CN120299591B - Intelligent analysis method and system for clinical test data - Google Patents
Intelligent analysis method and system for clinical test dataInfo
- Publication number
- CN120299591B CN120299591B CN202510779609.1A CN202510779609A CN120299591B CN 120299591 B CN120299591 B CN 120299591B CN 202510779609 A CN202510779609 A CN 202510779609A CN 120299591 B CN120299591 B CN 120299591B
- Authority
- CN
- China
- Prior art keywords
- target
- data
- physiological
- index
- data point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/20—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for electronic clinical trials or questionnaires
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to an intelligent analysis method and system for clinical test data, wherein the method comprises the following steps: obtaining a data sequence of each physiological index of a patient, calculating the deviation degree by quantifying the difference between a target data point and a normal range of the corresponding physiological index, calculating an abnormal index based on the deviation degree and the distribution characteristics of corresponding data in the data sequence of the corresponding physiological index, obtaining a fitting curve of each physiological index by fitting the abnormal index, screening a time period when all the fitting curves are in an ascending trend, taking a physiological index pair with the correlation larger than a preset value in the time period meeting the screening condition as a target index pair, constructing a causal graph by using a PC algorithm based on the target index pair, and identifying the causal relationship of each physiological index. The invention can reduce the complexity of constructing the causal graph by the PC algorithm while keeping the important causal relation among the physiological indexes.
Description
Technical Field
The invention relates to the technical field of data processing. More particularly, the invention relates to an intelligent analysis method and system for clinical test data.
Background
Along with the rapid development of modern clinical tests, data acquisition technologies are increasingly diversified, and massive heterogeneous data is generated by data sources such as electronic medical records, gene sequencing, wearable sensors, medical images and the like. Particularly in a remote patient monitoring scene, the wearable device acquires multidimensional physiological indexes such as heart rate, blood pressure, blood glucose level, motion quantity and the like in real time, and forms a high-density and high-dimensional time sequence data stream. The scale and complexity of such data presents a significant challenge to traditional causal reasoning approaches.
In the related art, a constraint-based causal discovery Algorithm, such as the PC Algorithm (Peter-Clark Algorithm), can identify causal relationships between different health indicators, and is generally used to construct causal graphs between health indicators and predict intervention effects. The PC algorithm comprises the core steps of (1) constructing a complete undirected graph, (2) gradually eliminating the undirected edges through a zero-order and high-order condition independence test, and (3) determining a causal relationship direction based on an orientation rule.
However, in high-dimensional, large-scale data scenarios, high-order conditional independence tests require traversing exponentially growing combinations of condition variables, resulting in dramatic increases in computational complexity. For example, for a dataset containing tens of physiological indexes such as heart rate, blood pressure, blood sugar level, etc., the algorithm needs to perform millions of independent tests, which is not only too long in time, but also is easy to cause erroneous judgment (such as false causality or missing real association) due to multiple hypothesis test problems, thereby affecting the effect prediction of intervention measures, resulting in clinical decision deviation and lowering the system reliability.
Disclosure of Invention
The invention provides an intelligent analysis method and system for clinical test data, which aims to solve the problems that the calculation complexity of a PC algorithm is high when the causal relation of each physiological index is identified due to huge clinical test data amount, and the accuracy of a constructed causal graph is affected.
According to a first aspect of the present invention, there is provided a method for intelligent analysis of clinical trial data, comprising:
acquiring clinical test data of a patient and preprocessing the clinical test data to obtain a data sequence of each physiological index aligned in time, wherein the physiological indexes comprise heart rate, blood pressure and blood sugar level;
selecting a target data point from a data sequence of the target physiological index, and determining the deviation degree of the target data point by quantifying the difference between the target data point and the normal range of the target physiological index at the corresponding moment;
Calculating an abnormality index of the target data point based on the deviation degree and the occurrence frequency and the average time interval of the data point with the same value as the target data point in the data sequence of the target physiological index, wherein the abnormality index is positively correlated with the occurrence frequency and the deviation degree and is negatively correlated with the average time interval;
The method comprises the steps of obtaining fitting curves of all physiological indexes by fitting abnormal indexes of data points in a data sequence of the physiological indexes, screening time periods when all fitting curves are in ascending trend, taking a physiological index pair with correlation larger than a preset value in the time period meeting screening conditions as a target index pair, and constructing a causal graph by using a PC algorithm based on the target index pair to identify causal relation of all the physiological indexes.
According to the invention, the abnormality index and the time persistence are comprehensively considered, the target index pair is screened, and the physiological index which has great influence on the health of the patient can be accurately identified, so that the causal relationship of each physiological index of the patient can be visualized on the basis of the causal graph constructed by the screened target index, and the accuracy of the constructed causal graph is ensured while the data quantity required to be processed when the causal graph is constructed by a PC algorithm is reduced.
Preferably, the method for acquiring the deviation degree of the target data point comprises the following steps:
If the value of the target data point is larger than the upper limit value of the normal range, the ratio of the difference between the value of the target data point and the upper limit value to the upper limit value is used as the deviation degree of the target data point;
If the value of the target data point is smaller than the lower limit value of the normal range, the ratio of the difference between the lower limit value and the value of the data point to the lower limit value is used as the deviation degree of the target data point;
And if the value of the target data point is in the normal range, setting the deviation degree of the target data point to be zero.
The invention can normalize the deviation degree to a relative proportion, which enables the deviation degree of different indexes to be compared on the same scale, and avoids the difficulty of comparison caused by the difference of the index dimension or the numerical range.
Preferably, when the health range of the target physiological index is affected by the movement amount of the patient, the method for acquiring the normal range includes:
Taking the product of the difference between the motion quantity of the patient at the corresponding moment of the target data point and the preset motion quantity threshold value and the preset weight as a variation, acquiring a static health range of the target physiological index, and updating a lower limit value and an upper limit value of the static health range through summation operation based on the variation;
and acquiring the maximum value in the lower limit values before and after updating and the minimum value in the upper limit values before and after updating, and taking the range formed by the maximum value and the minimum value as the normal range.
The normal range of each physiological index is dynamically adjusted, so that the normal change condition of the physiological index influenced by the motion quantity of a patient can be avoided, the physiological index is misjudged to be abnormal, and the accuracy of the deviation degree of each data point is ensured.
Preferably, when the health range of the target physiological index is a fixed range, the static health range of the target physiological index is used as the normal range of the target physiological index at each moment.
Preferably, the method for acquiring the abnormality index of the target data point includes:
taking the opposite number of the average time interval as the power of an exponential function, and performing power operation to obtain a severity index;
and carrying out normalization processing on the occurrence frequency, calculating the accumulated sum of the obtained normalization value and the severity index, and carrying out normalization processing on the product of the accumulated sum and the severity index to obtain the abnormality index of the target data point.
The method can comprehensively consider the frequency and the time interval of the abnormality, obtains a quantized abnormality index through weighted accumulation and normalization processing, has comparability, and enables the abnormality indexes of different data points to be compared on the same scale, thereby providing a quantized basis for subsequent screening operation.
Preferably, the method for obtaining the fitting curve of each physiological index by fitting the abnormal indexes of the data points in the data sequence of each physiological index comprises the following steps:
And respectively carrying out curve fitting on the abnormal indexes of all the data points in the data sequence of each physiological index by using a least square method to obtain a fitting curve of each physiological index.
Preferably, screening the time period in which all the fitted curves are in an ascending trend includes:
and acquiring slope values of data points in each fitting curve, and if the slope values of the data points on all the fitting curves in any time period are positive, reserving any time period to obtain the time period meeting the screening condition.
Preferably, the method for acquiring the target index pair comprises the following steps:
And calculating absolute values of Spearman correlation coefficients of data sequences of any two physiological indexes in any time period for any time period meeting the screening condition to obtain the correlation of corresponding physiological index pairs, and taking the physiological index pairs with the correlation larger than a preset correlation threshold as target index pairs.
The invention screens the target index pairs by utilizing the correlation, and can ensure that the screened target index pairs have important causal relations, thereby providing a data basis for the construction of the follow-up causal graph.
Preferably, when the causal graph is constructed by using the PC algorithm based on the target index pairs, the condition variable of any one target index pair is a physiological index with average correlation with any one target index pair being greater than a set value in the same time period.
According to a second aspect of the present invention there is provided a method of intelligent analysis of clinical trial data, the system comprising a memory and a processor, the memory having stored thereon a computer program, the processor executing the computer program to carry out the steps of the first aspect of the present invention.
The invention has the following effects:
The method and the system can accurately evaluate the possibility of abnormality of each data point by integrating multiple indexes to determine the abnormality index of each data point, and can facilitate the determination of the variation trend of each physiological index by a fitting mode, so that the physiological index pair with important relation, namely the target index pair, can be rapidly and accurately screened out by evaluating the correlation of any two physiological index pairs based on the abnormality duration of each physiological index, and the causal relation among each physiological index can be more accurately identified when a causal graph is constructed based on the screened target index pair, thereby effectively reducing the calculation complexity of a PC algorithm when large-scale data is processed and ensuring the accuracy of the constructed causal graph.
Drawings
The above, as well as additional purposes, features, and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description when read in conjunction with the accompanying drawings. In the drawings, embodiments of the invention are illustrated by way of example and not by way of limitation, and like reference numerals refer to similar or corresponding parts and in which:
Fig. 1 is a schematic flow chart of steps of an intelligent analysis method for clinical test data according to an embodiment of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.
Referring to fig. 1, an intelligent analysis method for clinical test data includes steps S1 to S4, specifically as follows:
s1, acquiring clinical test data of a patient and preprocessing to obtain a data sequence of each physiological index aligned in time, wherein the physiological indexes comprise heart rate, blood pressure and blood sugar level.
Specifically, clinical test data (such as heart rate, blood pressure, blood glucose level, etc.) of the patient in the last day can be continuously collected from the wearable device, the sensor or the electronic medical record system of the patient according to a fixed sampling frequency, such as 1 time/minute, so as to obtain a heart rate data sequence, a blood pressure data sequence, a blood glucose level data sequence, etc.
Alternatively, the total number of samples can be counted asThe heart rate data may be sequencedIs marked asSequence of blood pressure dataIs marked asSequence of blood glucose level dataIs marked asIn the formula (I), in the formula (II),、AndRespectively the firstA heart rate value, a blood pressure value, and a blood glucose level value acquired a second time; Is the sampling order; Is the total number of samplings.
It should be noted that, in order to eliminate the influence of different physiological index dimensions and align the data sequences of each physiological index in time, normalization processing, such as maximum and minimum normalization processing, needs to be performed on the data sequences of each physiological index.
Also, when the sampling frequencies of the different types of sensors are different, resampling techniques (e.g., up-sampling or down-sampling) may be required to align the data sequences of the physiological indices in time.
Optionally, when any physiological index at any sampling moment has a missing value, a linear interpolation mode is adopted to replace the missing value, so as to ensure the data integrity of the physiological index at each sampling moment. The normalization process, the resampling technique and the linear interpolation method are all the prior art, and the embodiment is not described in detail here.
S2, selecting a target data point from the data sequence of the target physiological index, and determining the deviation degree of the target data point by quantifying the difference between the target data point and the normal range of the target physiological index at the corresponding moment.
The target physiological index refers to a physiological index selected randomly, the target data point refers to a data point selected randomly from a data sequence of the target physiological index, and the deviation degree refers to the deviation between the value of the target data point and the normal level of the target physiological index.
In an exemplary embodiment of the present invention, when the health range of the target physiological index is affected by the movement amount of the patient, the determination of the normal range of the target physiological index at each moment may be achieved by:
The method comprises the steps of taking the product of the difference between the motion quantity of a patient at the moment corresponding to a target data point and a preset motion quantity threshold value and a preset weight as a variable quantity, obtaining a static health range of a target physiological index, updating a lower limit value and an upper limit value of the static health range through summation operation based on the variable quantity, obtaining the maximum value in the lower limit value before and after updating and the minimum value in the upper limit value before and after updating, and taking the range formed by the maximum value and the minimum value as a normal range.
It should be noted that, in the exercise state, the change of the physiological index (such as heart rate and blood glucose level) of the human body belongs to normal physiological reaction, and is not a health problem. If the data in the exercise state is evaluated using the health range in the stationary state (static health range), a false judgment phenomenon may be caused. Therefore, the embodiment provides a method for dynamically adjusting the health range, which aims at the physiological index influenced by the exercise amount of the patient and adjusts the normal range of the patient in real time according to the exercise state of the patient, so that erroneous judgment is avoided and the accuracy of evaluation is improved.
Specifically, the normal range of the heart rate at any time satisfies the following relation:
;
in the formula, At heart rate of60 And 100 are respectively a lower limit value and an upper limit value of a static health range of the heart rate, wherein the static health range of the heart rate refers to the health range of the heart rate which is monitored when the exercise amount of a patient is lower than a set exercise amount threshold value, and is usually 60-100 times/min;、 respectively, the return value is a function of the maximum value and the minimum value; To the patient at the first The amount of motion at the moment; For the preset motion amount threshold value, The value of (2) is estimated by a doctor aiming at the actual exercise capacity of the patient, and can effectively distinguish the physiological state of the patient, and 0.01 is a preset weight for controlling the adjustment amplitude of the heart rate boundary value.
Normal range of blood glucose levels at any instantThe following relation is satisfied:
;
in the formula, Is at the first blood sugar levelThe normal range of time, 3.9 and 6.1 are respectively a lower limit value and an upper limit value of a static health range of the blood sugar level, wherein the static health range of the blood sugar level refers to the health range of the monitored blood sugar level, which is usually 3.9-6.1mmol/L when the exercise amount of a patient is lower than a set exercise amount threshold value, and 0.02 is a preset weight of the blood sugar level and is used for controlling the adjustment range of the blood sugar level limit value.
In an exemplary embodiment of the present invention, when the health range of the target physiological index is a fixed range, the static health range of the target physiological index is used as the normal range of the target physiological index at each moment.
For example, for a physiological index such as blood pressure, where the health range is not affected by the exercise amount of the patient, the static health range of blood pressure can be directly used as the normal range of blood pressure at each moment. Wherein, the static health range of blood pressure refers to the health range of the monitored blood pressure, which is usually 70-100mmHg when the exercise amount of the patient is lower than the set exercise amount threshold value.
Further, after determining the normal range of each physiological index at each time, the degree of deviation of each data point in the data sequence of each physiological index can be calculated.
In an example embodiment of the present invention, the determination of the degree of deviation of each data point in the data sequence of each physiological index may be achieved by:
If the value of the target data point is larger than the upper limit value of the normal range, the ratio of the difference between the value of the target data point and the upper limit value to the upper limit value is used as the deviation degree of the target data point;
If the value of the target data point is smaller than the lower limit value of the normal range, the ratio of the difference between the lower limit value and the value of the data point to the lower limit value is used as the deviation degree of the target data point;
And if the value of the target data point is in the normal range, setting the deviation degree of the target data point to be zero.
Optionally, if the target data point is the first in the heart rate data sequenceData points, heart rate can be set at the firstThe lower limit value of the normal range at each moment is recorded asThe heart rate is at the firstThe upper limit value of the normal range at each moment is recorded asThe degree of deviation of the target data point satisfies the relationship:
;
in the formula, Is the first in the heart rate data sequenceDegree of deviation of data points; is the first in the heart rate data sequence Data points;、 Heart rates respectively at the first A lower limit value and an upper limit value of a normal range at each time; Representative of Is at heart rateWithin the normal range of the individual moments.
The determination method of the deviation degree of each data point in the data sequence of other physiological indexes is the same as the determination method of the deviation degree of each data point in the heart rate data sequence, and the description of the embodiment is omitted here.
And S3, calculating an abnormality index of the target data point based on the deviation degree and the occurrence frequency and the average time interval of the data point with the same value as the target data point in the data sequence of the target physiological index, wherein the abnormality index is positively correlated with the occurrence frequency and the deviation degree and is negatively correlated with the average time interval.
In an exemplary embodiment of the present invention, the determination of the abnormality index for each data point in the data sequence of each physiological index may be achieved by:
the method comprises the steps of taking the opposite number of an average time interval as the power of an exponential function, carrying out power operation to obtain a severity index, carrying out normalization processing on the occurrence frequency, calculating the accumulated sum of the obtained normalization value and the severity index, and carrying out normalization processing on the product of the accumulated sum and the severity index to obtain an abnormal index of a target data point.
Exemplary, when the target data point is the first in the heart rate data sequenceWhen the data points are obtained, the abnormality index of the target data points meets the following relation:
;
in the formula, Is the first in the heart rate data sequenceAbnormality index of data points; is the first in the heart rate data sequence Degree of deviation of data points; take value and the first in heart rate data sequence The number of data points is the same as the number of data points; is the total number of data points in the heart rate data sequence; take value and the first in heart rate data sequence Average time interval of data points with the same data point; to be with natural constant An exponential function of the base; Is a normalization function.
Wherein, the Reflecting the value and the first in the heart rate data sequenceThe frequency of occurrence of data points where the data points are identical; reflect the first in the heart rate data sequence Severity index of data point, the greater the value, the more values in the heart rate data sequence and the firstThe denser the distribution of the data points is, ifWhen the heart rate is larger, the probability of abnormality of the heart rate at the moment is larger, and the corresponding abnormality index is relatively larger.
Alternatively, other normalization methods, such as a sigmoid function, may be used for normalization processing, and the embodiment is not limited to the selected normalization method.
It should be noted that, the method for obtaining the abnormality index of each data point in the data sequence of other physiological indexes is the same as the method for determining the abnormality index of each data point in the heart rate data sequence, and this embodiment is not described here in detail.
In another embodiment, the relationship may also be used: an abnormality index is calculated for each data point in the heart rate data sequence.
S4, obtaining fitting curves of the abnormal indexes of the physiological indexes by fitting the abnormal indexes of the data points in the data sequences of the physiological indexes, screening the time periods when all fitting curves are in ascending trend, taking the physiological index pairs with the correlation larger than a preset value in the time periods meeting the screening conditions as target index pairs, and constructing a causal graph by using a PC algorithm based on the target index pairs to identify the causal relationship of the physiological indexes.
When the PC algorithm is used for constructing the causal graph, the number of physiological indexes to be processed can be reduced by screening and reserving important variables, so that the accuracy of causal relation in the constructed causal graph can be ensured while the calculation complexity is effectively reduced.
The invention only adds the screening process of data when constructing the causal graph, and does not improve other contents of the PC algorithm, such as the construction mode of the undirected graph, the test process of condition independence, the determination process of the directional edge and the like.
In an exemplary embodiment of the present invention, the determination of the fitted curve of each physiological index may be achieved by:
And respectively carrying out curve fitting on the abnormal indexes of all the data points in the data sequence of each physiological index by using a least square method to obtain a fitting curve of each physiological index.
For example, for a heart rate data sequence, the abnormality indexes of all data points in the heart rate data sequence may be curve-fitted using a least squares method, thereby obtaining a fitted curve of the heart rate. Similarly, the fitted curve of the blood glucose level and the fitted curve of the blood pressure may be determined in a manner that determines the fitted curve of the heart rate. The process of performing curve fitting by using the least square method is known in the art, and this embodiment will not be described in detail here.
Alternatively, curve fitting may be performed by using other fitting methods, such as spline interpolation, and the embodiment is not limited to the selected fitting method.
Further, after the fitted curve of each physiological index is obtained, time intervals in which all the variation trends of the fitted curve are synchronously rising can be screened, so that one or more time periods meeting the conditions can be determined. It should be noted that, the present invention aims to measure the duration of abnormal index increase of all physiological indexes by screening the time intervals in which all the variation trends of the fitting curves synchronously rise. The screened time periods are the time periods in which all physiological indexes are most likely to have abnormality, so that an important basis can be provided for the subsequent determination of target index pairs.
In an example embodiment of the invention, the determination of the time period for which the screening condition is met may be achieved by:
and acquiring slope values of data points in each fitting curve, and if the slope values of the data points on all the fitting curves in any time period are positive, reserving any time period to obtain the time period meeting the screening condition.
It should be noted that, in the mathematical representation of the fitted curve, the first derivative (i.e., slope value) of each data point essentially reflects the rate of change of the physiological index near the time point, and the sign and magnitude thereof can directly quantify the trend direction and the intensity change. Based on the characteristics, the slope value of each data point in each fitting curve is calculated, so that the change trend of each physiological index can be accurately estimated, and one or more time periods meeting the conditions can be screened.
In an example embodiment of the invention, the determination of the target index pair may be accomplished by:
And calculating absolute values of Spearman correlation coefficients of data sequences of any two physiological indexes in any time period for any time period meeting the screening condition to obtain the correlation of corresponding physiological index pairs, and taking the physiological index pairs with the correlation larger than a preset correlation threshold as target index pairs.
For example, the correlation threshold may be set to 0.5, and any time period that satisfies the screening condition may be recorded as [The Spearman correlation coefficient between any two of the heart rate data sequence, blood pressure data sequence and blood glucose level data sequence of the time period can be calculated and recorded as, wherein,AndIs any two different physiological indexes. And whenWhen it is, then reserve、The two physiological indexes are used for obtaining a target index pair in the time period, and then the target index pair in the time period meeting the screening conditions can be obtained. The magnitude of the correlation threshold is not particularly limited in this embodiment.
In another embodiment, the absolute value of the pearson correlation coefficient of any two data sequences may also be used as the correlation between the corresponding two data sequences. The Spearman correlation coefficient and the pearson correlation coefficient are both determined in the prior art, and this embodiment is not described in detail herein.
Further, after all target index pairs are determined, the PC algorithm may be utilized to implement the construction of all target index pairs corresponding causal graphs by initializing a completely undirected graph step, a step-by-step condition independence test step, and a step of determining an edge direction. It should be noted that, given the input data, the process of constructing a causal graph using the PC algorithm is known in the prior art, and this embodiment will not be described in detail here.
In an exemplary embodiment of the present invention, when the causal graph is constructed by using the PC algorithm based on the target index pairs, the condition variable of any one target index pair is a physiological index whose average correlation with the any one target index pair is greater than a set value in the same period.
Exemplary, when determining at [During this time period,、For target index pairs, the division can be calculated at this time、Data sequence of external physiological index in the time period, and、And (3) carrying out summation and averaging on the correlation of the data sequences in the time period, and if the obtained average value is larger than a set value, such as 0.6, taking the corresponding physiological index as a condition variable of the target index pair, so that a step-by-step condition independence checking step can be carried out on the target index pair based on the determined condition variable, and the testing efficiency when the step-by-step condition independence checking step is carried out on each target index pair is improved. The method for determining the correlation in this embodiment is the same as the method for calculating the correlation of the screening target index pair.
Further, after determining the causal graph of the patient, the causal relationship of each physiological index of the patient can be identified by comparing the causal graph of the patient with the causal graph of the general population. For example, if the causal graph of the patient shows that the blood glucose level has a greater impact on the heart rate, special attention needs to be paid to the blood glucose level control of the patient, thereby providing a more targeted reference for diagnosis and treatment by the doctor.
The invention also provides a clinical test data intelligent analysis system, which comprises a memory and a processor, wherein the memory is stored with a computer program, the computer program integrates the functions of a clinical test data intelligent analysis method, and when the computer program is executed, the complexity of constructing a causal graph by a PC algorithm can be reduced while the important causal relation among physiological indexes is maintained by the clinical test data intelligent analysis method.
In the description of the present specification, the meaning of "a plurality", "a number" or "a plurality" is at least two, for example, two, three or more, etc., unless explicitly defined otherwise.
While various embodiments of the present invention have been shown and described herein, it will be obvious to those skilled in the art that such embodiments are provided by way of example only. Many modifications, changes, and substitutions will now occur to those skilled in the art without departing from the spirit and scope of the invention. It should be understood that various alternatives to the embodiments of the invention described herein may be employed in practicing the invention.
Claims (9)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510779609.1A CN120299591B (en) | 2025-06-12 | 2025-06-12 | Intelligent analysis method and system for clinical test data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510779609.1A CN120299591B (en) | 2025-06-12 | 2025-06-12 | Intelligent analysis method and system for clinical test data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN120299591A CN120299591A (en) | 2025-07-11 |
| CN120299591B true CN120299591B (en) | 2025-08-29 |
Family
ID=96276251
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510779609.1A Active CN120299591B (en) | 2025-06-12 | 2025-06-12 | Intelligent analysis method and system for clinical test data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN120299591B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120356693B (en) * | 2025-06-24 | 2025-09-05 | 易迪希医药科技(嘉兴)有限公司 | Clinical trial data prediction method based on big data |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113421020A (en) * | 2021-07-13 | 2021-09-21 | 神策网络科技（北京）有限公司 | Multi-index abnormal point contact ratio analysis method |
| CN118571490A (en) * | 2024-07-31 | 2024-08-30 | 绿色医疗科技(大连)有限公司 | Pregnant woman pregnancy health state monitoring method based on big data analysis |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8388530B2 (en) * | 2000-05-30 | 2013-03-05 | Vladimir Shusterman | Personalized monitoring and healthcare information management using physiological basis functions |
| JP2017113382A (en) * | 2015-12-25 | 2017-06-29 | 大阪瓦斯株式会社 | Health management system using plural biological indexes |
| CN110782989B (en) * | 2019-09-18 | 2022-06-17 | 平安科技（深圳）有限公司 | Data analysis method, device, equipment and computer readable storage medium |
| CN115098740B (en) * | 2022-07-25 | 2022-11-04 | 广州市海捷计算机科技有限公司 | Data quality detection method and device based on multi-source heterogeneous data source |
| CN118964859B (en) * | 2024-10-12 | 2025-03-28 | 清华大学 | A health management integrated data collection optimization method and system |
| CN119763828A (en) * | 2024-12-13 | 2025-04-04 | 中国人民解放军海军第九七一医院 | Digital management method of graded nursing care in intensive care units based on the Internet of Things |
| CN119943398B (en) * | 2025-01-09 | 2025-10-31 | 南通大学 | Diabetes Management System Based on Big Data |
| CN119454046B (en) * | 2025-01-13 | 2025-05-23 | 中南大学湘雅医院 | An electrocardiogram monitoring method and system based on cardiac rehabilitation data |
| CN120015324A (en) * | 2025-02-18 | 2025-05-16 | 天津医科大学朱宪彝纪念医院(天津医科大学代谢病医院、天津代谢病防治中心) | A method and system for identifying diabetic nephropathy risk based on big data analysis |
| CN120015325A (en) * | 2025-02-19 | 2025-05-16 | 深圳市宝安区人民医院 | Colon cancer lymph node metastasis risk assessment method and system |
| CN119892286B (en) * | 2025-03-25 | 2025-06-20 | 深圳市微特精密科技股份有限公司 | A method and system for synchronously processing test equipment data |
| CN120048412B (en) * | 2025-04-24 | 2025-08-15 | 大连百首企家科技有限公司 | Method, system and device for monitoring endocrine and metabolic patients |
-
2025
- 2025-06-12 CN CN202510779609.1A patent/CN120299591B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113421020A (en) * | 2021-07-13 | 2021-09-21 | 神策网络科技（北京）有限公司 | Multi-index abnormal point contact ratio analysis method |
| CN118571490A (en) * | 2024-07-31 | 2024-08-30 | 绿色医疗科技(大连)有限公司 | Pregnant woman pregnancy health state monitoring method based on big data analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN120299591A (en) | 2025-07-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117238507B (en) | Intensive care monitoring system based on Internet of things | |
| CN117379021B (en) | Old person health index monitoring system based on intelligent wearing equipment | |
| CN120299591B (en) | Intelligent analysis method and system for clinical test data | |
| CN119230105A (en) | AI-based abnormal health event prediction system | |
| CN119028512B (en) | Obstetrical real-time nursing optimization method based on big data | |
| CN118866368B (en) | An impact quantification method and system for acute kidney injury assessment | |
| CN118658627A (en) | Cloud data fusion platform for medical wearable devices | |
| CN118072971B (en) | Smart elderly care service management method based on deep information integration | |
| CN118499705B (en) | Hierarchical early warning method, device, equipment and medium for leakage event of water supply network | |
| CN120388733A (en) | A method and system for early detection of chronic diseases based on a multimodal large model | |
| JP2014083194A (en) | Detection device, detection method and detection program that support detection of sign of state transition of living body based on network entropy | |
| CN118177766A (en) | Cardiovascular and cerebrovascular health monitoring and early warning method and system based on individual physiological characteristics | |
| CN118762849A (en) | An intelligent processing method and system for urology diagnosis and treatment data | |
| CN119679382A (en) | A cardiovascular data monitoring method for cardiovascular medicine | |
| CN117860221B (en) | Blood pressure measurement abnormality detection method and system based on combination of oscillography and auscultation | |
| CN120089386A (en) | A health assessment system and method for endocrine nursing | |
| CN115775627A (en) | Diabetes early warning method, equipment and system | |
| CN119523432B (en) | Intelligent cervical vertebra state data monitoring system | |
| CN113069108B (en) | User status monitoring method, device, electronic device and storage medium | |
| CN120473128A (en) | A method for assessing the risk of perioperative stroke during coronary artery bypass grafting | |
| KR102748088B1 (en) | Pressure ulcer occurrence prediction system | |
| CN119423704A (en) | A multi-parameter fusion blood sugar prediction method and system | |
| EP4550353A1 (en) | Risk prediction abstention in patient monitoring | |
| CN119207768A (en) | Data prediction method for falls in elderly patients based on comorbidity index | |
| CN118415607A (en) | Blood pressure continuous measurement prediction method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |