Methods, devices, media and equipment for intelligent screening of subjects for clinical trial projects

Abstract

The present application relates to a method, device, medium and equipment for intelligent screening of subjects for clinical trial projects, and to the technical field of clinical trials, wherein the method includes: each processed data is input into a preset subject screening model to obtain a target subject; the abnormal evaluation indexes are screened from each efficacy evaluation index corresponding to the target clinical trial project, and the corresponding dimension data that is prone to occur when each abnormal evaluation index is abnormal is determined; when there is dimension data that is prone to occur in the patient data of each target subject, the corresponding dimension data that is prone to occur is determined as key dimension data, and the corresponding target subject is verified according to the key dimension data and the abnormal evaluation indexes that are prone to occur in the corresponding dimension data that are prone to occur; if the verification is passed, the corresponding target subject is determined as the final subject of the target clinical trial project. The present application has the effect of improving the accuracy of the screening results.

Description

Technical Field

[0001] The present application relates to the technical field of clinical trials, and in particular to a method, device, medium and equipment for intelligent screening of subjects for clinical trial projects. Background Art

[0002] A clinical trial project refers to a scientific research project designed to verify the safety and effectiveness of new drugs, vaccines, treatments or diagnostic tools on humans. Clinical trial projects are an indispensable part of medical research. They are essential to promoting the advancement of medical science, improving patient treatment outcomes and ensuring the safety of medical products. Subjects refer to individuals who participate in tests in clinical trial projects. Subjects play a very important role in clinical trial projects. Subjects who meet the test requirements are particularly important for the success of clinical trial projects. Therefore, there is an urgent need for an effective method for screening subjects who meet the test requirements.

[0003] At present, the screening method for subjects who meet the test requirements is usually: manually reviewing patient medical records, laboratory test results and other information, and screening subjects according to the inclusion and exclusion criteria of the clinical trial project. However, once the number of patients is large and the amount of data is large, this manual screening method is difficult to ensure the objectivity and consistency of the screening results, resulting in poor accuracy of the screening results. Summary of the invention

[0004] In order to improve the accuracy of screening results, the present application provides a method, device, medium and equipment for intelligent screening of subjects for clinical trial projects.

[0005] In a first aspect of the present application, a method for intelligent screening of subjects for a clinical trial project is provided, which specifically comprises:

[0006] Acquire patient data of at least one candidate patient, wherein the patient data includes dimension data of the corresponding candidate patient under dimensions involved in inclusion criteria and exclusion criteria of the target clinical trial project;

[0007] Preprocessing the patient data of each candidate patient to obtain corresponding processed data, and inputting each processed data into a preset subject screening model to obtain target subjects that meet the test requirements of the target clinical trial project;

[0008] Screening abnormal evaluation indicators from various efficacy evaluation indicators corresponding to the target clinical trial project, and determining the easily occurring dimensional data corresponding to each abnormal evaluation indicator when an abnormality occurs, wherein the abnormal evaluation indicator is an efficacy evaluation indicator that is easily abnormal in patients with different diseases, the easily occurring dimensional data is dimensional data that is easily associated with patients with abnormalities in the abnormal evaluation indicator, and the efficacy evaluation indicator is an indicator for evaluating the efficacy of the target clinical trial project on the subject's disease;

[0009] When there is easily occurring dimension data in the patient data of each of the target subjects, the corresponding easily occurring dimension data is determined as key dimension data, and the corresponding target subject is verified according to the key dimension data and the easy abnormality assessment index of the key dimension data in the corresponding easily occurring dimension data;

[0010] If the verification passes, the corresponding target subject will be determined as the final subject of the target clinical trial project.

[0011] By adopting the above technical solution, after obtaining the patient data of each candidate patient, pre-processing is performed to obtain the corresponding processed data, and the processed data is input into the subject screening model, so that the artificial intelligence model is used to replace manual objective subject screening to obtain the target subject. Further, the abnormal evaluation index and the corresponding easy-to-appear dimensional data are determined. When there is easy-to-appear dimensional data in the patient data of a single target subject, it is determined as the key dimensional data, indicating that this target subject may have the risk of abnormal efficacy evaluation indicators in the trial, interfering with the trial results of the target clinical trial project, then the abnormal evaluation dimension and the key dimensional data in the corresponding easy-to-appear dimensional data are combined and analyzed to determine the degree of interference with the target clinical trial project, so as to determine whether the target subject is suitable for participating in the trial, and then realize the verification of the target subject. If the verification passes, it means that the target subject is suitable for participating in the trial, and then the target subject is determined as the final subject, thereby improving the accuracy of the subject screening results.

[0012] Optionally, the step of screening easily abnormal evaluation indicators from the various efficacy evaluation indicators corresponding to the clinical trial project, and determining easily occurring dimensional data corresponding to each easily abnormal evaluation indicator when an abnormality occurs, specifically includes:

[0013] Obtain the disease types of historical patients in which a single efficacy evaluation indicator corresponding to the target clinical trial project is abnormal, and count the number of different disease types corresponding to each efficacy evaluation indicator;

[0014] In descending order of the number, selecting the first number of the efficacy evaluation indicators from the efficacy evaluation indicators and determining it as the prone abnormality evaluation indicator;

[0015] Obtain historical dimensional data of a single historical patient with an abnormal abnormality in the abnormality-prone assessment indicator, count the first number of occurrences of each of the historical dimensional data, and select the second number of historical dimensional data from each of the historical dimensional data in descending order of the first number of occurrences to determine as the prone-to-occurrence dimensional data of the corresponding abnormality-prone assessment indicator.

[0016] By adopting the above technical solution, the larger the number, the more abnormalities the corresponding efficacy evaluation indicator has in historical patients with different disease types, and the higher the prevalence of abnormalities in the patient population, and the abnormality-prone evaluation indicators are determined from various efficacy evaluation indicators. Furthermore, the corresponding historical dimension data is obtained from the patient data of historical patients with abnormalities in a single abnormal evaluation indicator, and the first occurrence number of each historical dimension data is counted. The larger the first occurrence number, the more likely the historical patients with abnormal abnormal evaluation indicators are to have the corresponding historical dimension data, and the easily abnormal evaluation indicator dimension data is determined, so as to facilitate the subsequent verification of the target subjects.

[0017] Optionally, the verifying of the corresponding target subject according to the key dimension data and the abnormality assessment index of the key dimension data in the corresponding easily occurring dimension data specifically includes:

[0018] Determine the abnormality-prone assessment index of the key dimensional data in the corresponding easily occurring dimensional data as the key assessment index, and calculate the first weight of each of the key assessment indicators and the second weight of the corresponding key dimensional data, wherein the first weight is the ratio of the number corresponding to each of the key assessment indicators to the sum of the numbers corresponding to all of the abnormality-prone assessment indicators, and the second weight is the ratio of the first occurrence number of the key dimensional data corresponding to each of the key assessment indicators to the sum of the first occurrence numbers of all of the corresponding easily occurring dimensional data;

[0019] Calculate the first weight product of the first weight of each of the key evaluation indicators and the second weight of the corresponding key dimension data, and sum the first weight products to obtain the corresponding first weight product sum;

[0020] Based on each of the first weighted product sums, the corresponding target subject is verified.

[0021] By adopting the above technical solution, the first weight product of the first weight of each key evaluation indicator and the second weight of the corresponding key dimension data is calculated, and the first weight products are summed to obtain the first weight product sum of the corresponding target subjects. The larger the first weight product sum is, the more likely the corresponding target subjects will have abnormal efficacy evaluation indicators, which will interfere with the test results of the target clinical trial project on this target subject, resulting in inaccurate test results and less suitable for testing. Therefore, based on the first weight product sum, the corresponding target subjects are verified to improve the accuracy of the subject screening results.

[0022] Optionally, the verifying the corresponding target subject based on each of the first weight products specifically includes:

[0023] Determine a corresponding historical user portrait based on basic information of historical subjects who have passed the historical clinical trial project, wherein the historical clinical trial project is a clinical trial project with the same indication as the target clinical project;

[0024] Counting the second occurrence times of each of the historical user portraits, and selecting the historical user portrait with the third number from each of the historical user portraits in descending order of the second occurrence times to determine as the easy-to-pass user portrait;

[0025] Obtain the remaining dimensional data except the corresponding basic information from the historical patient data of each historical subject of the easy-to-pass user portrait, count the third number of occurrences of each of the remaining dimensional data, and select the fourth number of remaining dimensional data from each of the remaining dimensional data in descending order of the third number of occurrences to determine as the easy-to-pass dimensional data of the corresponding easy-to-pass user portrait;

[0026] Determine a corresponding target user profile based on the basic information in the patient data of each target subject;

[0027] When the target user portrait is an easy-to-pass user portrait, the corresponding target subject is determined as the key subject, and based on the first weight product sum of the key subject, patient data, the target user portrait and each of the easy-to-pass dimension data, it is determined whether the key subject has passed the verification.

[0028] By adopting the above technical solution, the larger the second number of occurrences, the more likely the corresponding historical user profile meets the test requirements, and the larger the third number of occurrences, the more likely the historical subjects who easily pass the user profile will have the corresponding remaining dimensional data. Finally, the target user profile of the target subject is determined. If the target user profile is an easy-to-pass user profile, it means that the target subject is likely to be suitable for the test. Then it is necessary to further analyze the first weight product sum to determine whether the key subjects who easily pass the user profile have passed the verification, thereby ensuring the accuracy of the subject screening results.

[0029] Optionally, the determining whether the key subject has passed the verification based on the first weighted product sum of the key subject, the patient data, the target user portrait and each of the easy-to-pass dimension data specifically includes:

[0030] Determine a third weight of the target user portrait and a fourth weight of the corresponding easy-to-pass dimension data, and when easy-to-pass dimension data exists in the patient data of the key subject, determine the corresponding easy-to-pass dimension data as the target dimension data, and calculate a second weight product of the third weight and the fourth weight of the corresponding target dimension data;

[0031] Summing each of the second weighted products to obtain a second weighted product sum, and normalizing the second weighted product sum and the first weighted product sum of the key subjects to obtain a processed first weighted product sum and a processed second weighted product sum;

[0032] If the processed second weight product sum is greater than the processed first weight product sum, subtracting the processed first weight product sum from the processed second weight product sum to obtain a difference;

[0033] When the difference is greater than a preset difference threshold, it is determined that the key subject has passed the verification, and when the difference is not greater than the preset difference threshold, it is determined that the key subject has failed the verification.

[0034] By adopting the above technical scheme, when the second weight product sum after processing is greater than the first weight product sum after processing, it means that the probability that the key subject is suitable for the test is higher than the probability that he is not suitable for the test, and the difference is obtained by subtracting the first weight product sum after processing from the second weight product sum after processing. If the difference is greater than the difference threshold, it means that the key subject is more suitable for the test, and it is determined that the key subject has passed the verification. Otherwise, if the difference is not greater than the difference threshold, it means that the second weight product sum after processing and the first weight product sum after processing are closer, and the probability of being unsuitable for the test is closer to the probability of being suitable for the test. In order to ensure the reliability of the test results, it is determined that the key subject has failed the verification.

[0035] Optionally, the determining whether the key subject has passed the verification based on the first weighted product sum of the key subject, the patient data, the target user portrait and each of the easy-to-pass dimension data specifically further includes:

[0036] Determine a third weight of the target user portrait and a fourth weight of the corresponding easy-to-pass dimension data, and when easy-to-pass dimension data exists in the patient data of the key subject, determine the corresponding easy-to-pass dimension data as the target dimension data, and calculate a second weight product of the third weight and the fourth weight of the corresponding target dimension data;

[0037] Summing each of the second weighted products to obtain a second weighted product sum, and normalizing the second weighted product sum and the first weighted product sum of the key subjects to obtain a processed first weighted product sum and a processed second weighted product sum;

[0038] If the first weighted product sum is less than a preset product sum threshold, comparing the processed first weighted product sum and the processed second weighted product sum;

[0039] When the second weight product sum after the processing is greater than the first weight product sum after the processing, it is determined that the key subject has passed the verification.

[0040] By adopting the above technical scheme, if the first weight product sum is less than the preset product sum threshold, it means that the probability that the key subject is not suitable for the test is small, and further verification is needed to verify whether it is suitable for the test; if the second weight product sum after processing is greater than the first weight product sum after processing, it means that the probability that the key subject is suitable for the test is higher than the probability that he is not suitable for the test, and it is determined that the key subject has passed the verification and is suitable for the test. At the same time, the reliability of the determined first weight product sum can be verified to avoid deviations in the first weight product sum.

[0041] Optionally, the method further includes:

[0042] If the verification passes, the maximum first weight product is selected from each of the first weight products, and the key evaluation indicator corresponding to the maximum first weight product is determined as the key monitoring indicator of the corresponding target subject in the test.

[0043] By adopting the above technical solution, the maximum first weight product is selected from each first weight product, and the probability of abnormality of the corresponding key evaluation indicator is relatively high. Although the verification is passed, we still need to be vigilant about the interference of the key evaluation indicator corresponding to the maximum first weight product on the test results, so as to ensure the reliability of the test results of the target clinical trial project. Then it will be determined as the key monitoring indicator of the corresponding target subject in the test.

[0044] In a second aspect of the present application, a device for intelligently screening subjects for a clinical trial project is provided, specifically comprising:

[0045] A data acquisition module, used to acquire patient data of at least one candidate patient, wherein the patient data includes dimensional data of the corresponding candidate patient under dimensions involved in inclusion criteria and exclusion criteria of the target clinical trial project;

[0046] The first screening module is used to pre-process the patient data of each candidate patient to obtain corresponding processed data, and input each processed data into a preset subject screening model to obtain target subjects that meet the test requirements of the target clinical trial project;

[0047] An indicator determination module, used for screening abnormal evaluation indicators from various efficacy evaluation indicators corresponding to the target clinical trial project, and determining the easily occurring dimensional data corresponding to each abnormal evaluation indicator when an abnormality occurs, wherein the easily occurring evaluation indicator is an efficacy evaluation indicator that is easily abnormal in patients with different diseases, the easily occurring dimensional data is dimensional data that is easily associated with patients with abnormalities in the easily occurring evaluation indicator, and the efficacy evaluation indicator is an indicator for evaluating the efficacy of the target clinical trial project on the subject's disease;

[0048] A test verification module, used for, when there is easily occurring dimension data in the patient data of each of the target subjects, determining the corresponding easily occurring dimension data as key dimension data, and verifying the corresponding target subject according to the key dimension data and the easy abnormality assessment index of the key dimension data in the corresponding easily occurring dimension data;

[0049] The second screening module is used to determine the corresponding target subject as the final subject of the target clinical trial project if the verification is passed.

[0050] By adopting the above technical solution, after the data acquisition module obtains the patient data, the processed data is input into the subject screening model through the first screening module to obtain the target subject. Then the indicator determination module determines the abnormal assessment indicator and the corresponding easy-to-occur dimension data. Then the subject verification module verifies the suitability of the target subject. Finally, when the second screening module passes the verification, the corresponding target subject is determined as the final subject of the target clinical trial project.

[0051] In a third aspect of the present application, a computer-readable storage medium is provided, in which a computer program is stored. When the computer program is loaded and executed by a processor, the method steps described in any one of the first aspects are performed.

[0052] In a fourth aspect of the present application, an electronic device is provided, specifically comprising:

[0053] A processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the processor is used to load and execute the computer program stored in the memory so that the electronic device performs the method as described in any one of the first aspects.

[0054] In summary, the present application includes at least one of the following beneficial technical effects: after obtaining the patient data of each candidate patient, preprocessing is performed to obtain the corresponding processed data, and the processed data is input into the subject screening model, so that the artificial intelligence model is used to replace manual objective subject screening to obtain the target subject. Further, the abnormal evaluation index and the corresponding easy-to-appear dimensional data are determined. When there is easy-to-appear dimensional data in the patient data of a single target subject, it is determined as the key dimensional data, indicating that the target subject may have an abnormal risk of abnormal efficacy evaluation indicators in the trial, interfering with the trial results of the target clinical trial project, then the abnormal evaluation dimension of the key dimensional data in the corresponding easy-to-appear dimensional data and the key dimensional data are combined and analyzed to determine the degree of interference with the target clinical trial project, thereby determining whether the target subject is suitable for participating in the trial, and then realizing the verification of the target subject. If the verification passes, it means that the target subject is suitable for participating in the trial, then the target subject is determined as the final subject, thereby improving the accuracy of the subject screening results. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 It is a flow chart of a method for intelligent screening of subjects for a clinical trial project provided in an embodiment of the present application;

[0056] Figure 2 It is a flow chart of another method for intelligent screening of subjects for a clinical trial project provided in an embodiment of the present application;

[0057] Figure 3 It is a schematic diagram of the structure of a device for intelligent screening of subjects for clinical trial projects provided in an embodiment of the present application;

[0058] Figure 4 It is a structural schematic diagram of another intelligent screening device for clinical trial project subjects provided in an embodiment of the present application.

[0059] Explanation of the accompanying drawings: 11. Data acquisition module; 12. First screening module; 13. Index determination module; 14. Test verification module; 15. Second screening module; 16. Key monitoring module. DETAILED DESCRIPTION

[0060] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0061] In the description of the embodiments of the present application, words such as "illustrative", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "illustrative", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "illustrative", "for example" or "for example" is intended to present related concepts in a concrete way.

[0062] In the description of the embodiments of the present application, the term "and / or" is only a kind of association relationship describing the associated objects, indicating that there may be three kinds of relationships, for example, A and / or B, which can represent: A exists alone, B exists alone, and A and B exist at the same time. In addition, unless otherwise specified, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" can explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0063] See also Figure 1 The present application embodiment discloses a flow chart of a method for intelligent screening of subjects for clinical trial projects, which can be implemented by a computer program or run on an intelligent screening device for subjects for clinical trial projects based on the von Neumann system. The computer program can be integrated into an application or run as an independent tool application, specifically including:

[0064] S101: Acquire patient data of at least one candidate patient.

[0065] Specifically, the candidate patients are the screening objects of the subjects of the target clinical trial project, and the patient data include the dimensional data of the corresponding candidate patients under the dimensions involved in the inclusion criteria and exclusion criteria of the target clinical trial project. Clinical trials refer to the research process of testing drugs, vaccines, treatment plans or diagnostic tools on human volunteers or patients. In an embodiment of the present application, the target clinical trial project can be a clinical trial project for new drugs, and in other embodiments, the target clinical trial project can also be a clinical trial project for a completely new treatment plan. The subject is the test subject of the target clinical trial project. Further, the inclusion criteria of the target clinical trial project refer to the basic conditions for participating in the trial project, and the exclusion criteria refer to other special circumstances that do not meet the requirements of the trial on the basis of meeting the inclusion criteria. Exemplarily, the dimensions involved in the inclusion criteria include but are not limited to the patient's age, gender, disease status, test results and other dimensions, and the dimensions involved in the exclusion criteria include but are not limited to whether they are in the lactation period, whether there are complications and other dimensions. Furthermore, the patient data of the test patients can be understood as the specific data of the dimensions involved in the inclusion criteria and the exclusion criteria. For example, the patient data can be: patient a, male, 45 years old, disease a1, no complications, not in the lactation period, and other dimensional data.

[0066] In addition, the execution subject of a method for intelligent screening of subjects for a clinical trial project disclosed in an embodiment of the present application is a server, which can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. The server and the terminal are directly or indirectly connected through a wired or wireless network, and the terminal can be a mobile phone, a tablet computer or a personal computer. For the server, a feasible way to obtain the patient data of the candidate patient is: the subject screening staff opens the subject screening client installed in the terminal and uploads the patient data of the candidate patient. The terminal sends the patient data of the candidate patient to the server through the client. The server is the background server of the client, and the server finally obtains the patient data.

[0067] S102: Preprocess the patient data of each candidate patient to obtain corresponding processed data, and input each processed data into a preset subject screening model to obtain target subjects that meet the test requirements of the target clinical trial project.

[0068] Specifically, the patient data of each candidate patient is preprocessed, mainly including data cleaning and format conversion of the patient data, wherein data cleaning ensures the quality and accuracy of the patient data, and format conversion ensures that the patient data can be correctly identified and processed by the model. This is a prior art and will not be repeated here. Further, after preprocessing, the corresponding processed data is obtained, and the processed data of each candidate patient is input into a preset subject screening model, and each candidate patient is screened, and finally the target subject that meets the test requirements of the target clinical trial project is obtained. It should be noted that the subject screening model can be a trained deep neural network model, and in other embodiments, it can also be a trained convolutional neural network model. Among them, the training process can be: the patient data of the historical subjects marked with "subjects meeting the test requirements" is used as training data, and the training data is divided into a training set and a test set according to a ratio of 8:2, and finally the deep neural network model is trained by the training set and the test set to obtain the subject screening model.

[0069] S103: Screening easily abnormal evaluation indicators from various efficacy evaluation indicators corresponding to the target clinical trial project, and determining easily occurring dimensional data corresponding to each easily abnormal evaluation indicator when an abnormality occurs.

[0070] Specifically, the efficacy evaluation index refers to an index for evaluating the efficacy of the target clinical trial project on the subject's disease. Exemplarily, the target clinical trial project is a test project for a new antipyretic drug, and the corresponding efficacy evaluation index can be body temperature. An easily abnormal evaluation index is an efficacy evaluation index that is prone to abnormality in patients with different diseases, and the easily abnormal dimensional data is the dimensional data that is easily accompanied by patients with abnormal easily abnormal evaluation indicators. Further, to determine the easily abnormal evaluation index and the easily abnormal dimensional data corresponding to the abnormality, a feasible implementation method is: based on the medical record system, obtain the disease type of each historical patient with abnormal single efficacy evaluation index, and then count the number of different disease types corresponding to the single efficacy evaluation index, that is, the total number of different disease types that occurred in historical patients when a single efficacy evaluation index was abnormal, select the first number of efficacy evaluation indicators from each efficacy evaluation index in order from large to small, and determine them as easily abnormal evaluation indicators. The larger the number, the more abnormal the corresponding efficacy evaluation index is in historical patients with different disease types, and the higher the prevalence of abnormality in the patient population. Furthermore, the corresponding historical dimension data is obtained from the patient data of historical patients with abnormalities in a single abnormality-prone assessment indicator, and the first occurrence number of each historical dimension data is counted. The larger the first occurrence number, the more likely the corresponding historical dimension data will appear in historical patients with abnormalities in the abnormality-prone assessment indicator. Finally, in order of the first occurrence number from large to small, the historical dimension data with the second number is selected from each historical dimension data to be determined as the easily occurring dimension data of the corresponding abnormality-prone assessment indicator.

[0071] S104: When there are easily occurring dimension data in the patient data of each target subject, the corresponding easily occurring dimension data is determined as key dimension data, and the corresponding target subject is verified based on the key dimension data and the easy abnormality assessment index of the key dimension data in the corresponding easily occurring dimension data.

[0072] Specifically, when there is prone-to-occur dimension data in the patient data of a single target subject, there may be a risk of abnormal abnormality in the prone-to-abnormality assessment indicator, which may interfere with the evaluation of the test results of the target subject through this prone-to-abnormality assessment indicator, thereby affecting the reliability of the target clinical trial project test. Then the existing prone-to-occur dimension data is determined as key dimension data, and based on this key dimension data and the prone-to-abnormality assessment indicators of the key dimension data in the corresponding prone-to-occur dimension data, the rationality of the target subject's acceptance of the test is verified. One achievable implementation method is:

[0073] The abnormal evaluation index of the key dimension data in the corresponding easy-to-appear dimensional data is determined as the key evaluation index, and then the first weight of each key evaluation index and the second weight of the corresponding key dimension data are calculated, the first weight is the ratio of the number corresponding to each key evaluation index to the sum of the numbers corresponding to all abnormal evaluation indicators, and the second weight is the ratio of the first occurrence number of the key dimension data corresponding to each key evaluation index to the sum of the first occurrence number of all easy-to-appear dimensional data. Further, the first weight product of each key evaluation index and the second weight of the corresponding key dimension data is calculated, and each first weight product is summed to obtain the first weight product sum of the corresponding target subject. The larger the sum of the first weight product, the more likely the corresponding target subject is to have abnormal efficacy evaluation indicators, which interferes with the test results of the target clinical trial project on this target subject, resulting in inaccurate test results and less suitable for testing. Exemplarily, the efficacy evaluation index is heart rate, and the effective efficacy is manifested as a decrease in heart rate. Even if the target clinical trial project is effective for the excessive heart rate caused by the subject's disease, other reasons (not the disease targeted by the target clinical trial project) cause the heart rate to rise again, resulting in the misjudgment of the efficacy of the target clinical trial project as poor efficacy.

[0074] Furthermore, based on the single first weight product sum, the corresponding target subject is verified, and the specific verification process is as follows: from the clinical trial history records, the basic information of the historical subjects who have passed the historical clinical trial project, that is, age, gender and other information, is obtained, and it is input into the portrait prediction model to obtain the corresponding historical user portrait, wherein the historical clinical trial project is a clinical trial project with the same indication as the target clinical project. In addition, the portrait prediction model is a trained deep neural network model or a recurrent neural network model, and the training process is to input the sample of basic information and the corresponding user portrait as training data into the model for training. This is a prior art and will not be repeated here.

[0075] The second number of occurrences of each historical user portrait is counted, and the third number of historical user portraits is selected from each historical user portrait in the order of the second number of occurrences from large to small to determine it as the easy-to-pass user portrait, that is, the user portrait that is easy to meet the test requirements. The larger the second number of occurrences, the more likely the corresponding historical user portrait meets the test requirements. Then, the historical patient data of each historical subject who is easy to pass the user portrait is retrieved from the medical record system, and the remaining dimensional data except the basic information is determined. The third number of occurrences of each remaining dimensional data is counted, and the fourth number of remaining dimensional data is selected from each remaining dimensional data in the order of the third number of occurrences from large to small to determine it as the easy-to-pass dimensional data of the corresponding easy-to-pass user portrait, that is, the dimensional data that is more likely to appear in the historical subject who is easy to pass the user portrait. The larger the third number of occurrences, the more likely the corresponding remaining dimensional data will appear in the historical subject who is easy to pass the user portrait.

[0076] Further, the basic information in the patient data of a single target subject is input into the portrait prediction model to obtain the corresponding target user portrait. When the target user portrait is an easy-to-pass user portrait, the corresponding target subject is determined as a key subject, and the third weight of the target user portrait and the fourth weight of the corresponding easy-to-pass dimension data are calculated. The third weight is the ratio of the second occurrence of the target user portrait to the sum of the second occurrence of all easy-to-pass user portraits, and the fourth weight is the ratio of the third occurrence of the single easy-to-pass dimension data corresponding to the target user portrait to the sum of the third occurrence of all easy-to-pass dimension data. If there is easy-to-pass dimension data in the patient data of this key subject, the existing easy-to-pass dimension data is determined as the target dimension data. Further, the second weight product of the third weight of the target user portrait and the fourth weight of the corresponding target dimension data is calculated, and each second weight product is summed to obtain the second weight product sum. The larger the second weight product sum is, the more the target subject meets the test requirements and the more suitable it is for the test. In other embodiments, when the target user portrait is not an easy-to-pass user portrait, if the first weight product sum is less than the preset product sum threshold, it is determined that the verification is passed, otherwise the verification fails.

[0077] Furthermore, the second weight product sum and the first weight product sum of the key subject are normalized by the preset SPSS software to obtain the first weight product sum after processing and the second weight product sum after processing. Finally, when the second weight product sum after processing is greater than the first weight product sum after processing, it means that the probability that the key subject is suitable for the test is higher than the probability that it is not suitable for the test. The difference is obtained by subtracting the first weight product sum after processing from the second weight product sum after processing. If the difference is greater than the difference threshold, it means that the key subject is more suitable for the test and it is determined that the key subject has passed the verification. Otherwise, it is determined that the key subject has failed the verification.

[0078] In other embodiments, the first weighted product sum after processing and the second weighted product sum after processing are determined. For details, please refer to the above steps S101-S104, which will not be repeated here. If the first weighted product sum is less than the preset product sum threshold, it means that the probability that the key subject is not suitable for the test is small, and further verification is required to verify whether it is suitable for the test. If the second weighted product sum after processing is greater than the first weighted product sum after processing, it means that the probability that the key subject is suitable for the test is higher than the probability that it is not suitable for the test. It is determined that the key subject has passed the verification and is suitable for the test, and the reliability of the determined first weighted product sum is verified.

[0079] S105: If the verification passes, the corresponding target subject is determined as the final subject of the target clinical trial project.

[0080] Specifically, if the verification is passed, it means that the target subject is more suitable for participating in the test of the target clinical trial project, and thus the test results of the target clinical trial project are more reliable, then the corresponding target subject is determined as the final subject of the target clinical trial project. The present application preliminarily screens out the target subject through the subject screening model, and finally verifies the target subject, so that the final screened subject has a higher accuracy.

[0081] See also Figure 2 , the present application embodiment discloses a flow chart of another method for intelligent screening of clinical trial project subjects, which can be implemented by a computer program or run on a device for intelligent screening of clinical trial project subjects based on the von Neumann system. The computer program can be integrated into an application or run as an independent tool application, specifically including:

[0082] S201: Acquire patient data of at least one candidate patient.

[0083] S202: Preprocess the patient data of each candidate patient to obtain corresponding processed data, and input each processed data into a preset subject screening model to obtain target subjects that meet the test requirements of the target clinical trial project.

[0084] S203: Obtain the disease types of historical patients with abnormal single efficacy evaluation indicators corresponding to the target clinical trial project, and count the number of different disease types corresponding to each efficacy evaluation indicator.

[0085] S204: Selecting the first efficacy evaluation indicator from each efficacy evaluation indicator in descending order of quantity and determining it as the prone-to-abnormality evaluation indicator.

[0086] S205: Obtain historical dimensional data of historical patients with abnormal single abnormal assessment indicators, count the first occurrence times of each historical dimensional data, and select the second number of historical dimensional data from each historical dimensional data in descending order of the first occurrence times as the prone-to-occurrence dimensional data of the corresponding abnormal assessment indicator.

[0087] S206: When there are easily occurring dimension data in the patient data of each target subject, the corresponding easily occurring dimension data are determined as key dimension data, and the easily abnormal assessment indicators in which the key dimension data exists in the corresponding easily occurring dimension data are determined as key assessment indicators, and the first weight of each key assessment indicator and the second weight of the corresponding key dimension data are calculated.

[0088] S207: Calculate the first weight product of the first weight of each key evaluation indicator and the second weight of the corresponding key dimension data, and sum the first weight products to obtain the corresponding first weight product sum.

[0089] S208: Based on each first weight product sum, verify the corresponding target subject.

[0090] S209: If the verification passes, the corresponding target subject is determined as the final subject of the target clinical trial project.

[0091] For details, please refer to steps S101-S105, which will not be described in detail here.

[0092] S210: If the verification passes, a maximum first weight product is selected from each first weight product, and the key evaluation index corresponding to the maximum first weight product is determined as the key monitoring index of the corresponding target subject in the test.

[0093] Specifically, if the verification passes, then the maximum first weight product is selected from each first weight product, and the probability of abnormality of the corresponding key evaluation indicator is relatively high. Although the verification passes, we still need to be vigilant about the interference of the key evaluation indicator corresponding to the maximum first weight product on the test results, so as to ensure the reliability of the test results of the target clinical trial project, and then determine it as the key monitoring indicator of the corresponding target subject in the test.

[0094] The implementation principle of the intelligent screening method for subjects of the clinical trial project of the present application embodiment is as follows: after obtaining the patient data of each patient to be selected, pre-processing is performed to obtain the corresponding processed data, and the processed data is input into the subject screening model, so as to replace the artificial intelligence model for objective subject screening and obtain the target subject. Further, the abnormal evaluation index and the corresponding easy-to-appear dimensional data are determined. When there is easy-to-appear dimensional data in the patient data of a single target subject, it is determined as the key dimensional data, indicating that the target subject may have the risk of abnormal efficacy evaluation index in the trial, interfering with the test results of the target clinical trial project, then the abnormal evaluation dimension of the key dimensional data in the corresponding easy-to-appear dimensional data and the key dimensional data are combined and analyzed to determine the degree of interference of the target clinical trial project, so as to determine whether the target subject is suitable for participating in the trial, and then realize the verification of the target subject. If the verification passes, it means that the target subject is suitable for participating in the trial, then the target subject is determined as the final subject, thereby improving the accuracy of the subject screening results.

[0095] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.

[0096] See also Figure 3 , which is a schematic diagram of the structure of the intelligent screening device for clinical trial project subjects provided in the embodiment of the present application. The intelligent screening device for clinical trial project subjects can be implemented as all or part of the device through software, hardware or a combination of both. The device includes a data acquisition module 11, a first screening module 12, an indicator determination module 13, a test verification module 14 and a second screening module 15.

[0097] A data acquisition module 11 is used to acquire patient data of at least one candidate patient, wherein the patient data includes dimensional data of the corresponding candidate patient under the dimensions involved in the inclusion criteria and exclusion criteria of the target clinical trial project;

[0098] The first screening module 12 is used to pre-process the patient data of each candidate patient to obtain corresponding processed data, and input each processed data into a preset subject screening model to obtain target subjects that meet the test requirements of the target clinical trial project;

[0099] The indicator determination module 13 is used to screen the abnormal evaluation indicators from the efficacy evaluation indicators corresponding to the target clinical trial project, and determine the dimensional data that is easy to appear when each abnormal evaluation indicator is abnormal. The abnormal evaluation indicator is an efficacy evaluation indicator that is easy to appear abnormal in patients with different diseases. The dimensional data that is easy to appear is the dimensional data that is easy to appear in patients with abnormal abnormal evaluation indicators. The efficacy evaluation indicator is an indicator for evaluating the efficacy of the target clinical trial project on the subject's disease.

[0100] The subject verification module 14 is used to determine the corresponding easily occurring dimension data as key dimension data when there is easily occurring dimension data in the patient data of each target subject, and verify the corresponding target subject according to the key dimension data and the easy abnormality assessment index of the key dimension data in the corresponding easily occurring dimension data;

[0101] The second screening module 15 is used to determine the corresponding target subject as the final subject of the target clinical trial project if the verification is passed.

[0102] Optionally, the indicator determination module 13 is specifically used to:

[0103] Obtain the disease types of historical patients with abnormal single efficacy evaluation indicators corresponding to the target clinical trial project, and count the number of different disease types corresponding to each efficacy evaluation indicator;

[0104] In descending order of quantity, the first efficacy evaluation indicator is selected from each efficacy evaluation indicator and determined as the evaluation indicator prone to abnormality;

[0105] Obtain historical dimension data of historical patients with abnormalities in a single abnormality-prone assessment indicator, count the first occurrence times of each historical dimension data, and select the historical dimension data with the second number from each historical dimension data in descending order of the first occurrence times to determine as the prone-to-occurrence dimension data of the corresponding abnormality-prone assessment indicator.

[0106] Optionally, the test verification module 14 is specifically used for:

[0107] Determine the abnormality-prone assessment indicators that have key dimension data in the corresponding easily occurring dimension data as key assessment indicators, and calculate the first weight of each key assessment indicator and the second weight of the corresponding key dimension data, the first weight being the ratio of the number corresponding to each key assessment indicator to the sum of the numbers corresponding to all abnormality-prone assessment indicators, and the second weight being the ratio of the first occurrence number of the key dimension data corresponding to each key assessment indicator to the sum of the first occurrence numbers of all corresponding easily occurring dimension data;

[0108] Calculate the first weight product of the first weight of each key evaluation indicator and the second weight of the corresponding key dimension data, and sum the first weight products to obtain the corresponding first weight product sum;

[0109] Based on each first weighted product sum, the corresponding target subject is verified.

[0110] Optionally, the test verification module 14 is specifically used for:

[0111] Based on the basic information of historical subjects who have passed the historical clinical trial project, the corresponding historical user portrait is determined. The historical clinical trial project is a clinical trial project with the same indication as the target clinical project;

[0112] The second occurrence times of each historical user portrait are counted, and the historical user portrait with the third highest number of second occurrence times is selected from each historical user portrait in descending order to be determined as the easy-to-pass user portrait;

[0113] Obtain the remaining dimension data except the corresponding basic information in the historical patient data of each historical subject who is easy to pass the user portrait, count the third number of occurrences of each remaining dimension data, and select the fourth number of remaining dimension data from each remaining dimension data in descending order of the third number of occurrences to determine as the easy-to-pass dimension data of the corresponding easy-to-pass user portrait;

[0114] Based on the basic information in the patient data of each target subject, determine the corresponding target user profile;

[0115] When the target user portrait is an easy-to-pass user portrait, the corresponding target subject is determined as the key subject, and based on the first weight product sum of the key subject, patient data, the target user portrait and each easy-to-pass dimension data, it is determined whether the key subject has passed the verification.

[0116] Optionally, the test verification module 14 is specifically used for:

[0117] Determine a third weight of the target user portrait and a fourth weight of the corresponding easy-to-pass dimension data, and when easy-to-pass dimension data exists in the patient data of the key subject, determine the corresponding easy-to-pass dimension data as the target dimension data, and calculate a second weight product of the third weight and the fourth weight of the corresponding target dimension data;

[0118] The second weighted products are summed to obtain a second weighted product sum, and the second weighted product sum and the first weighted product sum of the key subjects are normalized to obtain a processed first weighted product sum and a processed second weighted product sum;

[0119] If the processed second weight product sum is greater than the processed first weight product sum, subtract the processed first weight product sum from the processed second weight product sum to obtain a difference;

[0120] When the difference is greater than a preset difference threshold, it is determined that the key subject has passed the verification; when the difference is not greater than the preset difference threshold, it is determined that the key subject has failed the verification.

[0121] Optionally, the test verification module 14 is specifically used for:

[0122] Determine a third weight of the target user portrait and a fourth weight of the corresponding easy-to-pass dimension data, and when easy-to-pass dimension data exists in the patient data of the key subject, determine the corresponding easy-to-pass dimension data as the target dimension data, and calculate a second weight product of the third weight and the fourth weight of the corresponding target dimension data;

[0123] The second weighted products are summed to obtain a second weighted product sum, and the second weighted product sum and the first weighted product sum of the key subjects are normalized to obtain a processed first weighted product sum and a processed second weighted product sum;

[0124] If the first weighted product sum is less than a preset product sum threshold, comparing the processed first weighted product sum and the processed second weighted product sum;

[0125] When the second weight product sum after processing is greater than the first weight product sum after processing, it is determined that the key subject has passed the verification.

[0126] Optional, such as Figure 4 As shown, the device also includes a key monitoring module 16, which is specifically used for:

[0127] If the verification passes, the maximum first weight product is selected from the first weight products, and the key evaluation index corresponding to the maximum first weight product is determined as the key monitoring index of the corresponding target subject in the test.

[0128] It should be noted that the intelligent screening device for clinical trial project subjects provided in the above embodiment only uses the division of the above functional modules as an example when executing the intelligent screening method for clinical trial project subjects. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the intelligent screening device for clinical trial project subjects provided in the above embodiment and the embodiment of the intelligent screening method for clinical trial project subjects belong to the same concept, and the implementation process thereof is detailed in the method embodiment, which will not be repeated here.

[0129] An embodiment of the present application further discloses a computer-readable storage medium, and the computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, a method for intelligent screening of subjects for a clinical trial project of the above embodiment is adopted.

[0130] Among them, the computer program can be stored in a computer-readable medium, the computer program includes computer program code, the computer program code can be in the form of source code, object code, executable file or certain middleware, etc. The computer-readable medium includes any entity or device that can carry the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the computer-readable medium includes but is not limited to the above-mentioned components.

[0131] Among them, through this computer-readable storage medium, a method for intelligent screening of subjects for a clinical trial project in the above embodiment is stored in a computer-readable storage medium, and is loaded and executed on a processor to facilitate the storage and application of the above method.

[0132] An embodiment of the present application also discloses an electronic device, in which a computer program is stored in a computer-readable storage medium. When the computer program is loaded and executed by a processor, the above-mentioned method for intelligent screening of subjects for a clinical trial project is adopted.

[0133] The electronic device may be a desktop computer, a laptop computer, a cloud server or other electronic device, and the electronic device includes but is not limited to a processor and a memory. For example, the electronic device may also include input and output devices, a network access device, and a bus.

[0134] Among them, the processor can adopt a central processing unit (CPU). Of course, according to actual usage, other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. can also be adopted. The general-purpose processor can adopt a microprocessor or any conventional processor, etc., and this application does not impose any restrictions on this.

[0135] Among them, the memory can be an internal storage unit of the electronic device, such as a hard disk or memory of the electronic device, or it can be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (SMC), a secure digital card (SD) or a flash memory card (FC) equipped on the electronic device. Moreover, the memory can also be a combination of an internal storage unit and an external storage device of the electronic device. The memory is used to store computer programs and other programs and data required by the electronic device. The memory can also be used to temporarily store data that has been output or is to be output, and this application does not impose any restrictions on this.

[0136] Among them, through this electronic device, a clinical trial project subject intelligent screening method of the above embodiment is stored in the memory of the electronic device, and is loaded and executed on the processor of the electronic device for easy use.

[0137] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure here, those skilled in the art will easily think of other embodiments of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field not recorded in the present disclosure. The description and examples are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A method for intelligent screening of subjects for clinical trial projects, characterized in that: The method comprises: Acquire patient data of at least one candidate patient, wherein the patient data includes dimension data of the corresponding candidate patient under dimensions involved in inclusion criteria and exclusion criteria of the target clinical trial project; Preprocessing the patient data of each candidate patient to obtain corresponding processed data, and inputting each processed data into a preset subject screening model to obtain target subjects that meet the test requirements of the target clinical trial project; Screening abnormal evaluation indicators from various efficacy evaluation indicators corresponding to the target clinical trial project, and determining the easily occurring dimensional data corresponding to each abnormal evaluation indicator when an abnormality occurs, wherein the abnormal evaluation indicator is an efficacy evaluation indicator that is easily abnormal in patients with different diseases, the easily occurring dimensional data is dimensional data that is easily associated with patients with abnormalities in the abnormal evaluation indicator, and the efficacy evaluation indicator is an indicator for evaluating the efficacy of the target clinical trial project on the subject's disease; When there is easily occurring dimension data in the patient data of each of the target subjects, the corresponding easily occurring dimension data is determined as key dimension data, and the corresponding target subject is verified according to the key dimension data and the easy abnormality assessment index of the key dimension data in the corresponding easily occurring dimension data; If the verification passes, the corresponding target subject will be determined as the final subject of the target clinical trial project.

2. The method for intelligent screening of clinical trial subjects according to claim 1, characterized in that: The step of selecting easily abnormal evaluation indicators from the various efficacy evaluation indicators corresponding to the target clinical trial project, and determining easily occurring dimensional data corresponding to each easily abnormal evaluation indicator when an abnormality occurs, specifically includes: Obtain the disease types of historical patients in which a single efficacy evaluation indicator corresponding to the target clinical trial project is abnormal, and count the number of different disease types corresponding to each efficacy evaluation indicator; In descending order of the number, selecting the first number of the efficacy evaluation indicators from the efficacy evaluation indicators and determining it as the prone abnormality evaluation indicator; Obtain historical dimensional data of a single historical patient with an abnormal abnormality in the abnormality-prone assessment indicator, count the first number of occurrences of each of the historical dimensional data, and select the second number of historical dimensional data from each of the historical dimensional data in descending order of the first number of occurrences to determine as the prone-to-occurrence dimensional data of the corresponding abnormality-prone assessment indicator.

3. The method for intelligent screening of clinical trial subjects according to claim 2, characterized in that: The verifying of the corresponding target subject according to the key dimension data and the abnormality assessment index of the key dimension data in the corresponding easily occurring dimension data specifically includes: Determine the abnormality-prone assessment index of the key dimensional data in the corresponding easily occurring dimensional data as the key assessment index, and calculate the first weight of each of the key assessment indicators and the second weight of the corresponding key dimensional data, wherein the first weight is the ratio of the number corresponding to each of the key assessment indicators to the sum of the numbers corresponding to all of the abnormality-prone assessment indicators, and the second weight is the ratio of the first occurrence number of the key dimensional data corresponding to each of the key assessment indicators to the sum of the first occurrence numbers of all of the corresponding easily occurring dimensional data; Calculate the first weight product of the first weight of each of the key evaluation indicators and the second weight of the corresponding key dimension data, and sum the first weight products to obtain the corresponding first weight product sum; Based on each of the first weighted product sums, the corresponding target subject is verified.

4. The method for intelligent screening of clinical trial subjects according to claim 3, characterized in that: The verifying the corresponding target subject based on each of the first weight products specifically includes: Determine a corresponding historical user portrait based on basic information of historical subjects who have passed the historical clinical trial project, wherein the historical clinical trial project is a clinical trial project with the same indication as the target clinical project; Counting the second occurrence times of each of the historical user portraits, and selecting the historical user portrait with the third number from each of the historical user portraits in descending order of the second occurrence times to determine as the easy-to-pass user portrait; Obtain the remaining dimensional data except the corresponding basic information from the historical patient data of each historical subject of the easy-to-pass user portrait, count the third number of occurrences of each of the remaining dimensional data, and select the fourth number of remaining dimensional data from each of the remaining dimensional data in descending order of the third number of occurrences to determine as the easy-to-pass dimensional data of the corresponding easy-to-pass user portrait; Determine a corresponding target user profile based on the basic information in the patient data of each target subject; When the target user portrait is an easy-to-pass user portrait, the corresponding target subject is determined as the key subject, and based on the first weight product sum of the key subject, patient data, the target user portrait and each of the easy-to-pass dimension data, it is determined whether the key subject has passed the verification.

5. The method for intelligent screening of clinical trial subjects according to claim 4, characterized in that: The determining whether the key subject passes the verification based on the first weighted product sum of the key subject, the patient data, the target user portrait and each of the easy-to-pass dimension data specifically includes: Determine the third weight of the target user portrait and the fourth weight of the corresponding easy-to-pass dimension data. When easy-to-pass dimension data exists in the patient data of the key subject, determine the corresponding easy-to-pass dimension data as the target dimension data, and calculate the second weight product of the third weight and the fourth weight of the corresponding target dimension data, the third weight being the ratio of the second number of occurrences of the target user portrait to the sum of the second number of occurrences of all easy-to-pass user portraits, and the fourth weight being the ratio of the third number of occurrences of a single easy-to-pass dimension data corresponding to the target user portrait to the sum of the third number of occurrences of all corresponding easy-to-pass dimension data; Summing each of the second weighted products to obtain a second weighted product sum, and normalizing the second weighted product sum and the first weighted product sum of the key subjects to obtain a processed first weighted product sum and a processed second weighted product sum; If the processed second weight product sum is greater than the processed first weight product sum, subtracting the processed first weight product sum from the processed second weight product sum to obtain a difference; When the difference is greater than a preset difference threshold, it is determined that the key subject has passed the verification, and when the difference is not greater than the preset difference threshold, it is determined that the key subject has failed the verification.

6. The method for intelligent screening of clinical trial subjects according to claim 4, characterized in that: The determining whether the key subject has passed the verification based on the first weighted product sum of the key subject, the patient data, the target user portrait and each of the easy-to-pass dimension data specifically includes: Determine a third weight of the target user portrait and a fourth weight of the corresponding easy-to-pass dimension data, and when easy-to-pass dimension data exists in the patient data of the key subject, determine the corresponding easy-to-pass dimension data as the target dimension data, and calculate a second weight product of the third weight and the fourth weight of the corresponding target dimension data; Summing each of the second weighted products to obtain a second weighted product sum, and normalizing the second weighted product sum and the first weighted product sum of the key subjects to obtain a processed first weighted product sum and a processed second weighted product sum; If the first weighted product sum is less than a preset product sum threshold, comparing the processed first weighted product sum and the processed second weighted product sum; When the second weight product sum after the processing is greater than the first weight product sum after the processing, it is determined that the key subject has passed the verification.

7. The method for intelligent screening of clinical trial subjects according to claim 3, characterized in that: The method further comprises: If the verification passes, the maximum first weight product is selected from each of the first weight products, and the key evaluation indicator corresponding to the maximum first weight product is determined as the key monitoring indicator of the corresponding target subject in the test.

8. An intelligent screening device for clinical trial project subjects, characterized in that: include: A data acquisition module (11) is used to acquire patient data of at least one candidate patient, wherein the patient data includes dimensional data of the corresponding candidate patient under dimensions involved in inclusion criteria and exclusion criteria of a target clinical trial project; A first screening module (12) is used to pre-process the patient data of each candidate patient to obtain corresponding processed data, and input each processed data into a preset subject screening model to obtain target subjects that meet the test requirements of the target clinical trial project; An indicator determination module (13) is used to select an abnormal evaluation indicator from each efficacy evaluation indicator corresponding to the target clinical trial project, and determine the easily occurring dimensional data corresponding to each abnormal evaluation indicator when an abnormality occurs, wherein the easily occurring evaluation indicator is an efficacy evaluation indicator that is easily abnormal in patients with different diseases, the easily occurring dimensional data is dimensional data that is easily associated with patients with abnormalities in the easily occurring evaluation indicator, and the efficacy evaluation indicator is an indicator for evaluating the efficacy of the target clinical trial project on the subject's disease; A test subject verification module (14) is used to, when there is easily occurring dimension data in the patient data of each target subject, determine the corresponding easily occurring dimension data as key dimension data, and verify the corresponding target subject according to the key dimension data and the easy abnormality assessment index of the key dimension data in the corresponding easily occurring dimension data; The second screening module (15) is used to determine the corresponding target subject as the final subject of the target clinical trial project if the verification is passed.

9. A computer-readable storage medium having a computer program stored therein, characterized in that: When the computer program is loaded and executed by a processor, the method according to any one of claims 1 to 7 is adopted.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that: When the processor loads and executes the computer program, the method according to any one of claims 1 to 7 is adopted.

Images