Information Management Method, Device, Medium and Equipment for Drug Clinical Trials

Abstract

The present application relates to a method, device, medium and equipment for information management in drug clinical trials, belonging to the technical field of information management. The method includes: based on the test anomaly dimension, the target anomaly dimension where clinical trial information is prone to anomalies when the target subject has physical anomalies during drug clinical trials and the corresponding target fluctuation dimension, determining the cause of the anomaly of the abnormal clinical trial information; when the cause of the anomaly is an error in the entry of the abnormal clinical trial information, determining the appropriate entry form corresponding to the abnormal clinical trial information, and re-obtaining the clinical trial information of the test anomaly dimension based on the appropriate entry form; when the cause of the anomaly is that the target subject has physical anomalies during drug clinical trials, sending an anomaly warning to the terminal of the clinical trial staff. The present application has the effect of improving the accuracy of the collected clinical trial information.

Description

Technical Field

[0001] This application relates to the field of information management technology, and particularly to an information management method, device, medium, and equipment for drug clinical trials. Background Art

[0002] A drug clinical trial refers to any systematic study of a drug in humans (patients or healthy volunteers) to confirm or reveal the effects of the test drug, adverse reactions, and / or the absorption, distribution, metabolism, and excretion of the test drug, with the aim of determining the efficacy and safety of the test drug. Drug clinical trials are a key step for new drugs to move from the laboratory to the market, which is not only beneficial to individual patients but also promotes the health level and well-being of the entire society. In addition, the information management of drug clinical trials is also a particularly important link. The information management of drug clinical trials refers to a series of activities in the process of clinical trials to systematically and standardly collect, record, process, store, and report the test data, that is, clinical trial information and related information in various dimensions. Its purpose is to ensure the accuracy, integrity, and traceability of the data, so as to support scientific decision-making and regulatory requirements.

[0003] Currently, the common way to manage the information of drug clinical trials is as follows: during the clinical trial of subjects, clinical trial staff need to manually enter the clinical trial information of the subjects to complete the information management of drug clinical trials. However, in this way, once the volume of clinical trial information to be recorded is large, manual recording is prone to errors such as data entry errors, resulting in poor accuracy of the collected clinical trial information. Summary of the Invention

[0004] To improve the accuracy of the collected clinical trial information, this application provides an information management method, device, medium, and equipment for drug clinical trials.

[0005] In the first aspect of this application, an information management method for drug clinical trials is provided, specifically including:

[0006] Obtain at least one-dimensional target clinical trial information of the target subjects of the target drug;

[0007] If the target clinical trial information is not within the normal value range of the corresponding dimension, determine the corresponding target clinical trial information as abnormal clinical trial information, and determine the dimension corresponding to the abnormal clinical trial information as the test abnormal dimension;

[0008] Based on the test abnormal dimension, the target abnormal dimension where the clinical trial information is prone to abnormality when the target subject has a physical abnormality during the drug clinical trial, and the corresponding target fluctuation dimension, determine the cause of the abnormality of the abnormal clinical trial information, where the target fluctuation dimension is the dimension in which the clinical trial information is prone to abnormal fluctuation when the clinical trial information of the corresponding target abnormal dimension appears abnormal;

[0009] When the cause of the abnormality is an error in the entry of the abnormal clinical trial information, determine the appropriate entry form corresponding to the abnormal clinical trial information, and re-obtain the clinical trial information of the test abnormal dimension based on the appropriate entry form;

[0010] When the cause of the abnormality is that the target subject has a physical abnormality during the drug clinical trial, send an abnormality warning to the terminal of the clinical trial staff.

[0011] By adopting the above technical solution, after obtaining the target clinical trial information of the target subject in at least one dimension, if the target clinical trial information is not within the normal value range of the corresponding dimension, then it is determined as abnormal clinical trial information, indicating that the abnormal clinical trial information of the target subject appears abnormal, which may be due to the physical abnormality of the target subject during the target drug treatment, or may be due to an error in the entry by the staff, resulting in the abnormality of the abnormal clinical trial information. In order to ensure the accuracy of the entered clinical trial information, the cause of the abnormality of the abnormal clinical trial information is investigated. If the cause of the abnormality is an error in the entry, then it may be that the entry form is not very appropriate, so re-match the appropriate entry form and re-obtain the clinical trial information of this test abnormal dimension, thereby improving the accuracy of the collected clinical trial information; if the cause of the abnormality is a physical abnormality, not only can the physical condition of the target subject be checked in a timely manner by sending a warning, but also it can be verified that the entered clinical trial information is error-free, further improving the accuracy of the collected clinical trial information.

[0012] Optionally, the determining the cause of the abnormality of the abnormal clinical trial information based on the test abnormal dimension, the target abnormal dimension where the clinical trial information is prone to abnormality when the target subject has a physical abnormality during the drug clinical trial, and the corresponding target fluctuation dimension specifically includes:

[0013] Determine the target user portrait of the target subject, and obtain the historical abnormal dimensions where the clinical trial information appeared abnormal when the historical subjects of the target user portrait had physical abnormalities during the clinical trial of the target drug;

[0014] Count the first occurrence times of each of the historical abnormal dimensions, and select the historical abnormal dimension with the first number among all the historical abnormal dimensions in descending order of the first occurrence times as the target abnormal dimension. The first occurrence times refer to the number of occurrences of a single historical abnormal dimension among all historical abnormal dimensions;

[0015] Obtain other dimensions in which the clinical trial information fluctuates abnormally when an abnormality occurs in a single target abnormal dimension of a historical subject. Count the second occurrence times of each of the other dimensions, and select the other dimension with the second number among all the other dimensions in descending order of the second occurrence times as the target fluctuation dimension corresponding to the target abnormal dimension. The second occurrence times refer to the number of occurrences of a single other dimension among all other dimensions;

[0016] Calculate the first weight of each of the target abnormal dimensions and the second weights of the corresponding target fluctuation dimensions. The first weight is the ratio of the first occurrence times of each target abnormal dimension to the sum of the first occurrence times of all target abnormal dimensions. The second weight is the ratio of the second occurrence times of a single target fluctuation dimension corresponding to the target abnormal dimension to the sum of the second occurrence times of all the corresponding target fluctuation dimensions;

[0017] Determine the cause of the abnormal clinical trial information based on the trial abnormal dimension, the first weight, and the corresponding second weights.

[0018] By adopting the above technical solution, the larger the first occurrence times, the more likely the clinical trial information of the corresponding historical abnormal dimension is to be abnormal when the subject of the target user portrait has a physical abnormality during a drug clinical trial, and thus the target abnormal dimension is determined; the larger the second occurrence times, the more likely the corresponding other dimensions are to fluctuate abnormally when the target abnormal dimension is abnormal, and thus the target fluctuation dimension is determined. Finally, by combining the first weight and the corresponding second weights, the likelihood that the current abnormal clinical trial information is caused by a physical abnormality is determined, and thus the cause of the abnormal clinical trial information is accurately determined.

[0019] Optionally, the determining the cause of the abnormal clinical trial information based on the trial abnormal dimension, the first weight, and the corresponding second weights specifically includes:

[0020] Determine the remaining dimensions of the target subject except for the trial abnormal dimension, and determine at least one actual abnormal fluctuation dimension from the remaining dimensions according to the target clinical trial information of each of the remaining dimensions;

[0021] When the test abnormal dimension is the target abnormal dimension, at least one actual abnormal fluctuation dimension existing in each target fluctuation dimension corresponding to the test abnormal dimension is determined as the key abnormal fluctuation dimension, and the product of the first weight of the test abnormal dimension and the second weights of the corresponding key abnormal fluctuation dimensions is calculated to obtain the corresponding first product;

[0022] The sums of the first products are calculated to obtain the sum of the first products, and the sum of the first products is compared with a preset first threshold;

[0023] If the sum of the first products is greater than the first threshold, it is determined that the cause of the abnormality of the abnormal clinical trial information is that the target subject has an abnormality in the body during the drug clinical trial;

[0024] If the sum of the first products is not greater than the first threshold, it is determined that the cause of the abnormality of the abnormal clinical trial information is an error in the input of the abnormal clinical trial information.

[0025] By adopting the above technical solution, the larger the first product, the greater the possibility that the target subject has an abnormality in the body during the drug clinical trial when the test abnormal dimension actually has an abnormality and the key abnormal fluctuation dimension has an abnormal fluctuation. Further, the sums of the first products are calculated to obtain the sum of the first products. The larger the sum of the first products, the greater the overall possibility that the target subject has a physical abnormality, and the easier the cause of the abnormality of the abnormal clinical trial information is a physical abnormality. Finally, if the sum of the first products is greater than the first threshold, it is determined that the cause of the abnormality of the abnormal clinical trial information is that the target subject has an abnormality in the body during the drug clinical trial; otherwise, if the sum of the first products is not greater than the first threshold, it is determined that the cause of the abnormality of the abnormal clinical trial information is an error in the input of the abnormal clinical trial information.

[0026] Optionally, the method further includes:

[0027] The dimensions other than the test abnormal dimension of the target subject are determined as the remaining dimensions, and at least one actual abnormal fluctuation dimension is determined from the remaining dimensions according to the target clinical trial information of each remaining dimension;

[0028] The historical input forms with input errors in the historical clinical trial information of the clinical trial of the target drug are obtained, the first occurrence frequencies of each historical input form are counted, and the historical input form of the third number is selected from the historical input forms in descending order of the first occurrence frequencies and determined as the error-prone input form;

[0029] When obtaining the historical misrecording dimensions that went wrong when entering historical clinical trial information in each of the error-prone entry forms, count the second occurrence frequency of each of the historical misrecording dimensions, and select the historical misrecording dimension of the fourth number from each of the historical misrecording dimensions in descending order of the second occurrence frequency as the error-prone dimension corresponding to the error-prone entry form;

[0030] Calculate the third weight of each of the error-prone entry forms and the fourth weight of the corresponding error-prone dimensions. The third weight is the ratio of the first occurrence frequency of each error-prone entry form to the sum of the first occurrence frequencies of all error-prone entry forms, and the fourth weight is the ratio of the second occurrence frequency of a single error-prone dimension corresponding to the error-prone entry form to the sum of the second occurrence frequencies of all error-prone dimensions corresponding to the error-prone entry form;

[0031] According to the actual entry form of the target clinical trial information of each of the actual abnormal fluctuation dimensions, the third weight, and the corresponding fourth weights, verify the cause of the abnormality of the abnormal clinical trial information.

[0032] By adopting the above technical solution, the larger the first occurrence frequency, the easier it is to make mistakes when entering historical clinical trial information of the target drug using the corresponding historical entry form, and thus the error-prone entry form is determined; the larger the second occurrence frequency, the easier it is to make mistakes when entering the corresponding historical misrecording dimension in the error-prone entry form, and thus the error-prone dimension is determined. Finally, combined with the third weight and the corresponding fourth weights, analyze the possibility that the abnormal fluctuation of the actual abnormal fluctuation dimension is caused by entry errors, and then verify the reasonableness of the cause of the abnormality.

[0033] Optionally, the verifying the cause of the abnormality of the abnormal clinical trial information according to the actual entry form of the target clinical trial information of each of the actual abnormal fluctuation dimensions, the third weight, and the corresponding fourth weights specifically includes:

[0034] Determine the error-prone entry forms with at least one actual abnormal fluctuation dimension in the corresponding error-prone dimensions as the key entry forms. When the key entry form is the corresponding actual entry form, calculate the sum of the second products of the third weight of each of the key entry forms and the fourth weight of the corresponding actual abnormal fluctuation dimension to obtain the sum of the second products;

[0035] If the sum of the second products is not greater than a preset second threshold, it is determined that the verification of the cause of the abnormality of the abnormal clinical trial information is correct;

[0036] If the sum of the second products is greater than a preset second threshold, the actual abnormal fluctuation dimension corresponding to the second product exceeding the preset product threshold is determined as the misrecorded fluctuation dimension, and if the misrecorded fluctuation dimension exists in each of the key abnormal fluctuation dimensions, the misrecorded fluctuation dimension is removed from each of the key abnormal fluctuation dimensions to obtain a calibrated fluctuation dimension;

[0037] Calculating the third product of the first weight of the test abnormality dimension and the corresponding second weight of each calibration fluctuation dimension and summing them to obtain the sum of the third products;

[0038] If the sum of the third products is not greater than the first threshold, then when the abnormal cause of the abnormal clinical trial information is that the target subject has a physical abnormality in the drug clinical trial, the abnormal cause of the abnormal clinical trial information is calibrated as an error occurring during entry.

[0039] By adopting the above technical solution, the larger the sum of the second products, the greater the possibility that the target clinical trial information of the actual abnormal fluctuation dimension will be wrong during the actual entry. If the sum of the second products is not greater than the second threshold, it means that the possibility of error during entry is small, then the possibility of abnormal fluctuation in the actual abnormal fluctuation dimension due to the error in the target clinical trial information entry is small, and then the abnormal cause is verified to be correct; if the sum of the second products is greater than the second threshold, it means that the target clinical trial information of the actual abnormal fluctuation dimension is more likely to be wrong during the actual entry, and there is a high probability that the actual abnormal fluctuation dimension does not actually have abnormal fluctuations, but is caused by an error in recording. If the sum of the third products is not greater than the first threshold, it means that the target subject is less likely to have physical abnormalities, and the appearance of abnormal clinical trial information may be caused by an entry error. If the determined abnormal cause is physical abnormality, then the abnormal cause is calibrated to an error during entry. Thereby, not only can the false triggering of physical abnormality warnings be avoided, but also the problem of its entry error can be identified.

[0040] Optionally, the determining of an appropriate input form corresponding to the abnormal clinical trial information specifically includes:

[0041] Determine the error-prone entry form in which the test abnormality dimension exists in the corresponding error-prone entry dimensions as a reference entry form, and calculate the fourth product of the third weight of each reference entry form and the fourth weight of the corresponding test abnormality dimension;

[0042] A minimum fourth product is selected from each of the fourth products, and a reference entry form corresponding to the minimum fourth product is determined as a suitable entry form corresponding to the abnormal clinical trial information.

[0043] By adopting the above technical solution, the larger the fourth product is, the greater the possibility that the target clinical trial information of the test abnormal dimension entered in the corresponding reference entry form is incorrect. Then, select the smallest fourth product from each of the fourth products, and determine the reference entry form corresponding to the smallest fourth product as the appropriate entry form corresponding to the abnormal clinical trial information. Re-enter the clinical trial information of the test abnormal dimension in this appropriate entry form, and the possibility of entry error is relatively small.

[0044] Optionally, the method further includes:

[0045] If there is no abnormal clinical trial information, determine the reference fluctuation dimension with abnormal fluctuation of at least one target clinical trial information, and determine the target abnormal dimension with at least one reference fluctuation dimension among the corresponding target fluctuation dimensions as the dimension to be concerned;

[0046] Calculate the fifth product of the first weight of each dimension to be concerned and the second weight of the corresponding reference fluctuation dimensions and sum them to obtain the corresponding sum of products;

[0047] Select the largest sum of products from each of the sums of products. If the largest sum of products is greater than a preset first threshold, when there is no error in the entry of the target clinical trial information of the reference fluctuation dimension corresponding to the largest sum of products, send a wrong entry reminder to the terminal for the dimension to be concerned corresponding to the largest sum of products.

[0048] By adopting the above technical solution, the larger the sum of products is, the greater the possibility that the target subject has physical abnormalities during the drug clinical trial, and the greater the possibility that the target clinical trial information of the corresponding dimension to be concerned is abnormal. Further, select the largest sum of products from each of the sums of products. If the largest sum of products is greater than the first threshold, it means that the dimension to be concerned corresponding to this largest sum of products is more likely to be abnormal due to physical abnormalities. When there is no error in the entry of the target clinical trial information of the reference fluctuation dimension corresponding to the largest sum of products, it means that it is very likely that the dimension to be concerned corresponding to the largest sum of products is entered incorrectly. Then, send a wrong entry reminder for this dimension to be concerned to the terminal, so as to ensure the accuracy of the entered clinical trial information.

[0049] In the second aspect of the present application, an information management device for drug clinical trials is provided, which specifically includes:

[0050] An information acquisition module, configured to acquire target clinical trial information of at least one dimension of a target subject of a target drug;

[0051] An abnormality determination module, configured to, if the target clinical trial information is not within the normal value range of the corresponding dimension, determine the corresponding target clinical trial information as abnormal clinical trial information, and determine the dimension corresponding to the abnormal clinical trial information as the test abnormal dimension;

[0052] A cause determination module, configured to determine the cause of the abnormal clinical trial information based on the trial abnormal dimension, the target abnormal dimension where the clinical trial information is prone to be abnormal when the target subject has a physical abnormality during a drug clinical trial, and the corresponding target fluctuation dimension, where the target fluctuation dimension is the dimension in which the clinical trial information is prone to abnormal fluctuations when the clinical trial information corresponding to the target abnormal dimension is abnormal;

[0053] An input adjustment module, configured to determine the appropriate input form corresponding to the abnormal clinical trial information when the cause of the abnormality is an error in inputting the abnormal clinical trial information, and re-obtain the clinical trial information of the trial abnormal dimension based on the appropriate input form;

[0054] An abnormal warning module, configured to send an abnormal warning to the terminal of the clinical trial staff when the cause of the abnormality is that the target subject has a physical abnormality during the drug clinical trial.

[0055] By adopting the above technical solution, the information acquisition module acquires the target clinical trial information of at least one dimension, the abnormal determination module determines the corresponding target clinical trial information as abnormal clinical trial information, then the cause determination module determines the cause of the abnormal clinical trial information, then the input adjustment module determines the appropriate input form corresponding to the abnormal clinical trial information, and finally the abnormal warning module sends an abnormal warning to the terminal of the clinical trial staff when the cause of the abnormality is a physical abnormality.

[0056] In a third aspect of the present application, a computer-readable storage medium is provided. A computer program is stored in the computer-readable storage medium. When the computer program is loaded and executed by a processor, the method steps described in any one of the first aspects are executed.

[0057] In a fourth aspect of the present application, an electronic device is provided, specifically including:

[0058] A processor, a memory, and a computer program stored in the memory and capable of running on the processor. The processor is configured to load and execute the computer program stored in the memory so that the electronic device executes the method described in any one of the first aspects.

[0059] In summary, the present application includes at least one of the following beneficial technical effects: If the target clinical trial information is not within the normal value range of the corresponding dimension, it is determined as abnormal clinical trial information, indicating that the abnormal clinical trial information of the target subject appears abnormal. It may be that the target subject's body appears abnormal during the treatment with the target drug, or it may be an error occurred during the input by the staff, resulting in the abnormality of the abnormal clinical trial information. In order to ensure the accuracy of the input clinical trial information, the cause of the abnormality of the abnormal clinical trial information is investigated. If the cause of the abnormality is an error during input, it may be that the input form is not appropriate enough. Then, a suitable input form is re-matched, and the clinical trial information of this test's abnormal dimension is re-obtained, thereby improving the accuracy of the collected clinical trial information. If the cause of the abnormality is that the body appears abnormal, not only can the physical condition of the target subject be checked in a timely manner by issuing a warning, but also it can be verified that the input clinical trial information is error-free, further improving the accuracy of the collected clinical trial information. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 is a schematic flowchart of a method for managing information of a drug clinical trial provided by an embodiment of the present application;

[0061] Figure 2 is a schematic structural diagram of a device for managing information of a drug clinical trial provided by an embodiment of the present application;

[0062] Figure 3 is a schematic structural diagram of another device for managing information of a drug clinical trial provided by an embodiment of the present application.

[0063] Description of the reference numerals: 11, information acquisition module; 12, abnormality determination module; 13, cause determination module; 14, input adjustment module; 15, abnormality warning module; 16, cause verification module; 17, input error reminder module. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0064] 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 accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments.

[0065] In the description of the embodiments of the present application, words such as "exemplary", "for example" or "for illustration" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "exemplary", "for example" or "for illustration" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, the words such as "exemplary", "for example" or "for illustration" are intended to present relevant concepts in a specific manner.

[0066] See Figure 1 , the embodiment of the present application discloses a schematic flowchart of an information management method for drug clinical trials, which can be implemented depending on a computer program or run on an information management device for drug clinical trials based on the von Neumann architecture. This computer program can be integrated into an application or run as an independent tool-type application, and specifically includes:

[0067] S101: Obtain the target clinical trial information of the target subject of the target drug in at least one dimension.

[0068] Specifically, in the embodiment of the present application, the target drug is a new drug undergoing drug clinical trials, and the target subject is a patient or volunteer participating in the clinical trials of this target drug. The target clinical trial information can be various dimensions of laboratory test information during the treatment of the target subject with the target drug. Among them, the laboratory test information can be urine glucose data, blood lipid data, blood glucose data, etc. In other embodiments, the target clinical trial information can also be various dimensions of vital sign data during the treatment of the target subject with the target drug. Exemplarily, the vital sign data can be heart rate, body temperature, blood pressure, etc.

[0069] Furthermore, the execution subject of an information management method for drug clinical trials disclosed in the embodiment of the present application can be a server. The server is wirelessly connected to the terminal, and a client related to drug clinical trial information management is installed in the terminal. The server can be the background server of the client, specifically a physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal can be the personal computer or tablet computer of the clinical trial staff or researchers of this target drug. A feasible way to obtain the target clinical trial information of the target subject in at least one dimension is: the clinical trial staff enter the target clinical trial information of the target subject locally and send it to the server through the client in the terminal. The server finally obtains the target clinical trial information in each dimension, thereby collecting and storing the physical condition data of the subject during the treatment with the target drug, and helping the researchers of the clinical trial better evaluate the efficacy and safety of this target drug. It should be noted that the input form of the target clinical trial information by the clinical trial staff includes but is not limited to image input form, voice input form, and text input form, etc. The target clinical trial information input by the terminal obtained is also multi-modal data, that is, text data, image data, or video data, etc.

[0070] S102: If the target clinical trial information is not within the normal value range of the corresponding dimension, determine the corresponding target clinical trial information as abnormal clinical trial information, and determine the dimension corresponding to the abnormal clinical trial information as the trial abnormal dimension.

[0071] Specifically, after obtaining the target clinical trial information of each dimension, compare the target clinical trial information of each dimension with the normal value range of the corresponding dimension. The normal value range is the value range in which the target clinical trial information of the corresponding dimension is located when the physical condition of the target subject is normal. If the target clinical trial information is not within the normal value range of the corresponding dimension, it indicates that the target clinical trial information of the corresponding dimension of the target subject is abnormal. It may be that the target subject's body is abnormal during the target drug treatment, or it may be that there is an error in the input by the staff, resulting in the abnormality of the target clinical trial information. Then, determine the corresponding target clinical trial information as abnormal clinical trial information, and at the same time, determine the dimension corresponding to this abnormal clinical trial information as the trial abnormal dimension.

[0072] S103: Based on the trial abnormal dimension, the target abnormal dimension where the clinical trial information is prone to be abnormal when the target subject's body is abnormal during the drug clinical trial, and the corresponding target fluctuation dimension, determine the abnormal reason of the abnormal clinical trial information.

[0073] Specifically, after the trial abnormal dimension is determined, it is necessary to further determine the abnormal reason of this abnormal clinical trial information. In the embodiment of the present application, the abnormal reasons are divided into errors in input and physical abnormalities during the drug clinical trial. A feasible determination method is: input the basic information registered when the target subject signs up for the drug clinical trial into a preset portrait prediction model to obtain the corresponding target user portrait. The basic information includes, but is not limited to, age, gender, weight, past medical history information, allergy history, etc. The portrait prediction model is a trained decision tree model or a trained deep neural network model. The training process is briefly described as: using the basic information of historical subjects marked with user portraits as training samples, inputting them into the model for training, and continuously optimizing and adjusting the model parameters through the loss function and the reverse gradient algorithm until the model converges. This is the prior art and will not be elaborated here.

[0074] Further, retrieve the analysis records of the clinical trial information of historical subjects who have participated in the target drug. The analysis records include the historical abnormal dimensions that actually appeared abnormally in the clinical trial information of historical subjects and the clinical trial information with abnormal fluctuations at the same time. Abnormal fluctuations can be understood as the situation where the numerical fluctuations exceed the normal fluctuation range. Based on the above analysis records, when the historical subjects in the target user profile have physical abnormalities in the clinical trial of the target drug, obtain the historical abnormal dimensions in which the clinical trial information has appeared abnormally, and count the first occurrence times of each historical abnormal dimension. The larger the first occurrence times, the more likely the clinical trial information of the corresponding historical abnormal dimension is to appear abnormally when the subjects in the target user profile have physical abnormalities during the drug clinical trial. Then, in the order from largest to smallest of the first occurrence times, select the historical abnormal dimension with the first number from each historical abnormal dimension and determine it as the target abnormal dimension. Further, based on the above analysis records, when the historical subjects have abnormalities in a single target abnormal dimension, obtain the other dimensions with abnormal fluctuations in the clinical trial information that occur concomitantly, and count the second occurrence times of each other dimension. The larger the second occurrence times, the more likely the corresponding other dimension is to have abnormal fluctuations when the target abnormal dimension appears abnormally. Then, in the order from largest to smallest of the second occurrence times, select the other dimension with the second number from each other dimension and determine it as the target fluctuation dimension corresponding to the target abnormal dimension, that is, the dimension in which the clinical trial information is likely to have abnormal fluctuations when the clinical trial information of the corresponding target abnormal dimension appears abnormally. Among them, the first occurrence times is the occurrence times of a single historical abnormal dimension among all historical abnormal dimensions; the second occurrence times is the occurrence times of a single other dimension among all other dimensions.

[0075] Further, calculate the first weight of each target abnormal dimension and the second weight of the corresponding target fluctuation dimensions. The first weight is the ratio of the first occurrence times of each target abnormal dimension to the sum of the first occurrence times of all target abnormal dimensions, and the second weight is the ratio of the second occurrence times of a single target fluctuation dimension corresponding to the target abnormal dimension to the sum of the second occurrence times of all target fluctuation dimensions corresponding to the target abnormal dimension.

[0076] Further, determine the dimensions other than the test abnormal dimension of the target subject as the remaining dimensions. Based on the target clinical trial information of a single remaining dimension obtained currently and the clinical trial information entered previously, use a preset MATLAB tool to draw the data fluctuation curve of this remaining dimension, and fit this data fluctuation curve with the corresponding normal fluctuation curve. If the fitting rate does not exceed the preset fitting rate threshold, it indicates that the similarity between the data fluctuation curve and the corresponding normal fluctuation curve is low. Then determine the corresponding remaining dimension as the actual abnormal fluctuation dimension of the target subject. When the test abnormal dimension is the target abnormal dimension, determine at least one actual abnormal fluctuation dimension existing in each target fluctuation dimension corresponding to the test abnormal dimension as the key abnormal fluctuation dimension. Then calculate the product of the first weight of the test abnormal dimension and the second weight of each corresponding key abnormal fluctuation dimension to obtain the corresponding first product. The larger the first product, when the test abnormal dimension truly shows an abnormality and the key abnormal fluctuation dimension has an abnormal fluctuation, the greater the possibility that the target subject's body has an abnormality during the drug clinical trial. Further, sum up each first product to obtain the sum of the first products. The larger the sum of the first products, the greater the overall possibility that the target subject has a body abnormality, and the easier it is for the abnormal cause of the abnormal clinical trial information to be a body abnormality. Finally, if the sum of the first products is greater than the first threshold, determine that the abnormal cause of the abnormal clinical trial information is that the target subject has a body abnormality during the drug clinical trial; otherwise, if the sum of the first products is not greater than the first threshold, determine that the abnormal cause of the abnormal clinical trial information is an error occurred during the entry of the abnormal clinical trial information.

[0077] In one embodiment, after determining at least one actual abnormal fluctuation dimension from each remaining dimension of the target subject, based on the statistical record of the entry situation of the historical clinical trial information of the target drug, obtain the historical entry forms with entry errors that occurred in the historical clinical trial information of the clinical trial of the target drug. The statistical record of the entry situation includes, but is not limited to, the entry forms when errors occurred in the entry of the historical clinical trial information and the dimensions of the mis-entered information, etc. Count the first occurrence frequency of each historical entry form. The larger the first occurrence frequency, when using the corresponding historical entry form for the entry of the historical clinical trial information of the target drug, the more likely the entered information is to have an error. Select the historical entry form with the third number from largest to smallest in terms of the first occurrence frequency from each historical entry form and determine it as the error-prone entry form, that is, the entry form that the entered clinical trial information is likely to have.

[0078] Furthermore, based on the above-mentioned recorded situation statistics, obtain the historical misrecording dimensions where errors occur when entering historical clinical trial information in error-prone entry forms. Count the second occurrence frequency of each historical misrecording dimension. The greater the second occurrence frequency, the more likely it is to make an error when entering the corresponding historical misrecording dimension in the error-prone entry form. And select the historical misrecording dimension with the fourth number from each historical misrecording dimension in descending order of the second occurrence frequency as the error-prone dimension corresponding to the error-prone entry form, that is, the dimension where clinical trial information errors are likely to occur during entry.

[0079] Furthermore, calculate the third weight of each error-prone entry form and the fourth weight of the corresponding error-prone dimensions. The third weight is the ratio of the first occurrence frequency of each error-prone entry form to the sum of the first occurrence frequencies of all error-prone entry forms. The fourth weight is the ratio of the second occurrence frequency of a single error-prone dimension corresponding to the error-prone entry form to the sum of the second occurrence frequencies of all corresponding error-prone dimensions. Further, according to the actual entry form, the third weight, and the corresponding fourth weights of the target clinical trial information of each actual abnormal fluctuation dimension, verify the determined abnormal cause, thereby improving the accuracy of the abnormal cause.

[0080] A feasible verification method is as follows: Determine the error-prone entry forms with at least one actual abnormal fluctuation dimension in the corresponding error-prone dimensions as key entry forms. When the key entry form is the actual entry form corresponding to the existing actual abnormal fluctuation dimension, calculate the sum of the second products of the third weights of each key entry form and the fourth weights of the corresponding actual abnormal fluctuation dimensions, and obtain the sum of the second products. The greater the sum of the second products, the greater the possibility that the target clinical trial information of the actual abnormal fluctuation dimension has an error in this actual entry. If the sum of the second products is not greater than the preset second threshold, it indicates that the possibility of making an error during entry is small. Then the possibility that the actual abnormal fluctuation dimension has abnormal fluctuations due to the entry error of the target clinical trial information is small, and thus verify that the determined abnormal cause is correct. At the same time, it can also verify by the way that there is no entry error problem with the target clinical trial information entered for the actual abnormal fluctuation dimension this time.

[0081] If the sum of the second products is greater than the preset second threshold, it indicates that the possibility of making an error during the actual entry of the target clinical trial information of the actual abnormal fluctuation dimension is large. Most likely, there is no real abnormal fluctuation in the actual abnormal fluctuation dimension, but it is caused by misrecording. Then compare each second product with the preset product threshold. If the second product exceeds the product threshold, determine the corresponding actual abnormal fluctuation dimension as the misrecording fluctuation dimension, that is, the dimension with a high possibility of entry error. At the same time, remind the personnel that there is a risk of misrecording in the target clinical trial information of this misrecording fluctuation dimension.

[0082] Further, eliminate the recorded error fluctuation dimensions existing in each of the above key abnormal fluctuation dimensions to obtain calibrated fluctuation dimensions, which are key abnormal fluctuation dimensions with relatively low risk of input errors. Then, recalculate the sum of the third products of the first weight of the test abnormal dimension and the second weights of the corresponding calibrated fluctuation dimensions, and obtain the sum of the third products. Finally, compare the sum of the third products with the first threshold. If the sum of the third products is not greater than the first threshold, it indicates that the possibility of the target subject having a physical abnormality is relatively small, and the occurrence of abnormal clinical trial information may be caused by input errors. If the determined abnormal cause is that the target subject has a physical abnormality during the drug clinical trial, then calibrate the abnormal cause to an error during input. This can not only avoid false triggering of physical abnormality warnings but also identify input error problems.

[0083] S104: When the abnormal cause is an error during the input of abnormal clinical trial information, determine the appropriate input form corresponding to the abnormal clinical trial information, and re-obtain the clinical trial information of the test abnormal dimension based on the appropriate input form.

[0084] Specifically, after determining that the abnormal cause is an error during the input of abnormal clinical trial information, it is necessary to determine the appropriate input form corresponding to the abnormal clinical trial information. A feasible determination method is as follows: Determine the error-prone input form in which this test abnormal dimension exists in each corresponding error-prone dimension as the reference input form, calculate the fourth product of the third weight of each reference input form and the fourth weight of the corresponding test abnormal dimension. The larger the fourth product, the greater the possibility of an error occurring when inputting the target clinical trial information of the test abnormal dimension in the corresponding reference input form. Then, select the smallest fourth product from each of the fourth products, and determine the reference input form corresponding to the smallest fourth product as the appropriate input form corresponding to the abnormal clinical trial information. Re-enter the clinical trial information of the test abnormal dimension in this appropriate input form, and the possibility of an input error is relatively small. Further, send a re-entry reminder message for this test abnormal dimension to the terminal. The re-entry reminder message includes the appropriate input form, so as to re-obtain the clinical trial information of the test abnormal dimension based on the appropriate input form, and thus ensure the accuracy of the collected clinical trial information. In other embodiments, obtain the actual target input form of the abnormal clinical trial information. When the target input form is an error-prone input form, calculate the weight product of the third weight of the target input form and the fourth weight of the corresponding test abnormal dimension. If the weight product is greater than the preset product threshold, the possibility of an error occurring when inputting the target clinical trial information of the test abnormal dimension in the target input form is relatively large. Then, verify again that the abnormal cause is indeed an error during the input of abnormal clinical trial information. At the same time, if the smallest fourth product is less than this weight product, it can also verify that the appropriate input form is relatively reasonable. It should be noted that the abnormal cause can also be the verified abnormal cause in step S103.

[0085] S105: When the abnormal reason is that the target subject has physical abnormalities during the drug clinical trial, send an abnormal warning to the terminal of the clinical trial staff.

[0086] Specifically, when the abnormal reason is that the target subject has physical abnormalities during the drug clinical trial, then send an abnormal warning of the drug clinical trial of the target subject to the terminal of the clinical trial staff, so as to promptly go to check the physical condition of the target subject in time and avoid problems with the target subject's body during the drug clinical trial.

[0087] In other embodiments, if there is no abnormal clinical trial information in the target clinical trial information of each dimension of the target subject, then determine the reference fluctuation dimension with abnormal fluctuations in the target clinical trial information of each dimension. The determination method of abnormal fluctuations can be seen in step S103 and will not be elaborated here. Further, determine at least one target abnormal dimension of the reference fluctuation dimension existing in the corresponding target fluctuation dimensions as the dimension to be concerned. Calculate the sum of the fifth products of the first weight of each dimension to be concerned and the second weight of the corresponding reference fluctuation dimensions, and obtain the corresponding sum of products. The larger the sum of products, the greater the possibility of physical abnormalities of the target subject during the drug clinical trial, and the greater the possibility of abnormalities in the target clinical trial information of the corresponding dimension to be concerned. Further, select the largest sum of products from each sum of products. If the largest sum of products is greater than the first threshold, it means that the dimension to be concerned corresponding to this largest sum of products is more likely to have abnormalities due to physical abnormalities. When there is no error in the input of the target clinical trial information of the reference fluctuation dimension corresponding to the largest sum of products, it means that it is very likely that there is an error in the input of the dimension to be concerned corresponding to the largest sum of products. Then send a wrong input reminder for this dimension to be concerned to the terminal to ensure the accuracy of the input clinical trial information. It should be noted that the determination method for there being no error in the input of the target clinical trial information of the reference fluctuation dimension corresponding to the largest sum of products can be seen in step S103 and will not be elaborated here.

[0088] The implementation principle of the information management method for drug clinical trials in the embodiments of this application is as follows: If the target clinical trial information is not within the normal value range of the corresponding dimension, it is determined as abnormal clinical trial information, indicating that there is an abnormality in the abnormal clinical trial information of the target subject. This may be due to an abnormality in the target subject's body during the treatment with the target drug, or it may be due to an error in data entry by the staff, resulting in the abnormality of the abnormal clinical trial information. To ensure the accuracy of the entered clinical trial information, an investigation is carried out on the cause of the abnormality of the abnormal clinical trial information. If the cause of the abnormality is an error in data entry, it may be that the entry form is not appropriate. Then, a suitable entry form is re-matched, and the clinical trial information of this trial's abnormal dimension is re-obtained, thereby improving the accuracy of the collected clinical trial information. If the cause of the abnormality is a physical abnormality, not only can the physical condition of the target subject be checked in a timely manner by issuing a warning, but it can also be verified that the entered clinical trial information is error-free, further improving the accuracy of the collected clinical trial information.

[0089] The following are the device embodiments of this application, which can be used to execute the method embodiments of this application. For the details not disclosed in the device embodiments of this application, please refer to the method embodiments of this application.

[0090] Please refer to Figure 2 , which is a schematic structural diagram of the information management device for drug clinical trials provided by the embodiments of this application. The information management device applied to drug clinical trials can be implemented as all or part of the device through software, hardware, or a combination of both. The device includes an information acquisition module 11, an abnormality determination module 12, a cause determination module 13, an entry adjustment module 14, and an abnormality warning module 15.

[0091] The information acquisition module 11 is used to acquire the target clinical trial information of at least one dimension of the target subject of the target drug;

[0092] The abnormality determination module 12 is used to determine the corresponding target clinical trial information as abnormal clinical trial information if the target clinical trial information is not within the normal value range of the corresponding dimension, and determine the dimension corresponding to the abnormal clinical trial information as the trial abnormal dimension;

[0093] The cause determination module 13 is used to determine the cause of the abnormality of the abnormal clinical trial information based on the trial abnormal dimension, the target abnormal dimension where the clinical trial information is prone to abnormality when the target subject has a physical abnormality during the drug clinical trial, and the corresponding target fluctuation dimension. The target fluctuation dimension is the dimension in which the clinical trial information is prone to abnormal fluctuations when the clinical trial information of the corresponding target abnormal dimension appears abnormal;

[0094] An input adjustment module 14, which is used to determine the appropriate input form corresponding to the abnormal clinical trial information when an error occurs during the input of abnormal clinical trial information, and re-obtain the clinical trial information of the test abnormal dimension based on the appropriate input form;

[0095] An abnormal warning module 15, which is used to send an abnormal warning to the terminal of the clinical trial staff when the abnormal reason is that the target subject has an abnormality in the body during the drug clinical trial.

[0096] Optionally, the reason determination module 13 is specifically used for:

[0097] Determine the target user portrait of the target subject, and obtain the historical abnormal dimensions in which the clinical trial information was abnormal when the historical subjects of the target user portrait had physical abnormalities during the clinical trial of the target drug;

[0098] Count the first occurrence times of each historical abnormal dimension, and select the historical abnormal dimension with the first number from each historical abnormal dimension in the order from largest to smallest first occurrence times as the target abnormal dimension. The first occurrence times are the occurrence times of a single historical abnormal dimension among all historical abnormal dimensions;

[0099] Obtain other dimensions in which the clinical trial information fluctuates abnormally when a single target abnormal dimension appears abnormally for the historical subjects, count the second occurrence times of each other dimension, and select the other dimension with the second number from each other dimension in the order from largest to smallest second occurrence times as the target fluctuation dimension corresponding to the corresponding target abnormal dimension. The second occurrence times are the occurrence times of a single other dimension among all other dimensions;

[0100] Calculate the first weight of each target abnormal dimension and the second weight of the corresponding target fluctuation dimensions. The first weight is the ratio of the first occurrence times of each target abnormal dimension to the sum of the first occurrence times of all target abnormal dimensions, and the second weight is the ratio of the second occurrence times of a single target fluctuation dimension corresponding to the target abnormal dimension to the sum of the second occurrence times of all target fluctuation dimensions corresponding to the target abnormal dimension;

[0101] Determine the abnormal reason of the abnormal clinical trial information according to the test abnormal dimension, the first weight, and the corresponding second weights.

[0102] Optionally, the reason determination module 13 is specifically used for:

[0103] Determine the dimensions other than the test abnormal dimension of the target subject as the remaining dimensions, and determine at least one actual abnormal fluctuation dimension from each remaining dimension according to the target clinical trial information of each remaining dimension;

[0104] When the test anomaly dimension is the target anomaly dimension, at least one actual abnormal fluctuation dimension existing in each target fluctuation dimension corresponding to the test anomaly dimension is determined as the key abnormal fluctuation dimension, and the product of the first weight of the test anomaly dimension and the second weight of each corresponding key abnormal fluctuation dimension is calculated to obtain the corresponding first product;

[0105] Sum the first products to obtain the sum of the first products, and compare the sum of the first products with a preset first threshold;

[0106] If the sum of the first products is greater than the first threshold, it is determined that the reason for the abnormality of the abnormal clinical trial information is that the subject's body shows abnormalities in the drug clinical trial;

[0107] If the sum of the first products is not greater than the first threshold, it is determined that the reason for the abnormality of the abnormal clinical trial information is an error in the entry of the abnormal clinical trial information.

[0108] Optionally, as Figure 3 shown, the device further includes a cause verification module 16, which is specifically used for:

[0109] Determine the dimensions other than the test anomaly dimension of the target subject as the remaining dimensions, and determine at least one actual abnormal fluctuation dimension from each of the remaining dimensions according to the target clinical trial information of each remaining dimension;

[0110] Obtain the historical entry forms with entry errors in the historical clinical trial information of the clinical trial of the target drug, count the first occurrence frequency of each historical entry form, and select the historical entry form with the third number from each historical entry form in descending order of the first occurrence frequency as the error-prone entry form;

[0111] Obtain the historical misentry dimensions when entering the historical clinical trial information in each error-prone entry form, count the second occurrence frequency of each historical misentry dimension, and select the historical misentry dimension with the fourth number from each historical misentry dimension in descending order of the second occurrence frequency as the error-prone dimension corresponding to the corresponding error-prone entry form;

[0112] Calculate the third weight of each error-prone entry form and the fourth weight of each corresponding error-prone dimension. The third weight is the ratio of the first occurrence frequency of each error-prone entry form to the sum of the first occurrence frequencies of all error-prone entry forms, and the fourth weight is the ratio of the second occurrence frequency of a single error-prone dimension corresponding to the error-prone entry form to the sum of the second occurrence frequencies of all error-prone dimensions corresponding to the error-prone entry form;

[0113] Verify the reason for the abnormality of the abnormal clinical trial information according to the actual entry form, the third weight, and the corresponding fourth weights of the target clinical trial information of each actual abnormal fluctuation dimension.

[0114] Optionally, the cause verification module 16 is specifically configured to:

[0115] Determine the error-prone entry forms with at least one actual abnormal fluctuation dimension in the corresponding error-prone dimensions as the key entry forms. When the key entry form is the corresponding actual entry form, calculate the second product of the third weight of each key entry form and the fourth weight of the corresponding actual abnormal fluctuation dimension and sum them to obtain the sum of the second products;

[0116] If the sum of the second products is not greater than the preset second threshold, it is determined that the verification of the abnormal cause of the abnormal clinical trial information is correct;

[0117] If the sum of the second products is greater than the preset second threshold, determine the actual abnormal fluctuation dimension corresponding to the second product exceeding the preset product threshold as the wrongly recorded fluctuation dimension. If there is a wrongly recorded fluctuation dimension among the key abnormal fluctuation dimensions, then remove the wrongly recorded fluctuation dimension from the key abnormal fluctuation dimensions to obtain the calibrated fluctuation dimension;

[0118] Calculate the third product of the first weight of the test abnormal dimension and the second weight of the corresponding calibrated fluctuation dimensions and sum them to obtain the sum of the third products;

[0119] If the sum of the third products is not greater than the first threshold, when the abnormal cause of the abnormal clinical trial information is that the body of the target subject has an abnormality in the drug clinical trial, calibrate the abnormal cause of the abnormal clinical trial information as an error occurred during entry.

[0120] Optionally, the entry adjustment module 14 is specifically configured to:

[0121] Determine the error-prone entry forms with test abnormal dimensions in the corresponding error-prone dimensions as the reference entry forms, and calculate the fourth product of the third weight of each reference entry form and the fourth weight of the corresponding test abnormal dimension;

[0122] Select the smallest fourth product from each fourth product, and determine the reference entry form corresponding to the smallest fourth product as the appropriate entry form corresponding to the abnormal clinical trial information.

[0123] Optionally, the device further includes a wrong entry reminder module 17, which is specifically configured to:

[0124] If there is no abnormal clinical trial information, determine the reference fluctuation dimensions with abnormal fluctuations in at least one target clinical trial information, and determine the target abnormal dimensions with at least one reference fluctuation dimension in the corresponding target fluctuation dimensions as the dimensions to be concerned;

[0125] Calculate the fifth product of the first weight of each dimension to be concerned and the second weight of the corresponding reference fluctuation dimensions and sum them to obtain the corresponding sum of products;

[0126] Select the maximum sum of products from the sums of each product. If the maximum sum of products is greater than a preset first threshold, when there is no error in entering the target clinical trial information in the reference fluctuation dimension corresponding to the maximum sum of products, send a wrong entry reminder to the terminal for the dimension to be concerned corresponding to the maximum sum of products.

[0127] It should be noted that when the information management device for drug clinical trials provided in the above embodiments executes the information management method for drug clinical trials, only the above division of each functional module is used for illustration. In practical applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the information management device for drug clinical trials and the information management method embodiments provided in the above embodiments belong to the same concept. The implementation process is detailed in the method embodiments and will not be repeated here.

[0128] The embodiments of the present application also disclose a computer-readable storage medium. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, it adopts the information management method for drug clinical trials in the above embodiments.

[0129] 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 some middleware form, etc. The computer-readable medium includes any entity or device, 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 that can carry the computer program code. It should be noted that the computer-readable medium includes, but is not limited to, the above components.

[0130] Among them, through this computer-readable storage medium, the information management method for drug clinical trials in the above embodiments is stored in the computer-readable storage medium and is loaded and executed on the processor to facilitate the storage and application of the above method.

[0131] The embodiments of the present application also disclose an electronic device. A computer program is stored in the computer-readable storage medium. When the computer program is loaded and executed by the processor, it adopts the above information management method for drug clinical trials.

[0132] Among them, the electronic device can be a desktop computer, a laptop computer or a cloud server and other electronic devices. And the electronic device includes, but is not limited to, a processor and a memory. For example, the electronic device may also include input / output devices, network access devices, and a bus, etc.

[0133] Among them, the processor may adopt a central processing unit (CPU). Of course, according to the actual usage situation, other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. may also be adopted. The general-purpose processor may adopt a microprocessor or any conventional processor, etc. This application does not make any restrictions on this.

[0134] Among them, the memory may be an internal storage unit of the electronic device. For example, the hard disk or memory of the electronic device. It may also be an external storage device of the electronic device. For example, a plug-in hard disk, a smart media card (SMC), a secure digital card (SD), or a flash card (FC) equipped on the electronic device, etc. And the memory may also be a combination of the internal storage unit and the 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 may also be used to temporarily store the data that has been output or will be output. This application does not make any restrictions on this.

[0135] Among them, through this electronic device, the information management method of a drug clinical trial in the above embodiment is stored in the memory of the electronic device, and is loaded and executed on the processor of the electronic device, which is convenient for use.

[0136] The above are only exemplary embodiments of the present disclosure, and the scope of the present disclosure cannot be limited thereby. That is, any equivalent changes and modifications made according to the teachings of the present disclosure still fall within the scope covered by the present disclosure. This application aims to cover any variations, uses or adaptive changes of the present disclosure. These variations, uses or adaptive changes follow the general principles of the present disclosure and include the common general knowledge or conventional technical means in the technical field not recorded in the present disclosure. The description and the embodiments are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. An information management method for drug clinical trials, characterized in that, The method includes: Obtaining target clinical trial information of at least one dimension of a target subject for a target drug; If the target clinical trial information is not within the normal value range of the corresponding dimension, determining the corresponding target clinical trial information as abnormal clinical trial information, and determining the dimension corresponding to the abnormal clinical trial information as the trial abnormal dimension; Based on the trial abnormal dimension, the target abnormal dimension where the clinical trial information is prone to be abnormal when the target subject has a physical abnormality during the drug clinical trial, and the corresponding target fluctuation dimension, determining the cause of the abnormal clinical trial information, including: determining the target user portrait of the target subject, and obtaining the historical abnormal dimensions where the clinical trial information was abnormal when the historical subjects of the target user portrait had physical abnormalities during the clinical trial of the target drug; Counting the first occurrence times of each of the historical abnormal dimensions, and selecting the historical abnormal dimension with the first number from each of the historical abnormal dimensions in descending order of the first occurrence times as the target abnormal dimension; Obtaining the other dimensions where the clinical trial information fluctuates abnormally when a single target abnormal dimension of the historical subject is abnormal, counting the second occurrence times of each of the other dimensions, and selecting the other dimension with the second number from each of the other dimensions in descending order of the second occurrence times as the target fluctuation dimension corresponding to the corresponding target abnormal dimension; Calculating the first weight of each of the target abnormal dimensions and the second weight of each of the corresponding target fluctuation dimensions, where the first weight is the ratio of the first occurrence times of each target abnormal dimension to the sum of the first occurrence times of all target abnormal dimensions, and the second weight is the ratio of the second occurrence times of a single target fluctuation dimension corresponding to the target abnormal dimension to the sum of the second occurrence times of all corresponding target fluctuation dimensions; Determining the cause of the abnormal clinical trial information according to the trial abnormal dimension, the first weight, and the corresponding second weights; the target fluctuation dimension is the dimension where the clinical trial information is prone to abnormal fluctuations when the clinical trial information of the corresponding target abnormal dimension is abnormal; When the cause of the abnormality is an error in entering the abnormal clinical trial information, determining the appropriate entry form corresponding to the abnormal clinical trial information, and re-obtaining the clinical trial information of the trial abnormal dimension based on the appropriate entry form; When the cause of the abnormality is that the target subject has a physical abnormality during the drug clinical trial, sending an abnormal warning to the terminal of the clinical trial staff; If there is no abnormal clinical trial information, determining the reference fluctuation dimensions where at least one target clinical trial information fluctuates abnormally, and determining the target abnormal dimensions where at least one reference fluctuation dimension exists in the corresponding target fluctuation dimensions as the dimensions to be concerned; Calculating the sum of the fifth products of the first weight of each of the dimensions to be concerned and the second weight of each of the corresponding reference fluctuation dimensions to obtain the corresponding sum of products; Select the maximum sum of products from the sums of the respective products. If the maximum sum of products is greater than a preset first threshold, when there is no error in entering the target clinical trial information for the reference fluctuation dimension corresponding to the maximum sum of products, send an error entry reminder to the terminal for the dimension to be concerned corresponding to the maximum sum of products.

2. The information management method for drug clinical trials according to claim 1, wherein, Determining the cause of the abnormality of the abnormal clinical trial information according to the trial abnormal dimension, the first weight, and the respective second weights corresponding thereto specifically includes: Determine the remaining dimensions of the target subject except for the trial abnormal dimension, and determine at least one actual abnormal fluctuation dimension from the respective remaining dimensions according to the target clinical trial information of each remaining dimension; When the trial abnormal dimension is the target abnormal dimension, determine at least one actual abnormal fluctuation dimension existing in the respective target fluctuation dimensions corresponding to the trial abnormal dimension as the key abnormal fluctuation dimension, and calculate the product of the first weight of the trial abnormal dimension and the respective second weights of the key abnormal fluctuation dimensions to obtain the corresponding first product; Sum the respective first products to obtain the sum of the first products, and compare the sum of the first products with a preset first threshold; If the sum of the first products is greater than the first threshold, determine that the cause of the abnormality of the abnormal clinical trial information is that the body of the target subject shows an abnormality in the drug clinical trial; If the sum of the first products is not greater than the first threshold, determine that the cause of the abnormality of the abnormal clinical trial information is an error in entering the abnormal clinical trial information.

3. The information management method for drug clinical trials according to claim 1, characterized in that, The method further includes: Determine the remaining dimensions of the target subject except for the trial abnormal dimension, and determine at least one actual abnormal fluctuation dimension from the respective remaining dimensions according to the target clinical trial information of each remaining dimension; Obtain the historical entry forms with entry errors in the historical clinical trial information of the clinical trial of the target drug, count the first occurrence frequency of each historical entry form, and select the historical entry form with the third number from the respective historical entry forms in the order from largest to smallest first occurrence frequency as the error-prone entry form; Obtain the historical misentry dimensions when entering the historical clinical trial information in each error-prone entry form, count the second occurrence frequency of each historical misentry dimension, and select the historical misentry dimension with the fourth number from the respective historical misentry dimensions in the order from largest to smallest second occurrence frequency as the error-prone entry dimension corresponding to the corresponding error-prone entry form; Calculate the third weight of each error-prone entry form and the respective fourth weights of the error-prone entry dimensions. The third weight is the ratio of the first occurrence frequency of each error-prone entry form to the sum of the first occurrence frequencies of all error-prone entry forms, and the fourth weight is the ratio of the second occurrence frequency of a single error-prone entry dimension corresponding to the error-prone entry form to the sum of the second occurrence frequencies of all error-prone entry dimensions corresponding thereto; Verify the cause of the abnormal clinical trial information according to the actual input form of the target clinical trial information of each actual abnormal fluctuation dimension, the third weight, and the corresponding fourth weights.

4. The information management method for drug clinical trials according to claim 3, characterized in that, The verification of the cause of the abnormal clinical trial information according to the actual input form of the target clinical trial information of each actual abnormal fluctuation dimension, the third weight, and the corresponding fourth weights specifically includes: Determine the error-prone input form with at least one actual abnormal fluctuation dimension in each corresponding error-prone dimension as the key input form. When the key input form is the corresponding actual input form, calculate the sum of the second products of the third weights of each key input form and the fourth weights of the corresponding actual abnormal fluctuation dimensions to obtain the sum of the second products; If the sum of the second products is not greater than a preset second threshold, it is determined that the verification of the cause of the abnormal clinical trial information is correct; If the sum of the second products is greater than the preset second threshold, determine the actual abnormal fluctuation dimension corresponding to the second product that exceeds the preset product threshold as the misrecorded fluctuation dimension. If there is the misrecorded fluctuation dimension among the key abnormal fluctuation dimensions, then remove the misrecorded fluctuation dimension from each key abnormal fluctuation dimension to obtain the calibrated fluctuation dimension; Calculate the sum of the third products of the first weight of the test abnormal dimension and the second weights of the corresponding calibrated fluctuation dimensions to obtain the sum of the third products; If the sum of the third products is not greater than the first threshold, when the cause of the abnormal clinical trial information is that the target subject has an abnormality in the body during the drug clinical trial, calibrate the cause of the abnormal clinical trial information to an error during input.

5. The information management method for drug clinical trials according to claim 3, wherein The determination of the appropriate input form corresponding to the abnormal clinical trial information specifically includes: Determine the error-prone input form with the test abnormal dimension in each corresponding error-prone dimension as the reference input form, and calculate the fourth product of the third weight of each reference input form and the fourth weight of the corresponding test abnormal dimension; Select the smallest fourth product from each of the fourth products, and determine the reference input form corresponding to the smallest fourth product as the appropriate input form corresponding to the abnormal clinical trial information.

6. An information management device for a drug clinical trial, which is used to implement the method described in any one of claims 1 to 5, and is characterized in that, Including: An information acquisition module (11) for acquiring target clinical trial information of at least one dimension of a target subject of a target drug; An abnormality determination module (12) for determining the corresponding target clinical trial information as abnormal clinical trial information if the target clinical trial information is not within the normal value range of the corresponding dimension, and determining the dimension corresponding to the abnormal clinical trial information as the test abnormal dimension; A cause determination module (13) for determining the cause of the abnormal clinical trial information based on the test abnormal dimension, the target abnormal dimension in which the clinical trial information is likely to be abnormal when the target subject has an abnormality in the body during the drug clinical trial, and the corresponding target fluctuation dimension, where the target fluctuation dimension is the dimension in which the clinical trial information is likely to have an abnormal fluctuation when the clinical trial information of the corresponding target abnormal dimension is abnormal. An input adjustment module (14) is configured to determine a suitable input form corresponding to the abnormal clinical trial information and re-acquire the clinical trial information of the trial abnormal dimension based on the suitable input form when the abnormal cause is an error in the input of the abnormal clinical trial information; An abnormal warning module (15) is configured to send an abnormal warning to the terminal of the clinical trial staff when the abnormal cause is that the target subject has a physical abnormality during the drug clinical trial.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is loaded and executed by a processor, the method described in any one of claims 1-5 is adopted.

8. 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 described in any one of claims 1-5 is adopted.

Images