TW202111723A - Apparatus and method for processing of a prescription - Google Patents

Abstract

An apparatus and a method for processing a prescription are introduced. The apparatus includes at least one non-transitory computer-readable medium and at least one processor. The at least one non-transitory computer-readable medium and computer executable instructions are configured to, with the at least one processor, cause the apparatus to perform: receiving a first code set comprising at least one diagnosis code and at least one medicine code classification codes; outputting one or more medicine codes of the first code set; receiving a first signal responsive to the output medicine codes; and updating first weights and second weights associated with the output medicine codes in a database in communication with the at least one processor. Therefore, the apparatus and method enhance the accuracy of prescriptions, reduce likelihood of medication errors, cut medical expenditure, and save patients' lives.

Description

Device and method for processing prescription

The present invention relates to a device and method for processing prescriptions. More specifically, the present invention relates to a device and method for detecting drug errors.

Common medication mistakes endanger the health of patients or even cause patients to eventually develop life-threatening illnesses, and greatly and unknowingly increase medical expenses. This will happen if the physician does not consider the patient’s condition at the time of prescription or in the case of cross-reactions between drugs prescribed by different experts.

Statistics report that nearly 100,000 individuals die from preventable medical errors each year in the United States, most of which are drug errors. In addition, the study also reported that 39% of medication errors occurred during the prescription; 12% occurred in prescription transcription/entry; 11% occurred in pharmacy compounding, and 39% occurred in delivery or actual use. Only 2% of drug errors were intercepted at some point in the drug administration process. In view of the above, in order to detect drug errors, it is necessary to provide a device and method for processing prescriptions to help physicians and pharmacists determine the appropriateness of prescriptions.

In order to improve the efficiency of detecting drug errors, we use a collection of data acquisition techniques for identifying diagnosis-drug correlation and drug-drug correlation in order to develop a probability model for processing prescriptions. However, some drugs that can be based on new indications, off-label uses, or doctor’s experience can be detected as drug errors, and frequent warnings or notifications will occur. In addition, some erroneous diagnosis-drug correlations (pseudo correlations) can occur during data collection. For example, antihypertensive agents may have a high correlation with both hypertension and diabetes, because diabetic patients often suffer from hypertension.

In one aspect, according to some embodiments, the device includes at least one non-transitory computer-readable medium and at least one processor. At least one non-transitory computer-readable medium has computer-executable instructions stored therein. At least one processor is coupled to at least one non-transitory computer-readable medium. At least one non-transitory computer-readable medium and computer-executable instructions and at least one processor are configured to cause the device to execute: receive a first code set; output one or more drug codes in the first code set; Output the first message of the medicine code; and update the first weight and the second weight associated with the output medicine code in the database in communication with the at least one processor. The first code set includes at least one diagnostic code and at least one drug classification.

In one aspect, according to some embodiments, the device includes at least one non-transitory computer-readable medium and at least one processor. At least one non-transitory computer-readable medium has computer-executable instructions stored therein. At least one processor is coupled to at least one non-transitory computer-readable medium. At least one non-transitory computer-readable medium and computer-executable instructions and at least one processor are configured to cause the device to execute: receive a first code set; output the diagnostic code and medication code of the first code set to and at least one process A database of device communication, wherein: receiving the first weight and the second weight associated with the diagnostic code and drug code of the first code set from the database; and processing each drug code in the first code set with at least one The device stores the first weight with the largest value. The first code set includes at least one diagnostic code and at least one drug classification. The database includes a first weight (Q _{DM ) between a diagnostic code and a medicine code and a second weight (Q MM} ) between a medicine code and another medicine code, and the first weight and the second weight are greater than zero.

In one aspect, according to some embodiments, the device includes at least one non-transitory computer-readable medium and at least one processor. At least one non-transitory computer-readable medium has computer-executable instructions stored therein. At least one processor is coupled to at least one non-transitory computer-readable medium. At least one non-transitory computer-readable medium and computer-executable instructions and at least one processor are configured to cause the device to execute: receiving the first data between the diagnostic code and the medication code from a database in communication with the at least one processor Weight; and for each drug code, output the first weight with the maximum value to the database communicating with at least one processor.

In one aspect, according to some embodiments, a method for processing a prescription includes: receiving a first code set; outputting one or more medicine codes of the first code set; receiving a first message in response to the output medicine code; And update the first weight and the second weight associated with the output drug code in the database. The first code set includes at least one diagnostic code and at least one drug classification.

In one aspect, according to some embodiments, a method for processing prescriptions includes: receiving a first code set; outputting diagnostic codes and drug codes of the first code set to a database; receiving and receiving the first code from the database The first weight and the second weight associated with the diagnostic code and the medicine code in the set; and for each medicine code in the first code set, the first weight with the largest value is stored. The first code set includes at least one diagnostic code and at least one drug classification. The database includes a first weight between a diagnostic code and a medicine code and a second weight between the medicine code and another medicine code, and the first weight and the second weight are greater than zero.

In one aspect, according to some embodiments, the method for determining the correlation between the diagnostic code and the drug code includes: receiving the first data between the diagnostic code and the drug code from a database in communication with at least one processor. Weight; and for each drug code, output the first weight with the maximum value to the database communicating with at least one processor.

Other aspects and embodiments of the present invention are also considered. The foregoing summary of the invention and the following embodiments are not meant to limit the present invention to any specific embodiments, but only to describe some embodiments of the present invention.

The present invention includes automated technology for identifying the correlation between disease-drug and drug-drug and calculating the strength of the correlation. All diagnostic-drug (DM) and drug-drug (MM) correlations derived from big data of drugs (that is, prescriptions) and their related weights are stored in the knowledge database. The following example illustrates the knowledge database. The medical information is borrowed from the Taiwan National Health Insurance Research Database (Taiwan National Health Insurance Research Database).

Since 2002, it has collected a total of 263.6 million prescriptions for Taiwan National Health Insurance (NHI) claim data. All information is about outpatient visits of hospitals and clinics in Taiwan. Each record (that is, prescription) consists of the date of visit in the NHI code, the patient's pseudo ID, age, gender, first diagnosis and second diagnosis. Each prescription also includes one to three diagnostic codes and 1 to 15 drug codes. 160.1 million prescriptions were excluded due to the following reasons: (a) missing or invalid disease codes or drug codes; and (b) the use of Chinese medicine prescriptions. Therefore, the remaining 103.5 million prescriptions with 204.5 million diagnostic ICD-9-CM (International Statistical Classification of Diseases and Related Health Problems (International Statistical Classification of Diseases and Related Health Problems), 9th revised edition, clinical modification) codes and 347.7 million drugs with Taiwan’s NHI code were used for analysis. These drug codes are mapped to the ATC (Anatomical Therapeutic Chemical) classification code system. The data set consists of 13,070 unique ICD-9-CM codes and 1,548 unique ATC codes. In some embodiments, ICD-10 (International Statistical Classification System of Diseases and Related Health Problems, 10th revised edition), ICD-10-CM (International Statistical Classification System of Diseases and Related Health Problems, 10th revised edition) are used in some embodiments. Clinical revision) or ICD-10-TM (International Statistical Classification System of Diseases and Related Health Problems, 10th revised edition, revised by Thailand).

According to an embodiment of the present invention, the combination of the disease-drug and the drug-drug is related because they appear together in the doctor's prescription for each patient. Relative to its expected probability under the independent hypothesis, the weight (or related intensity value) of the disease-drug and the drug-drug defines the ratio between the diagnosis-drug and the drug-drug combination probability. The weight is labeled Q. The weights of disease-drug and drug-drug are represented by Q _DM and Q _MM respectively.

公式1Based on this definition, a 2×2 chart (see Table 1) is used to calculate the correlation strength of each DM and MM pair. In this chart, for a given rule (X->Y), "a" represents the number of transactions in the database containing both X and Y, "b" is the number containing X but not Y, and "c" It is the number that contains Y but does not contain X, and "d" is the number that does not contain X or Y. C1 and C2 are the total number of prescriptions for diseases and drugs, respectively. Drug Y exists Drug Y does not exist Diagnosis X exists a b a+b (=C1) Diagnosis X does not exist c d a+c (=C2) N (=a+b+c+d) Table 1

Formula 1

According to formula 1, Q _{XY is within the} range of [0, +∞]; where Q _XY =1 indicates that there is no correlation between the diagnosis and the drug, and Q _XY <1 indicates that the diagnosis and the drug are negatively correlated (ie, negative Q _DM ), and Q _XY >1 indicates that the diagnosis and the drug are positively correlated (that is, positive Q _DM -the disease X containing drug Y appears more often than other drugs). In some embodiments, Q _XY is mapped to the range of [0.2, 2].

After processing all the observed correlations between DM and MM, we established a _{database of 1.34 million DM and 650,000 MM pairs (i.e. Q DM} and Q _MM ) with a total Q value (the term is NHI claims database). DM and MM correlations that have less than 5 co-occurrences are regarded as "uncommon or rare correlations" by default and are not included in the database development. In addition, according to some embodiments of the present invention, the threshold of Q is 1. For any correlation (DM or MM) with a Q value less than 1, it is regarded as a negative correlation or an uncommon correlation. The threshold can be adjusted to improve the system.

The present invention provides a system for processing prescriptions. Referring to Figure 1, the system basically includes a computer 1, a database 2, and a client 3. The computer 1, the database 2 and the client 3 are in communication. In one embodiment, the computer 1 and the database 2 are in communication, and the computer 1 and the client 3 are in communication.

In some embodiments, the client 3 includes at least one non-transitory computer-readable medium having computer-executable instructions stored therein; at least one processor coupled to at least one non-transitory computer-readable medium; And input/output modules. At least one non-transitory computer-readable medium and computer-executable instructions and at least one processor are configured to cause the device to perform different operations. In one embodiment, the physician uses the user terminal 3 to input the prescription. The user terminal 3 can be a personal computer, a smart device or a portable electronic device. The prescription entered by the physician is converted or recorded as a code set. The code set includes at least one diagnostic code and at least one medication code. The diagnostic code can be mapped to one of the following: ICD-9-CM, ICD-10, ICD-10-CM and ICD-10-TM code system. The drug code can be mapped to the ATC code system, the LOINC (Logical Observation Identifiers Names and Codes) code system, or the SNOMED (Systematized Nomenclature of Medicine) code system. The code set is output to the computer 1.

Computer 1 receives the code set. Computer 1 can be a server. In some embodiments, the computer 1 includes a central processing unit (CPU) 11 (or processor), a memory 12 (or a non-transitory computer-readable medium), and an input/output module 13. The CPU 11, the memory 12, and the input/output module 13 are in communication. In some embodiments, the memory 12 has computer-executable instructions stored therein. The memory 12 and computer executable instructions and the CPU 11 are configured to enable the computer 1 to perform different operations. The computer 1 outputs the diagnostic code and drug code of the code set to the database 2.

In some embodiments, the database 2 includes at least one non-transitory computer-readable medium having computer-executable instructions stored therein; at least one processor coupled to at least one non-transitory computer-readable medium; And input/output modules. At least one non-transitory computer-readable medium and computer-executable instructions and at least one processor are configured to cause the device to perform different operations. Database 2 receives the code set. The database 2 includes the Q _{DM value between the diagnostic code and the drug code and the Q MM} value between the drug code and another drug code. In some embodiments, the Q _DM value and the Q _MM value are greater than zero. In some embodiments, the Q _DM value and the Q _MM value are in the range of [0, +∞]. In some embodiments, the Q _DM value and the Q _MM value are between 0.2 and 2 (that is, in the range of [0, 2]). _{The database 2 outputs the Q DM} value and Q _MM value associated with the diagnostic code and drug code of the received code set to the computer 1.

The computer 1 receives the Q _DM value and the Q _MM value from the database 2. Based on the Q _DM value and Q _MM value of the code set, the computer 1 processes the prescription. Specifically, the computer 1 determines whether the prescription meets the following criteria: (1) _{The total number of Q DM} values greater than the threshold and Q _MM values greater than the threshold is greater than or equal to the number of drug codes in the code set; (2) Each diagnosis of the code set The code has at least one Q _DM value greater than the threshold; and (3) each drug code of the code set has at least one Q _DM value greater than the threshold or has at least one Q _MM value greater than the threshold.

公式2The above three criteria are expressed mathematically as:

Formula 2

In formula 2, n is the number of diagnostic codes; m is the number of drugs; α is the threshold. Q _{DiMj indicates the Q DM} value between the i-th diagnostic code and the j-th drug code; Q _{MjMk indicates the Q MM} value between the j-th drug code and the k-th drug code. In the present invention, the threshold α is set to 1 by default.

Figure 2 is a schematic diagram of an example of a prescription, where D1, D2, and D3 are the diagnostic codes in the prescription, and M1, M2, M3, M4, and M5 are the drug codes. In one embodiment, the computer 1 outputs the diagnostic codes D1, D2, D3 and the medicine codes M1, M2, M3, M4, and M5 to the database. The database 2 receives the diagnostic codes D1 to D3 and the drug codes M1 to M5, and outputs the relevant Q _DM values and Q _MM values to the computer 1. In the embodiment of FIG. 2 of, the library Output _{Q D1M1, Q D1M2, Q D2M3} , Q D3M4, Q M1M2, Q M1M3, Q M1M4, Q M1M5, Q M2M3, Q M2M4, Q M2M5, Q M3M4, Q M3M5 and Q _M4M5 . In the embodiment of FIG. 2 of _{the, Q D1M1, Q D1M2, Q} D2M3, Q D3M4 and _Q M1M5 positive correlation, and _{Q M1M2, Q M1M3, Q M1M4} , Q M2M3, Q M2M4, Q M2M5, Q M3M4, Q M3M5 And Q _M4M5 is negatively correlated. _{Q D1M1, Q D1M2, Q D2M3} , Q D3M4 and _Q M1M5 greater than a threshold value (defaults to 1), and _{Q M1M2, Q M1M3, Q M1M4} , Q M2M3, Q M2M4, Q M2M5, Q M3M4, Q M3M5 and _Q M4M5 Less than the threshold (default setting is 1).

In some embodiments, if the computer 1 determines that the code set meets all three criteria, the computer 1 will not send a message or alert to the client 3, for example, to check whether the corresponding prescription is appropriate. In some embodiments, if the computer 1 determines that the code set does not meet all three criteria, the computer 1 will send a message or alert to the client 3, for example, to check whether the corresponding prescription is appropriate, and output the message to the client 3. .

In some embodiments, if the client 3 receives a message from the computer 1 indicating that the code set does not meet all three criteria, the client 3 warns or informs the physician or pharmacist to check whether the corresponding prescription is appropriate or should be modified.

The present invention has been evaluated by human experts. First, the present invention conducts initial testing based on the verification data set. Subsequently, human experts including four physicians and three clinical pharmacists conducted a second evaluation of the system to measure the accuracy of the present invention.

Figure 3 is a flow chart of verifying and testing the present invention according to some embodiments of the present invention. In operation 31, 100,000 prescriptions were randomly selected from the 2003 NHI database. Then, the present invention is used to help physicians and pharmacists test the suitability of the selected prescription. In the total of 100,000 prescriptions, 99,004 prescriptions (99.004%) in the present invention are identified as appropriate, and 996 prescriptions (0.996%) are identified as inappropriate.

In operation 32, 400 prescriptions were randomly selected from the 100,000 prescriptions tested in operation 31. The 400 prescriptions selected for evaluation by experts (such as physicians or pharmacists) included 254 (63.5%) appropriate prescriptions and 146 (36.5%) improper prescriptions. In order to facilitate the identification and measurement of prescriptions, all experts explain the purpose of the research and require the identification of the overall prescription information provided to these experts, whether the experts agree, oppose or are not sure. Then, two types of questionnaires are used to evaluate the same prescription-the Q value of the correlation between each DM that exists in the prescription is required or not required. Appropriate and inappropriate prescriptions are identified and mixed in the same questionnaire. We submitted the questionnaire to four physicians in their clinics (200 prescriptions for each physician) and three clinical pharmacists (800 prescriptions for each pharmacist) in the hospital pharmacy. The questionnaire without Q value is first filled out by all experts, and then the questionnaire with Q value is filled in. In total, we administered 3,200 prescriptions (1,600 prescriptions without Q value and 1,600 prescriptions with Q value).

In order to compare the differences and consensus between the system and the experts, the sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) are calculated from the obtained results.

When the Q value was not revealed, the experts responded to 1,590 (99.3%) prescriptions, of which 1,374 (85.9%) were appropriate and 216 (13.5%) were improper prescriptions, and the remaining 10 prescriptions were “unknown”. However, when the Q value was displayed in the prescriptions, experts only responded to 1,587 (99.2%) prescriptions, of which 1,313 (82.1%) were appropriate, 274 (17.1%) were improper prescriptions, and 13 prescriptions belonged to The class is "unknown" (see Figure 3).

The accuracy of the system was evaluated by the clinical pharmacist and the results obtained are shown in Table 2. When Q is revealed, the average sensitivity, PPV, and NPV are 68.8%, 95.6%, and 24.6% of pharmacists, respectively. The change found in the questionnaire showing the Q value is different from the change in the questionnaire not showing the Q value. However, the average sensitivity, PPV and NPV were 74.3%, 98.7% and 40.6%, respectively. _{Q DM is} not displayed,% Display Q _DM ,% expert Sens Spec PPV NPV Sens Spec PPV NPV Physician 74.3 82.7 94.8 43.1 76.7 84.9 94.8 50.3 pharmacist 68.8 75.0 95.6 24.6 74.3 94.2 98.7 40.6 overall 71.5 78.9 95.2 33.9 75.5 89.5 96.7 45.5 Abbreviations: Sens, sensitivity; Spec, specificity; PPV, positive predictive value; NPV, negative predictive value. Note: The confidence interval (CI) of each parameter is small and is omitted from the self-reported results. Table 2

Based on the results described above, the present invention provides a prescription analysis method that uses a probability model as an effective tool when automatically identifying uncommon or rare correlations between disease-drug and drug-drug in a prescription. The present invention not only helps to reduce medication errors by alerting physicians to check the marked prescriptions, but also improves the safety of patients and the overall quality of health care.

The present invention further provides operations executed by the computer 1 for processing prescriptions. FIG. 4 is a flowchart of operations executed by the computer 1 according to some embodiments of the present invention. In some embodiments, the memory 12 has computer-executable instructions stored therein. The memory 12 and computer executable instructions and the CPU 11 are configured to enable the computer 1 to perform operations.

In operation 41, the computer 1 receives the code set. The code set includes at least one diagnostic code and at least one medication code. In some embodiments, the code set is received from the user terminal 3, and the physician enters the prescription on the user terminal. The diagnostic code can be mapped to one of the following: ICD-9-CM, ICD-10, ICD-10-CM and ICD-10-TM code system. The drug code can be mapped to the ATC code system, LOINC (Logical Observation Identifier Name and Code) code system, or SNOMED (Systematic Medical Naming) code system.

In operation 42, the computer 1 outputs the received code set to the database 2. The database 2 includes the Q _{DM value between the diagnostic code and the drug code and the Q MM} value between the drug code and another drug code. In some embodiments, the database 2 queries and outputs the _{relevant Q DM} value and Q _MM value according to the input diagnostic code and drug code.

In operation 43, the computer 1 receives the Q _DM value and the Q _MM value associated with the code set output to the database 2.

In operations 44, 45, and 46, the computer 1 determines whether the received code set satisfies the criteria. Specifically, the computer 1 determines _{whether the Q DM} value and Q _MM value associated with the code set satisfy all the following three criteria: (1) _{The total number of Q DM} values greater than the threshold and Q _MM values greater than the threshold is greater than or equal to The number of drug codes in the code set; (2) Each diagnostic code in the code set has at least one Q _DM value greater than the threshold; and (3) Each drug code in the code set has at least one Q _DM value greater than the threshold or has at least one Q DM value greater than The Q _MM value of the threshold (the threshold is set to 1 by default).

In some embodiments, determining _{whether the Q DM} value and the Q _MM value associated with the code set satisfy all the following three criteria (ie, operations 44, 45, and 46) can be explored using flags. The computer 1 generates a flag. Computer 1 sets the flag equal to 0 by default. The computer 1 compares _{the total number of Q DM} values greater than the threshold and Q _MM values greater than the threshold with the number of drug codes in the code set. If the total number of the first weight of the first code set greater than the threshold and the second weight of the first code set greater than the threshold is less than the number of drug codes in the first code set, the computer 1 sets the flag equal to 1; for the code set For each diagnostic code, the computer 1 compares the Q _DM value with the threshold value. _{If the Q DM} value of the diagnostic code of the code set is less than or equal to the threshold, the computer 1 sets the flag equal to 1. For each drug code in the code set, the computer 1 compares the Q _DM value with the threshold value and compares the Q _MM value with the threshold value. _{If the Q DM} value and Q _MM value of the drug code in the code set are less than or equal to the threshold, the computer 1 sets the flag equal to 1. If the flag is equal to 0, the Q _DM value and Q _MM value associated with the code set satisfy all three criteria above. If the flag is equal to 1, the Q _DM value and Q _MM value associated with the code set do not satisfy all three criteria above.

_{If the Q DM} value and Q _MM value associated with the code set meet all the above three criteria, computer 1 will not output a message. _{If the Q DM} value and Q _MM value associated with the code set do not satisfy all three criteria above, the computer 1 outputs a message in operation 47. In some embodiments, the computer 1 outputs the message to the client 3 in operation 47. In some embodiments, if the client 3 receives a message from the computer 1 indicating that the code set does not meet all three criteria, the client 3 warns or informs the physician to check whether the corresponding prescription is appropriate or should be modified.

FIG. 5 is a flowchart of operations executed by the computer 1 according to some embodiments of the present invention. In some embodiments, the memory 12 has computer-executable instructions stored therein. The memory 12 and computer executable instructions and the CPU 11 are configured to enable the computer 1 to perform operations.

In operation 51, the computer 1 receives the code set. The code set includes at least one diagnostic code and at least one medication code. In some embodiments, the code set is received from the user terminal 3, and the physician enters the prescription on the user terminal. The diagnostic code can be mapped to one of the following: ICD-9-CM, ICD-10, ICD-10-CM and ICD-10-TM code system. The drug code can be mapped to the ATC code system, LOINC (Logical Observation Identifier Name and Code) code system, or SNOMED (Systematic Medical Naming) code system.

In operation 52, the computer 1 outputs the received code set to the database 2. The database 2 includes the Q _{DM value between the diagnostic code and the drug code and the Q MM} value between the drug code and another drug code. In some embodiments, the database 2 queries and outputs the _{relevant Q DM} value and Q _MM value according to the input diagnostic code and drug code.

In operation 53, the computer 1 receives the Q _DM value and the Q _MM value associated with the code set output to the database 2.

During the generation of the Q _DM value and Q _{MM value from the prescription database or the acquisition of these} values in the prescription database (such as the NHI claims database), some false diagnosis-drug correlations (pseudo correlations) may occur. For example, antihypertensive agents may have a high correlation with both hypertension and diabetes, because diabetic patients often suffer from hypertension. Therefore, antihypertensive agents are often present in prescriptions with the diagnosis of hypertension and diabetes. For this reason, anti-hypertensive agent with respect to the blood pressure value and a high Q _DM diabetes have a high relative value Q _DM. However, antihypertensive agents and diabetes should not have high Q _DM values. The high correlation between antihypertensive agents and diabetes is called pseudo-correlation.

In operation 54, for each drug code in the code set, the computer 1 only stores the maximum Q _DM value and discards other Q _DM values (or only stores the correlation with the maximum Q _DM value). For a prescription Examples of antihypertensive agents, hypertension and diabetes, as not every patient is suffering from hypertension, diabetes, although hypertension antihypertensive agents having a high relative value with respect to Q _DM diabetes having a high Q _DM value, but Q _DM value between hypertension and antihypertensive agents is greater than the value Q _DM between diabetes and antihypertensive agents. After operation 54, the false correlation between the antihypertensive agent and diabetes is removed.

According to some embodiments, in operation 54, for each drug code of the code set, the computer 1 not only stores the maximum Q _DM value, but also stores the Q _DM value associated with the diagnostic code in the same set of diagnostic codes of the _{maximum Q DM} value. For examples of prescriptions with antihypertensive agents, essential hypertension, benign essential hypertension and diabetes, because the Q _DM value between antihypertensive agents and essential hypertension (for example, in ICD-9- The diagnostic code 401) in the CM code system is the maximum value, which stores the maximum Q _DM value between the antihypertensive agent and essential hypertension, and also stores the benign primary in the same group as the essential hypertension _{Q DM} value associated with hypertension (for example, diagnosis code 4011, benign essential hypertension).

According to some embodiments, in operation 54, for each drug codes, computer 1 stores not only has the highest correlation _DM value Q, and stored with a Q and diagnosis codes in the same set of diagnostic codes maximum _DM value in Q's associated with the _DM Correlation of values. For examples of prescriptions with antihypertensive agents, essential hypertension, benign essential hypertension and diabetes, because the Q _DM value between antihypertensive agents and essential hypertension (for example, in ICD-9- The diagnostic code 401) in the CM code system is the maximum value. The maximum Q _DM value between the antihypertensive agent and the essential hypertension is stored, and the benign primary in the same group as the essential hypertension is also stored. Correlation of Q _DM values associated with hypertension (for example, diagnosis code 4011, benign essential hypertension).

In operation 55, the computer 1 determines whether the received code set satisfies all three criteria as disclosed in operations 44, 45, and 46. Specifically, operation 55 includes operations 44, 45, and 46 shown in FIG. 4. In operation 55, if the computer 1 determines that the stored Q _DM value and Q _MM value associated with the code set satisfy all three criteria disclosed in operations 44, 45, and 46 as shown in FIG. 4, the computer 1No message will be output.

In operation 55, if the computer 1 determines that the stored Q _DM value and Q _MM value associated with the code set do not satisfy all three criteria disclosed in operations 44, 45, and 46 as shown in FIG. 4, then The computer 1 outputs a message in operation 56. In some embodiments, the computer 1 outputs the message to the client 3 in operation 56. In some embodiments, if the client 3 receives a message from the computer 1 indicating that the code set does not meet all three criteria, the client 3 warns or informs the physician to check whether the corresponding prescription is appropriate or should be modified.

Table 3 shows five exemplary prescriptions for _{calculating Q DM} values according to Table 1 and Formula 1. Table 4 shows essential hypertension (i.e. diagnostic code (ICD9) 4019) and drugs used for diabetes (i.e. drug code (ATC code) A10AB03, A10AB04, A10AC01, A10AD05, A10AE05, A10BA02, A10BA03, A10BB01, A10BB02 And A10BB07) Q _DM value between. Table 4 shows that the correlation between essential hypertension and drugs used for diabetes is highly positive. The correlation between essential hypertension and the drugs used for diabetes shown in Table 4 is called pseudo-correlation. If the pseudo-correlation shown in Table 4 is not removed, the prescription processing will be wrong. Prescription 1 Diagnosis: {hypertension} Medication: {lisinopril, multivitamin} Prescription 2 Diagnosis: {diabetes, hypertension} Drugs: {insulin, metformin, lisinopril} Prescription 3 Diagnosis: {diabetes} Drug: {insulin} Prescription 4 Diagnosis: {diabetes} Drug: {metformin} Prescription 5 Diagnosis: {Polycystic Ovary Syndrome} Drug: {Metformin} table 3 Diagnostic code (ICD9) Drug code (ATC code) Q _DM 4019 A10AB03 5.42 4019 A10AB04 2.67 4019 A10AC01 4.24 4019 A10AD05 4.23 4019 A10AE05 4.84 4019 A10BA02 5.14 4019 A10BA03 4.06 4019 A10BB01 4.82 4019 A10BB02 5.85 4019 A10BB07 4.97 Table 4

FIG. 6 is a flowchart of operations executed by the computer 1 according to some embodiments of the present invention. In some embodiments, the memory 12 has computer-executable instructions stored therein. The memory 12 and computer executable instructions and the CPU 11 are configured to enable the computer 1 to perform operations.

In operation 61, the computer 1 receives the code set. The code set includes at least one diagnostic code and at least one medication code. In some embodiments, the code set is received from the user terminal 3, and the physician enters the prescription on the user terminal. The diagnostic code can be mapped to one of the following: ICD-9-CM, ICD-10, ICD-10-CM and ICD-10-TM code system. The drug code can be mapped to the ATC code system, LOINC (Logical Observation Identifier Name and Code) code system, or SNOMED (Systematic Medical Naming) code system.

In operation 62, the computer 1 determines whether the received code set satisfies all three criteria as disclosed in operations 44, 45, and 46. Specifically, operation 62 includes operations 42, 43, 44, 45, and 46 shown in FIG. 4. In operation 62, the computer 1 outputs the received code set to the database 2, receives the Q _DM value and the Q _MM value associated with the code set output to the database 2, and determines the stored value associated with the code set Whether the Q _DM value and Q _MM value satisfy all three criteria of operations 44, 45, and 46 shown in FIG. 4. In operation 62, if the computer 1 determines that the stored Q _DM value and Q _MM value associated with the code set satisfy all three criteria disclosed in operations 44, 45, and 46 as shown in FIG. 4, the computer 1No message will be output.

In operation 62, if the computer 1 determines that the received code set does not satisfy all three criteria disclosed in operations 44, 45, and 46 as shown in FIG. 4, the computer 1 outputs a message in operation 63. In some embodiments, the computer 1 outputs the message to the user terminal 3 in operation 63. In some embodiments, the computer 1 outputs at least one medicine code to the user terminal 3. At least one drug code output from the computer 1 to the user terminal 3 has at least one Q _DM value smaller than the threshold (default setting is 1) or has at least one Q _MM value smaller than the threshold (default setting 1). That is, the at least one medicine code output by the computer 1 has at least one negative correlation with one diagnostic code of the received code set or at least one negative correlation with another medicine code of the received code set. In some embodiments, if the client 3 receives a message from the computer 1 indicating that the received code set does not meet all three criteria disclosed in operations 44, 45, and 46 as shown in FIG. 4, the client 3 Notify or warn the physician to check whether the corresponding prescription is appropriate or should be modified. In some embodiments, if the client 3 receives at least one drug code from the computer 1 indicating that the received code set does not satisfy all three criteria disclosed in operations 44, 45, and 46 as shown in FIG. 4, then The user terminal 3 notifies (or warns) the physician of at least one modifiable medication code and notifies (or warns) the physician to check whether the corresponding medication is appropriate or should be modified.

In operation 64, the computer 1 determines whether the code set (which does not satisfy all three criteria) has been modified. Specifically, if the code set (which does not satisfy all three criteria) has not been modified within a period of time (for example, the client 3 is enabled), the computer 1 receives the first type of message. In addition, if the code set (which does not satisfy all three criteria) is modified within a period of time (for example, the client 3 is enabled), the computer 1 receives the second type of message.

If the computer 1 receives the second type of message in operation 64, the computer 1 performs operation 65 to receive another code set (for example, from the client 3). After operation 65, the computer 1 performs operation 62 to determine whether the code set received in operation 65 satisfies all three criteria as disclosed in operations 44, 45, and 46.

If the computer 1 receives the first type of message in operation 64, the computer 1 performs operation 66 to update the Q _DM value and Q _MM value associated with the output drug code output in operation 63. _{Specifically, the computer 1 updates the Q DM} value and Q _MM value in (or stored in) the database 2 associated with the output drug code output in operation 63. _{In some embodiments, the computer 1 updates the Q DM} value and the Q _MM value associated with the output drug code that are smaller than the threshold value (set to 1 by default) in operation 63.

In some embodiments, by the value of Q _DM and Q _MM to update the value of a number is multiplied by the value of Q _DM and Q _MM value. In some embodiments, the number to be multiplied is greater than one. In some embodiments, _{the DM} Q value by _MM and a number Q value updated by adding the value of _{the DM} and Q values Q _MM. In some embodiments, the number to be added is greater than zero.

Because some drugs are based on new indications, off-label use, or physician experience, these drugs can be determined as not meeting all three criteria disclosed in operations 44, 45, and 46 as shown in Figure 4, and will Frequent warnings or notifications appear. The physician in charge of the prescription has checked the warning or notice generated by the present invention, and the physician has decided not to modify the prescription. _{The Q DM} value and Q _MM value associated with the drug code output in operation 63 are updated to avoid frequent warnings or notifications.

In operation 67, the computer 1 confirms that the received code satisfies all three criteria disclosed in operations 44, 45, and 46 as shown in FIG. 4. Because the physician has checked that the code set (that is, the prescription) does not meet the warnings or notifications of all three criteria and has decided not to modify the prescription, the code set (that is, the prescription) has been double-checked by the physician. Therefore, it should be believed that it is confirmed in operation 67 that the received code set satisfies all three criteria.

The operation shown in FIG. 6 is verified by 938 notifications (for example, the message sent in operation 63) and 12 experts (for example, physicians or pharmacists). In the result, for every three experts, there is one expert who agrees to the notification at a percentage of 85%. It should be noted that in the absence of operations to update the Q _DM and Q _MM values (such as operations 66 and 67), the expert agrees to the notification with a percentage less than 30%.

FIG. 7 is a flowchart of operations executed by the computer 1 according to some embodiments of the present invention. In some embodiments, the memory 12 has computer-executable instructions stored therein. The memory 12 and computer executable instructions and the CPU 11 are configured to enable the computer 1 to perform operations.

The operation shown in FIG. 7 is a combination of the operations shown in FIG. 5 and FIG. 6. Specifically, operations 51, 52, 53, 54 and 55 and operations 63, 64, 65, 66 and 67 in FIG. 5 are applied to FIG. 7. For the sake of simplicity, the details of FIG. 7 are not described here, please refer to the disclosure of operations 51, 52, 53, 54, 55, 63, 64, 65, 66, and 67 above. Based on the disclosures of operations 51, 52, 53, 54, 55, 63, 64, 65, 66, and 67 above, those familiar with the art should understand the operations shown in FIG. 7.

FIG. 8 is a flowchart of operations executed by the computer 1 according to some embodiments of the present invention. In some embodiments, the memory 12 has computer-executable instructions stored therein. The memory 12 and computer executable instructions and the CPU 11 are configured to enable the computer 1 to perform operations.

In some embodiments, after calculating the disease-drug weight (Q _DM value) and the drug-drug weight (Q _MM value) as disclosed in paragraphs 0020 to 0023, the operations shown in FIG. 8 are performed. In some embodiments, the operations shown in FIG. 8 can be used to further process the Q _DM values and Q _MM values stored in the database 2.

During the generation of the Q _DM value and Q _{MM value from the prescription database or the acquisition of these} values in the prescription database (such as the NHI claims database), some false diagnosis-drug correlations (pseudo correlations) may occur. For example, antihypertensive agents may have a high correlation with both hypertension and diabetes, because diabetic patients often suffer from hypertension. Therefore, antihypertensive agents are often present in prescriptions with the diagnosis of hypertension and diabetes. For this reason, anti-hypertensive agent with respect to the blood pressure value and a high Q _DM diabetes have a high relative value Q _DM. However, antihypertensive agents and diabetes should not have high Q _DM values. The high correlation between antihypertensive agents and diabetes is called pseudo-correlation.

In operation 81, the computer 1 receives the Q _DM value. In some embodiments, the diagnostic code can be mapped to one of the ICD-9-CM, ICD-10, ICD-10-CM, and ICD-10-TM code systems, and the drug code can be mapped to the ATC code system, LOINC (Logical Observation Identifier Name and Code) code system or SNOMED (Systematic Medical Naming) code system.

In operation 82, for each drug code, the computer 1 only stores the maximum Q _DM value and discards other Q _DM values (or only stores the correlation with the maximum Q _DM value). For a prescription Examples of antihypertensive agents, hypertension and diabetes, as not every patient is suffering from hypertension, diabetes, although hypertension antihypertensive agents having a high relative value with respect to Q _DM diabetes having a high Q _DM value, but Q _DM value between hypertension and antihypertensive agents is greater than the value Q _DM between diabetes and antihypertensive agents. After operation 82, the false correlation between the antihypertensive agent and diabetes is removed.

According to some embodiments, in operation 82, for each drug code, the computer 1 not only stores the maximum Q _DM value, but also stores the Q _DM value associated with the diagnostic code in the same set of diagnostic codes _{with the maximum Q DM} value. For examples of prescriptions with antihypertensive agents, essential hypertension, benign essential hypertension and diabetes, because the Q _DM value between antihypertensive agents and essential hypertension (for example, in ICD-9- The diagnostic code 401) in the CM code system is the maximum value, which stores the maximum Q _DM value between the antihypertensive agent and essential hypertension, and also stores the benign primary in the same group as the essential hypertension _{Q DM} value associated with hypertension (for example, diagnosis code 4011, benign essential hypertension).

According to some embodiments, in operation 82, for each drug codes, computer 1 stores not only correlated with the maximum Q _DM value, and stored with a Q and diagnosis codes in the same set of diagnostic codes maximum _DM value in Q's associated with the _DM Correlation of values. For examples of prescriptions with antihypertensive agents, essential hypertension, benign essential hypertension and diabetes, because the Q _DM value between antihypertensive agents and essential hypertension (for example, in ICD-9- The diagnostic code 401) in the CM code system is the maximum value, and the maximum Q _DM value between the antihypertensive agent and essential hypertension is stored, and it also stores the benign factors that are in the same group as the essential hypertension. Correlation of Q _DM values associated with essential hypertension (for example, diagnosis code 4011, benign essential hypertension).

In operation 83, the processed Q _DM value is output to the database 2 and stored in the database 2.

After operations 81 to 83, the pseudo correlation in the _{Q DM value is removed. The processed Q DM} value and Q _MM value stored in the database 2 can be used for the operations shown in FIG. 4 or FIG. 6.

Table 5 shows five exemplary prescriptions for _{calculating Q DM} values according to Table 1 and Formula 1. Without the operation shown in Figure 8, Table 6 shows essential hypertension (i.e. diagnostic code (ICD9) 4019) and drugs for diabetes (i.e. drug code (ATC code) A10AB03, A10AB04, A10AC01, A10AD05, A10AE05, A10BA02, A10BA03, A10BB01, A10BB02 and A10BB07) between the Q _DM values. Figure 6 shows that the correlation between essential hypertension and drugs used for diabetes is highly positive. The correlation between essential hypertension and the drugs used for diabetes shown in Table 6 is called pseudo-correlation.

After the operation shown in Figure 8, Table 7 shows essential hypertension (i.e. diagnostic code (ICD9) 4019) and drugs for diabetes (i.e. drug code (ATC code) A10AB01, A10AC01, A10AD01, A10AD05 Q _DM value between, A10BA02, A10BA03, A10BB01, A10BB02 , A10BB05 and A10BB07). Table 7 shows that the correlation between essential hypertension and drugs used for diabetes is negative. The pseudo-correlation between essential hypertension and the drugs used for diabetes shown in Table 6 is removed. Prescription 1 Diagnosis: {hypertension} Medication: {lisinopril, multivitamin} Prescription 2 Diagnosis: {diabetes, hypertension} Drugs: {insulin, metformin, lisinopril} Prescription 3 Diagnosis: {diabetes} Drug: {insulin} Prescription 4 Diagnosis: {diabetes} Drug: {metformin} Prescription 5 Diagnosis: {Polycystic Ovary Syndrome} Drug: {Metformin} table 5 Diagnostic code (ICD9) Drug code (ATC code) Q _DM 4019 A10AB03 5.42 4019 A10AB04 2.67 4019 A10AC01 4.24 4019 A10AD05 4.23 4019 A10AE05 4.84 4019 A10BA02 5.14 4019 A10BA03 4.06 4019 A10BB01 4.82 4019 A10BB02 5.85 4019 A10BB07 4.97 Table 6 Diagnostic code (ICD9) Drug code (ATC code) Q _DM 4019 A10AB03 0.04 4019 A10AB04 0.06 4019 A10AC01 0.06 4019 A10AD05 0.06 4019 A10AE05 0.23 4019 A10BA02 0.03 4019 A10BA03 0.15 4019 A10BB01 0.11 4019 A10BB02 0.15 4019 A10BB07 0.19 Table 7

Unless the context clearly dictates otherwise, as used herein, the singular terms "a/an" and "the" may include plural referents. For example, unless the context clearly dictates otherwise, a reference to an electronic device may include multiple electronic devices.

As used herein, the terms "connected/connection", "communication" and "in communication" refer to operating coupling or linking. Components in communication can be directly or indirectly coupled or connected to each other via, for example, another set of components.

In addition, quantities, ratios, and other numerical values are sometimes presented in range format in this article. It should be understood that such range formats are used for convenience and brevity, and should be flexibly understood to include not only the values explicitly designated as range limits, but also all individual values or sub-ranges covered within that range, as if clearly Specify the values and sub-ranges in general.

Although the present invention has been described and illustrated with reference to specific embodiments thereof, these descriptions and illustrations are not restrictive. Those familiar with the art should understand that various changes can be made and equivalents can be substituted without departing from the true spirit and scope of the present invention as defined by the scope of the appended patent application. The diagram does not have to be drawn to scale. Due to the manufacturing process and tolerances, there may be differences between the technical reproduction in the present invention and the actual device. There may be other embodiments of the invention that are not specifically described. The description and drawings should be regarded as illustrative rather than restrictive. Modifications can be made to adapt specific situations, materials, material compositions, methods, or manufacturing processes to the objectives, spirit, and scope of the present invention. All such modifications are intended to be within the scope of the patent application attached herewith. Although the methods disclosed herein have been described with reference to specific operations performed in a specific order, it should be understood that these operations can be combined, subdivided, or reordered to form equivalents without departing from the teachings of the present invention. method. Therefore, unless specifically indicated otherwise herein, the order and grouping of operations is not a limitation of the present invention.

1: computer 2: Database 3: User side 11: Central Processing Unit 12: Memory 13: Input/output module 31: Operation 32: Operation 41: Operation 42: Operation 43: Operation 44: Operation 45: Operation 46: Operation 47: Operation 51: Operation 52: Operation 53: Operation 54: Operation 55: Operation 56: Operation 61: Operation 62: Operation 63: Operation 64: Operation 65: Operation 66: Operation 67: Operation 81: Operation 82: Operation 83: Operation D1: Diagnostic code D2: Diagnostic code D3: Diagnostic code M1: Drug code M2: Drug code M3: Drug code M4: Drug code M5: Drug code

In order to better understand the essence and objectives of some embodiments of the present invention, the following detailed descriptions should be made with reference to the accompanying drawings. In the drawings, unless otherwise specified, the same or functionally same elements are given the same reference numerals.

Figure 1 illustrates a system according to some embodiments of the invention.

Figure 2 illustrates the correlation between diagnosis and medication according to some embodiments of the present invention.

Figure 3 is a flow chart of verification and testing according to some embodiments of the present invention.

Fig. 4 is a flowchart of operations according to some embodiments of the present invention.

Figure 5 is a flowchart of operations according to some embodiments of the present invention.

Fig. 6 is a flowchart of operations according to some embodiments of the present invention.

Fig. 7 is a flowchart of operations according to some embodiments of the present invention.

Fig. 8 is a flowchart of operations according to some embodiments of the present invention.

61: Operation

62: Operation

63: Operation

64: Operation

65: Operation

66: Operation

67: Operation

Claims (20)

A device comprising: At least one non-transitory computer-readable medium having computer-executable instructions stored therein; and At least one processor coupled to the at least one non-transitory computer-readable medium, Wherein the at least one non-transitory computer-readable medium and the computer-executable instructions and the at least one processor are configured to cause the device to execute: Receiving a first code set, the first code set including at least one diagnostic code and at least one medication code; Output one or more drug codes in the first code set; Receive the first message in response to the output drug code; and The first weight and the second weight associated with the output drug code in the database in communication with the at least one processor are updated. Such as the device of claim 1, wherein if the first code set is not modified within a period of time, the first message is received. Such as the device of claim 1, wherein the database includes a first weight between a diagnosis code and a medicine code and a second weight between the medicine code and another medicine code, and the first weights and the first weights The second weight is greater than zero. Such as the device of claim 3, where: The output drug code has at least one first weight smaller than the threshold value or has at least one second weight smaller than the threshold value. Such as the device of claim 3, wherein the device is further caused to execute: Generate flags; Set the flag to 0; Comparing the total number of the first weights of the first code set greater than a threshold and the second weights of the first code set greater than the threshold with the number of drug codes in the first code set; If the total number of the first weights of the first code set greater than the threshold and the second weights of the first code set greater than the threshold is less than the number of drug codes in the first code set, then the flag is set equal to 1; For each diagnostic code in the first code set, compare the first weight with the threshold; If the first weights of the diagnostic codes of the first code set are less than or equal to the threshold, then the flag is set to 1; For each drug code in the first code set, compare the first weight with the threshold and compare the second weight with the threshold; and If the first weight and the second weight of the drug codes of the first code set are less than or equal to the threshold, then the flag is set to 1. Such as the device of claim 5, where: The device is further made to execute: if the flag is equal to 1, output one or more medicine codes of the first code set. Such as the device of claim 5, wherein the device is further caused to execute: Receiving the second message in response to the output drug code; Receiving a second code set including at least one diagnostic code and at least one drug code; Set the flag to 0; Comparing the total number of the first weights of the second code set greater than the threshold and the second weights of the second code set greater than the threshold with the number of drug codes in the second code set; If the total number of the first weights of the second code set greater than the threshold and the second weights of the second code set greater than the threshold is less than the number of drug codes in the second code set, then the flag is set equal to 1; For each diagnostic code in the second code set, compare the first weight with the threshold; If the first weights of the diagnostic codes of the second code set are less than or equal to the threshold, then the flag is set to 1; For each drug code in the second code set, compare the first weight with the threshold and compare the second weight with the threshold; and If the first weight and the second weight of the drug codes of the second code set are less than or equal to the threshold, then the flag is set equal to 1. Such as the device of claim 7, wherein if the first code set is modified within a period of time, the second message is received. Such as the device of claim 5, wherein, after updating the first weights and the second weights associated with the output drug code in the database in communication with the at least one processor, the device further executes: Verify that the flag is equal to 0. Such as the device of claim 3, wherein the update of the first weights and the second weights includes one of the following: Multiply the first weights and the second weights by a number; and The weight includes adding the first weights and the second weights to a number. A method for processing prescriptions, which includes: Receiving a first code set, the first code set including at least one diagnostic code and at least one medication code; Output one or more drug codes in the first code set; Receive the first message in response to the output drug code; and Update the first weight and the second weight associated with the output drug code in the database in the communication. Such as the method of claim 11, wherein if the first code set has not been modified within a period of time, the first message is received. Such as the method of claim 11, wherein the database includes a first weight between a diagnostic code and a medicine code and a second weight between the medicine code and another medicine code, and the first weight and the second weights The weight is greater than zero. Such as the method of claim 13, where: The output drug code has at least one first weight smaller than the threshold value or has at least one second weight smaller than the threshold value. Such as the method of claim 13, which further includes: Generate flags; Set the flag to 0; Comparing the total number of the first weights of the first code set greater than a threshold and the second weights of the first code set greater than the threshold with the number of drug codes in the first code set; If the total number of the first weights of the first code set greater than the threshold and the second weights of the first code set greater than the threshold is less than the number of drug codes in the first code set, then the flag is set equal to 1; For each diagnostic code in the first code set, compare the first weight with the threshold; If the first weights of the diagnostic codes of the first code set are less than or equal to the threshold, then the flag is set to 1; For each drug code in the first code set, compare the first weight with the threshold and compare the second weight with the threshold; and If the first weight and the second weight of the drug codes of the first code set are less than or equal to the threshold, then the flag is set to 1. Such as the method of claim 15, which further includes: If the flag is equal to 1, output one or more drug codes of the first code set. Such as the method of claim 15, which further includes: Receiving the second message in response to the output drug code; Receiving a second code set including at least one diagnostic code and at least one drug code; Set the flag to 0; Comparing the total number of the first weights of the second code set greater than the threshold and the second weights of the second code set greater than the threshold with the number of drug codes in the second code set; If the total number of the first weights of the second code set greater than the threshold and the second weights of the second code set greater than the threshold is less than the number of drug codes in the second code set, then the flag is set equal to 1; For each diagnostic code in the second code set, compare the first weight with the threshold; If the first weights of the diagnostic codes of the second code set are less than or equal to the threshold, then the flag is set to 1; For each drug code in the second code set, compare the first weight with the threshold and compare the second weight with the threshold; and If the first weight and the second weight of the drug codes of the second code set are less than or equal to the threshold, then the flag is set equal to 1. Such as the method of claim 17, wherein if the first code set is modified within a period of time, the second message is received. Such as the method of claim 15, which further includes: After updating the first weights and the second weights associated with the output drug code in the database in communication with the at least one processor, it is confirmed that the flag is equal to 0. Such as the method of claim 13, wherein updating the first weights and the second weights includes one of the following: Multiply the first weights and the second weights by a number; and Add the first weights and the second weights to a number.

Images