example, by outputting different information such as changing the display color or displaying "checked by doctor," it becomes easy to distinguish whether the patient was automatically selected or has been checked by a doctor.

By performing the above process, the same effect as in Example 1 can be obtained.

This embodiment is a modification of the first and second embodiments, and describes a case in which patients who are candidates for clinical trial subjects are identified even before a clinical diagnosis is given. An example of the processing process of the candidate processing unit 22 in this case is shown in the flowchart of FIG. 13. Note that the processing process up to the processing in the candidate processing unit 22 in S120 and S230 is the same as in the first and second embodiments.

In this embodiment, since a confirmed clinical diagnosis has not yet been given, the confirmed clinical diagnosis is not written in the free entry field of the electronic medical record. Therefore, the confirmed clinical diagnosis is not stored in the electronic medical record information storage unit 201 and the input information storage unit 204 (a state in which a confirmed standardized diagnosis is not stored, such as a state in which the standardized diagnosis (clinical diagnosis) in FIG. 7(d) is suspect, or a state in which a standardized diagnosis has not been stored).

In the present embodiment, the clinical trial-related information storage unit 203 stores in advance, as criteria for clinical trials, symptoms and test values that are likely to occur in the case of the disease in addition to the clinical diagnosis. For example, in the case of "cerebral infarction" as a "clinical diagnosis," the criteria stored include one or more of the following "symptoms": "paralysis," "numbness," "impaired consciousness," "difficulty walking," and "weakness in the limbs."

The disease and symptoms that are likely to occur with that disease (disease-related symptoms) may be stored in the clinical trial-related information storage unit 203 as the criteria for the clinical trial, or a table may be provided in advance that stores diseases in association with disease-related symptoms. In addition, the disease-related symptoms corresponding to each disease may be identified by deep learning or machine learning, and stored in the clinical trial-related information storage unit 203 or a specified table.

The doctor starts the information processing system 1 of the present invention by performing a predetermined operation. Then, the doctor sequentially inputs the information obtained by interviewing the patient and checking predetermined vital signs into a predetermined input field, such as a free-form entry field, of the input screen used by the electronic medical record or input support processing unit 24 (S300). Note that test information may be input into the test information input field as necessary.

The structuring processing unit 21 executes structuring processing on the text information entered in the free-text field of the electronic medical record or the input screen used by the input support processing unit 24 (S310) to generate structured information. For example, "headache" is stored as structured information as the "chief complaint" in the electronic medical record information storage unit 201 or the input information storage unit 204. The structured information, "headache" associated with the information type "chief complaint", is stored sequentially in the electronic medical record information storage unit 201 or the input information storage unit 204. The structured information, "headache" associated with the information type "chief complaint", is stored sequentially in the electronic medical record information storage unit 201 or the input information storage unit 204. Similarly, the structuring processing unit 21 executes structuring processing sequentially on the text information entered in the free-text field of the electronic medical record or the input screen used by the input support processing unit 24, and stores the information in the electronic medical record information storage unit 201 or the input information storage unit 204.

Then, the candidate processing unit 22 executes a process to identify candidates for clinical trial subjects who meet the criteria for each clinical trial stored in the clinical trial-related information storage unit 203 (S320).

Specifically, the candidate processing unit 22 first extracts information on the criteria for the clinical trial to be stored in the clinical trial-related information storage unit 203. It also determines whether a confirmed standardized diagnosis (clinical diagnosis) is stored in the electronic medical record information storage unit 201 or the input information storage unit 204 for the patient, for example, in the table in FIG. 7(d) (S300).

If the confirmed clinical diagnosis is stored in the electronic medical record information storage unit 201 or the input information storage unit 204, the clinical diagnosis in the extracted clinical trial criteria information is also used, and one or more of the electronic medical record information stored in the electronic medical record information storage unit 201, the test information stored in the test information storage unit 202, and the information stored in the input information storage unit 204 are referenced to identify patients who meet the clinical trial criteria as candidates for clinical trial subjects (S310).

On the other hand, if the confirmed clinical diagnosis is not stored in the electronic medical record information storage unit 201 or the input information storage unit 204, the clinical diagnosis is not used from the extracted clinical trial criteria information, but one or more of the electronic medical record information stored in the electronic medical record information storage unit 201, the test information stored in the test information storage unit 202, and the information stored in the input information storage unit 204 are referenced to identify patients who meet the conditions (S320).

Then, from among the patients identified in S320, patients for whom a clinical diagnosis other than the clinical diagnosis in the extracted clinical trial criteria is stored in the electronic medical record information in the electronic medical record information storage unit 201 or in the information in the input information storage unit 204 are excluded (S330), and the remaining patients are identified as patients who are candidates for the clinical trial (S340), and the notification processing unit 23 displays an indication 101 on the electronic medical record screen 100 or the input screen of the input support processing unit 24 that the patients are candidates for the clinical trial.

For example, the criteria for a certain clinical trial are set as "cerebral infarction (within 12 hours after onset)" as the "clinical diagnosis" (confirmed clinical diagnosis), one or more of "paralysis," "numbness," "impaired consciousness," "difficulty walking," and weakness of the limbs" as the "symptoms," "60 to 85 years old" as the age, "ADL (activity) before the onset of the disease" as "1 or less" (able to walk independently), and "NIHSS score (stroke severity) 8 to 22 points" as the "severity of the disease," and these are stored in the clinical trial-related information storage unit 203. Note that the time from onset of the clinical diagnosis is obtained by the doctor during the examination and entered in the free entry field of the electronic medical record or on the input screen of the input support processing unit 24, and can be determined from appropriate time information such as the onset time information stored in the standard symptom name (table in FIG. 7(a)) and the date and time of transport.

In this case, for a 25-year-old male patient who has been brought to the emergency department, the electronic medical record stores "symptoms" such as "vomiting" and "diarrhea," an "ADL (activity level) before the onset of the disease" of "less than 1," and an "severity of the disease" of "NIHSS score (severity of stroke) 10 points." A doctor at the emergency department may examine the patient and the results of that examination may be stored, or the results of an examination by a doctor at the medical institution who examined the patient before the emergency transport may be stored. In this case, since the patient has just been brought to the emergency department, a confirmed clinical diagnosis is not stored in the electronic medical record information storage unit 201 or the input information storage unit 204, and only standard symptom names and the like are stored. Therefore, since the confirmed clinical diagnosis is not stored in the electronic medical record information storage unit 201 or the input information storage unit 204 (S300), the candidate processing unit 22 determines whether the patient meets the clinical trial criteria without using the "clinical diagnosis" from the clinical trial criteria extracted from the clinical trial-related information storage unit 203 (S320).

The patient in question does not meet the conditions because none of the symptoms "paralysis," "numbness," "impaired consciousness," "difficulty walking," or "weakness in the limbs" are listed in the table of standard symptom names (Figure 7(a)) stored in the electronic medical record information storage unit 201 or the input information storage unit 204. Therefore, the patient is not identified as a candidate for the clinical trial. Therefore, as shown in Figure 14, the notification processing unit 23 does not display that the patient is a candidate for the clinical trial on the electronic medical record screen 100 or the input screen of the input support processing unit 24.

On the other hand, suppose that for a 75-year-old male patient who has been transported to the emergency room, the doctor at the emergency room or the doctor at the medical institution who examined him before the emergency transport has stored in the electronic medical record the following symptoms: "paralysis," "numbness," "ADL (activity) before the onset of the disease" of "1 or less," and "severity of the disease" of "NIHSS score (stroke severity) 10 points." In this case, since the patient has just been transported to the emergency room, the confirmed clinical diagnosis is not stored in the electronic medical record information storage unit 201 or the input information storage unit 204, and only standard symptom names and the like are stored. Therefore, since the confirmed clinical diagnosis is not stored in the electronic medical record information storage unit 201 or the input information storage unit 204 (S300), the candidate processing unit 22 determines whether the patient satisfies the clinical trial criteria without using the "clinical diagnosis" among the clinical trial criteria extracted from the clinical trial-related information storage unit 203 (S320).

The patient has "paralysis" and "numbness" stored as symptoms in the standard symptom name table (FIG. 7(a)) stored in the electronic medical record information storage unit 201 or the input information storage unit 204, and other clinical trial criteria are also met, so the candidate processing unit 22 identifies the patient as a candidate for the clinical trial (S320). And, since no clinical diagnosis (confirmed or suspected) other than "cerebral infarction" is stored in the electronic medical record information storage unit 201 or the input information storage unit 204 for the patient, the patient is not excluded as a clinical trial subject (S330), and the candidate processing unit 22 identifies the patient as a candidate for the clinical trial (S340). Therefore, as shown in FIG. 15, the notification processing unit 23 displays 101 that the patient is a candidate for the clinical trial on the screen 100 of the electronic medical record of the patient or the input screen of the input support processing unit 24 (S130).

In addition, suppose that a 75-year-old male patient who has been brought to the emergency department is examined by a doctor at the emergency department and a doctor at the medical institution where the patient was examined before the emergency transport, and the following symptoms are stored in the electronic medical record: "paralysis," "numbness," "ADL (activity level) before the onset of illness" of "1 or less," "severity of illness" of "NIHSS score (stroke severity) 10 points," and "hyperventilation syndrome" as a "suspected clinical diagnosis." In this case, since the patient has just been brought to the emergency department, the confirmed clinical diagnosis is not stored in the electronic medical record information storage unit 201 or the input information storage unit 204, and only a suspected clinical diagnosis is stored. Therefore, since the confirmed clinical diagnosis is not stored in the electronic medical record information storage unit 201 or the input information storage unit 204 (S300), the candidate processing unit 22 determines whether the patient meets the clinical trial criteria without using the "clinical diagnosis" from the clinical trial criteria extracted from the clinical trial-related information storage unit 203 (S320).

The patient has "paralysis" and "numbness" stored as symptoms in the standard symptom name table (FIG. 7(a)) stored in the electronic medical record information storage unit 201 or the input information storage unit 204, and other clinical trial criteria are also met, so the candidate processing unit 22 identifies the patient as a candidate for the clinical trial (S320). And, because a clinical diagnosis other than "cerebral infarction" (hyperventilation syndrome) is stored as a suspected clinical diagnosis for the patient in the electronic medical record information storage unit 201 or the input information storage unit 204, the patient is excluded as a clinical trial subject (S330). Therefore, as shown in FIG. 16, the electronic medical record screen 100 of the patient or the input screen of the input support processing unit 24 does not display that the patient is a candidate for the clinical trial.

Furthermore, suppose that a 75-year-old male patient who has been brought to the emergency room is examined by a doctor at the emergency room and the following symptoms are stored in the electronic medical record: "paralysis," "numbness," "pre-disease ADL (activity)" of "1 or less," "disease severity" of "NIHSS score (stroke severity) 10 points," and "cerebral infarction" as a "suspected clinical diagnosis." In this case, since the patient has just been brought to the emergency room, a confirmed clinical diagnosis is not stored in the electronic medical record information storage unit 201 or the input information storage unit 204, and only a suspected clinical diagnosis is stored. Therefore, since a confirmed clinical diagnosis is not stored in the electronic medical record information storage unit 201 or the input information storage unit 204 (S300), the candidate processing unit 22 determines whether the patient satisfies the clinical trial criteria without using the "clinical diagnosis" among the clinical trial criteria extracted from the clinical trial-related information storage unit 203 (S320).

The patient has "paralysis" and "numbness" stored as symptoms in the standard symptom name table (FIG. 7(a)) stored in the electronic medical record information storage unit 201 or the input information storage unit 204, and other clinical trial criteria are also met, so the candidate processing unit 22 identifies the patient as a candidate for the clinical trial (S320). And, since no clinical diagnosis other than "cerebral infarction" is stored as a suspected clinical diagnosis for the patient in the electronic medical record information storage unit 201 or the input information storage unit 204, the patient is not excluded as a clinical trial subject (S330). Therefore, as shown in FIG. 17, the notification processing unit 23 displays 101 that the patient is a candidate for the clinical trial on the electronic medical record screen 100 or the input screen of the input support processing unit 24 (S130).

In the above-mentioned candidate processing unit 22, patients who are candidates for clinical trial subjects are identified by the processing of the flowchart in FIG. 13, but this is not limiting, and they can also be identified using disease-related symptoms. For example, instead of using the "clinical diagnosis" in the clinical trial criteria, criteria other than the clinical diagnosis, such as disease-related symptoms that correspond to the "clinical diagnosis" in the clinical trial criteria, can be used to quantify the possibility that the patient can satisfy the clinical trial criteria using a specified algorithm, and if this is higher than a specified threshold, the patient can be identified by a process that determines whether the patient satisfies the criteria for other clinical trials.

As an example of this algorithm, among the structured information stored in the electronic medical record information storage unit 201 or input information storage unit 204 for the patient, a table of structured information indicating the standardized symptom names and their presence or absence (Figure 7(a)) is compared with the disease-related symptoms corresponding to the "clinical diagnosis name" in the criteria for the clinical trial, and the proportion that is met is calculated. Then, if this is higher than a specified threshold, it is possible to identify the patient by determining whether he or she meets the criteria for other clinical trials.

Furthermore, deep learning or machine learning may be used as another process in the candidate processing unit 22. Natural language analysis processing using deep learning is used, which executes machine learning by referring to a learning model in which the weighting coefficients between neurons in each layer of a neural network consisting of many intermediate layers are optimized. In this case, at least the patient's symptoms may be input to the learning model, and the accuracy of the clinical diagnosis of the patient may be output as the output value. As a learning model, it is possible to use one in which disease-related symptoms are input as input values and the corresponding clinical diagnosis is given as correct answer information.

In addition to the symptoms of the patient, information (preferably structured information) stored in the electronic medical record information storage unit 201 or the input information storage unit 204 of the patient and attribute information of the patient may be input as input values, and the accuracy of the clinical diagnosis of the patient may be output as the output value. As a learning model, disease-related symptoms, structured information and attribute information stored in the electronic medical record information storage unit 201 or the input information storage unit 204 of various patients may be used as input values, and the corresponding clinical diagnosis may be given as correct answer information.

In this way, the candidate processing unit 22 estimates the accuracy of the clinical diagnosis of the patient from the patient's symptoms and other information (preferably structured information), and by determining whether it is above a predetermined threshold, estimates whether the clinical diagnosis satisfies the criteria for the clinical trial. This makes it possible to execute processing even if the patient's electronic medical record information storage unit 201 or input information storage unit 204 does not have a "confirmed clinical diagnosis."

Whether the criteria other than the clinical diagnosis in the clinical trial criteria are met can be determined in the same manner as described above.

By performing the above-mentioned processing, the candidate processing unit 22 can identify patients who are candidates for clinical trials even if they have not been given a confirmed clinical diagnosis. This makes it easy to select candidates for clinical trials of new drugs for acute illnesses.

Note that, although the present specification has mainly described the case where the disease is "cerebral infarction," it goes without saying that the same treatment can be applied to other diseases, such as cerebral hemorrhage, subarachnoid hemorrhage, acute myocardial infarction, moderate to severe COVID-19, acute heart failure, pneumonia/COPD (chronic obstructive pulmonary disease) acute exacerbation, head trauma, cerebral contusion, spinal cord injury, fractures and other trauma, anaphylaxis, sepsis, DIC (disseminated intravascular coagulation syndrome), severe respiratory failure, ARDS (acute respiratory distress syndrome), acute pancreatitis and other ICU diseases, asthma, seizures and other diseases that are common in emergency outpatient clinics.

In the information processing system 1 of the present invention, information such as clinical diagnoses entered on a specified input screen is structured and stored, and variations in notation are absorbed, so that patients who are suitable candidates for clinical trials according to their current clinical diagnoses can be selected without interfering with the freedom of doctors to enter information into electronic medical records. In addition, even if a patient does not have a confirmed clinical diagnosis, they can be selected as a candidate for a clinical trial, which is particularly effective in clinical trials of new drugs for acute diseases.

1: Information processing system 20: Subject information storage unit 21: Structuring processing unit 22: Candidate processing unit 23: Notification processing unit 24: Input support processing unit 70: Calculation device 71: Storage device 72: Display device 73: Input device 74: Communication device 100: Electronic medical record screen 101: Mark indicating a candidate for clinical trial subject 102: Pop-up screen of checklist for clinical trial subject 103: Send button 201: Electronic medical record information storage unit 202: Test information storage unit 203: Clinical trial related information storage unit 204: Input information storage unit

Claims (18)

An information processing system for supporting the selection of patients who are candidates for clinical trials,
The information processing system includes:
a structuring processing unit for structuring text information inputted on a predetermined screen;
A candidate processing unit that identifies patients who are candidates for clinical trial subjects using information obtained by structuring the input text information and information on clinical trial criteria,
The candidate processing unit
Identifying patients who are candidates for the clinical trial using a portion of the information on the clinical trial criteria, excluding at least a clinical diagnosis from the information on the clinical trial criteria, and excluding from the candidates, from among the identified patients, patients whose clinical diagnosis includes a clinical diagnosis other than the clinical diagnosis in the information on the clinical trial criteria, thereby identifying patients who are candidates for the clinical trial.
An information processing system comprising: The information processing system includes:
A notification processing unit that outputs, on a screen displaying information on the patient identified by the candidate processing unit, information indicating that the patient is a candidate for a clinical trial;
2. The information processing system according to claim 1, further comprising: An information processing system for supporting the selection of patients who are candidates for clinical trials,
The information processing system includes:
A candidate processing unit that identifies patients who are candidates for clinical trial subjects using text information about the patient's disease entered on a predetermined screen and information about the clinical trial criteria;
A notification processing unit that outputs, on a screen displaying information of the identified patient, an indication that the patient is a candidate for a clinical trial;
The candidate processing unit
Identifying patients who are candidates for the clinical trial using a portion of the information on the clinical trial criteria, excluding at least a clinical diagnosis from the information on the clinical trial criteria, and excluding from the candidates, from among the identified patients, patients whose clinical diagnosis includes a clinical diagnosis other than the clinical diagnosis in the information on the clinical trial criteria, thereby identifying patients who are candidates for the clinical trial.
An information processing system comprising: The notification processing unit includes:
Displaying information related to the clinical trial on a screen displaying information of the patient identified by the candidate processing unit;
4. The information processing system according to claim 2 or 3. The notification processing unit includes:
A screen displaying information on the patient identified by the candidate processing unit displays the criteria for the clinical trial and an input field for whether the criteria are met,
Notifying a predetermined person of the information entered into the input field and the information of the patient who is a candidate for the clinical trial;
5. The information processing system according to claim 2, wherein the information processing system is a data processing system. The notification processing unit includes:
The output indicating that the person is a candidate for a clinical trial subject identified by the candidate processing unit is different from the output indicating that the person is a candidate for a clinical trial subject after input into the input field.
6. The information processing system according to claim 5. The candidate processing unit
determining whether the patient has a confirmed clinical diagnosis;
If the patient has a confirmed clinical diagnosis, the clinical diagnosis is also used in the clinical trial criteria information to identify patients who are candidates for the clinical trial;
If the patient has not been assigned a definite clinical diagnosis, a portion of the information in the clinical trial criteria, excluding at least the clinical diagnosis, is used to identify patients who are candidates for the clinical trial, and among the identified patients, patients whose clinical diagnosis includes a clinical diagnosis other than the clinical diagnosis in the information in the clinical trial criteria are excluded from the candidates, thereby identifying patients who are candidates for the clinical trial.
7. The information processing system according to claim 1, wherein the information processing system is a data processing system. An information processing system for supporting the selection of patients who are candidates for clinical trials,
The information processing system includes:
a structuring processing unit for structuring text information inputted on a predetermined screen;
A candidate processing unit that identifies patients who are candidates for clinical trial subjects using information obtained by structuring the input text information and information on clinical trial criteria,
The candidate processing unit
If the patient does not have a confirmed clinical diagnosis, identifying potential patients using at least the patient's symptoms and disease-related symptoms that correspond to the clinical diagnosis;
An information processing system comprising: An information processing system for supporting the selection of patients who are candidates for clinical trials,
The information processing system includes:
A candidate processing unit that identifies patients who are candidates for clinical trial subjects using text information about the patient's disease entered on a predetermined screen and information about the clinical trial criteria;
A notification processing unit that outputs, on a screen displaying information of the identified patient, an indication that the patient is a candidate for a clinical trial;
The candidate processing unit
If the patient does not have a confirmed clinical diagnosis, identifying potential patients using at least the patient's symptoms and disease-related symptoms that correspond to the clinical diagnosis;
An information processing system comprising: The candidate processing unit
If the patient has not been assigned a definite clinical diagnosis, the accuracy of the clinical diagnosis of the patient is estimated using at least the patient's symptoms and the disease-related symptoms corresponding to the clinical diagnosis, and if the accuracy satisfies a predetermined condition, the patient is determined to meet the clinical diagnosis in the clinical trial criteria.
10. The information processing system according to claim 8 or 9 . An information processing system for supporting the selection of patients who are candidates for clinical trials,
The information processing system includes:
a structuring processing unit for structuring text information inputted on a predetermined screen;
A candidate processing unit that identifies patients who are candidates for clinical trial subjects using information obtained by structuring the input text information and information on clinical trial criteria,
The candidate processing unit
If the patient has not been assigned a definitive clinical diagnosis, at least the symptoms of the patient are input as input values into a predetermined deep learning or machine learning learning model to output the accuracy of the clinical diagnosis of the patient;
If the accuracy of the output clinical diagnosis satisfies a predetermined condition, it is determined that the patient satisfies the clinical diagnosis in the clinical trial criteria.
An information processing system comprising: An information processing system for supporting the selection of patients who are candidates for clinical trials,
The information processing system includes:
A candidate processing unit that identifies patients who are candidates for clinical trial subjects using text information about the patient's disease entered on a predetermined screen and information about the clinical trial criteria;
A notification processing unit that outputs, on a screen displaying information of the identified patient, an indication that the patient is a candidate for a clinical trial;
The candidate processing unit
If the patient has not been assigned a definitive clinical diagnosis, at least the symptoms of the patient are input as input values into a predetermined deep learning or machine learning learning model to output the accuracy of the clinical diagnosis of the patient;
If the accuracy of the output clinical diagnosis satisfies a predetermined condition, it is determined that the patient satisfies the clinical diagnosis in the clinical trial criteria.
An information processing system comprising: Computer,
a structuring processing unit that structures text information inputted on a predetermined screen;
An information processing program that functions as a candidate processing unit that identifies patients who are candidates for clinical trial subjects using structured information of the input text information and information on clinical trial criteria,
The candidate processing unit
Identifying patients who are candidates for the clinical trial using a portion of the information on the clinical trial criteria, excluding at least a clinical diagnosis from the information on the clinical trial criteria, and excluding from the candidates, from among the identified patients, patients whose clinical diagnosis includes a clinical diagnosis other than the clinical diagnosis in the information on the clinical trial criteria, thereby identifying patients who are candidates for the clinical trial.
2. An information processing program comprising: Computer,
A candidate processing unit that identifies patients who are candidates for clinical trial subjects using text information about the patient's disease entered on a predetermined screen and information about the criteria for the clinical trial;
An information processing program that functions as a notification processing unit that outputs, on a screen displaying information of the identified patient, an indication that the patient is a candidate for a clinical trial,
The candidate processing unit
Identifying patients who are candidates for the clinical trial using a portion of the information on the clinical trial criteria, excluding at least a clinical diagnosis from the information on the clinical trial criteria, and excluding from the candidates, from among the identified patients, patients whose clinical diagnosis includes a clinical diagnosis other than the clinical diagnosis in the information on the clinical trial criteria, thereby identifying patients who are candidates for the clinical trial.
2. An information processing program comprising: Computer,
a structuring processing unit that structures text information inputted on a predetermined screen;
An information processing program that functions as a candidate processing unit that identifies patients who are candidates for clinical trial subjects using structured information of the input text information and information on clinical trial criteria,
The candidate processing unit
If the patient does not have a confirmed clinical diagnosis, identifying potential patients using at least the patient's symptoms and disease-related symptoms corresponding to the clinical diagnosis;
2. An information processing program comprising: Computer,
A candidate processing unit that identifies patients who are candidates for clinical trial subjects using text information about the patient's disease entered on a predetermined screen and information about the criteria for the clinical trial;
An information processing program that functions as a notification processing unit that outputs, on a screen displaying information of the identified patient, an indication that the patient is a candidate for a clinical trial,
The candidate processing unit
If the patient does not have a confirmed clinical diagnosis, identifying potential patients using at least the patient's symptoms and disease-related symptoms that correspond to the clinical diagnosis;
2. An information processing program comprising: Computer,
a structuring processing unit that structures text information inputted on a predetermined screen;
An information processing program that functions as a candidate processing unit that identifies patients who are candidates for clinical trial subjects using structured information of the input text information and information on clinical trial criteria,
The candidate processing unit
If the patient has not been assigned a definitive clinical diagnosis, at least the symptoms of the patient are input as input values into a predetermined deep learning or machine learning learning model to output the accuracy of the clinical diagnosis of the patient;
If the accuracy of the output clinical diagnosis satisfies a predetermined condition, it is determined that the patient satisfies the clinical diagnosis in the clinical trial criteria.
2. An information processing program comprising: Computer,
A candidate processing unit that identifies patients who are candidates for clinical trial subjects using text information about the patient's disease entered on a predetermined screen and information about the criteria for the clinical trial;
An information processing program that functions as a notification processing unit that outputs, on a screen displaying information of the identified patient, an indication that the patient is a candidate for a clinical trial,
The candidate processing unit
If the patient has not been assigned a definitive clinical diagnosis, at least the symptoms of the patient are input as input values into a predetermined deep learning or machine learning learning model to output the accuracy of the clinical diagnosis of the patient;
If the accuracy of the output clinical diagnosis satisfies a predetermined condition, it is determined that the patient satisfies the clinical diagnosis in the clinical trial criteria.
2. An information processing program comprising: