Test data processing system and method and storage medium

Abstract

The invention provides a test data processing system and method and a storage medium, and belongs to the technical field of test data processing. The test data processing system comprises the following steps: acquiring a plurality of clinical test groups in a database; calculating basic importance data according to the clinical test data; repeated data and missing data are obtained according to the clinical test data, repeated influence data are analyzed according to the test repeated data, and missing influence data are analyzed according to the test missing data; determining comprehensive importance data of each clinical test group according to the basic importance data, the repeated influence data and the missing influence data, and determining processing sequence data of each clinical test group based on the comprehensive importance data; by adopting the scheme, the accuracy and the processing efficiency of clinical test data can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of test data processing, and in particular to a test data processing system, method and storage medium. Background Art

[0002] Clinical trials refer to medical research conducted on human bodies to evaluate the safety and effectiveness of drugs, medical devices, treatments or preventive measures. After completing clinical trials and obtaining clinical trial data, the clinical trial data needs to be processed to a certain extent, such as duplicate data and missing data in the trial data. Among them, clinical trial data includes two types, one is the patient's personal data, and the other is the patient's trial data, and different types of data are equipped with corresponding identifiers, that is, feature labels of the data, such as the patient's age, gender, etc. In some long-term clinical trials, data are collected in batches, and these data will be stored in the database according to different clinical trial groups. Each clinical trial group includes clinical trial data of a number of patients. When processing the trial data, the trial data of this group of patients needs to be uniformly processed. Since the above-mentioned trial data needs to be processed, it is very necessary to determine the processing order of the trial data under the condition of limited data processing computing power. Summary of the Invention

[0003] The present application provides a test data processing system, method and storage medium, which can analyze the processing priority of test data and thus improve data processing efficiency.

[0004] In a first aspect, the present application provides a test data processing system. The system includes an acquisition module, a calculation module, an analysis module, and a determination module;

[0005] The acquisition module is used to acquire multiple clinical trial groups in the database; each clinical trial group includes clinical trial data of a preset number of patients; the clinical trial data includes the patient's personal basic data and medical trial data;

[0006] The calculation module is used to calculate basic importance data based on the clinical trial data; the basic importance data is associated with the clinical trial data;

[0007] The analysis module is used to obtain duplicate data and missing data based on the clinical trial data, and analyze duplicate impact data based on the trial duplicate data, and analyze missing impact data based on the trial missing data; the duplicate impact data is associated with the personal basic data and the medical trial data; and the missing impact data is associated with the clinical trial data;

[0008] The determination module is used to determine the comprehensive importance data of each clinical trial group according to the basic importance data, the duplicate impact data and the missing impact data, and to determine the processing order data of each clinical trial group based on the comprehensive importance data.

[0009] Furthermore, the analysis module is further configured to obtain duplicate data and missing data based on the clinical trial data, and analyze duplicate impact data based on the trial duplicate data, and analyze missing impact data based on the trial missing data; the duplicate impact data is associated with the personal basic data and the medical trial data; the missing impact data is associated with the clinical trial data and includes:

[0010] The repetition data includes first repetition ratio data and second repetition ratio data;

[0011] determining first repetition ratio data based on the clinical trial data and preset standard reference patient data;

[0012] Analyzing the second repetition ratio data between the clinical trial data of each patient in the same clinical trial group based on the personal basic data and the medical trial data;

[0013] Repetition impact data is analyzed based on the first repetition ratio data and the second repetition ratio data.

[0014] Furthermore, the analysis module is further configured to obtain duplicate data and missing data based on the clinical trial data, and analyze duplicate impact data based on the trial duplicate data, and analyze missing impact data based on the trial missing data; the duplicate impact data is associated with the personal basic data and the medical trial data; the missing impact data is associated with the clinical trial data and includes:

[0015] The calculation method of the duplication impact data is:

[0016] C=D1×K1+D2×K2

[0017] In the formula, C is the repetition influence data; D1 is the first repetition ratio data, and D2 is the second repetition ratio data; K1 and K2 are the preset first weight and the preset second weight, respectively; and K1+K2=1.

[0018] Furthermore, the analysis module is further configured to obtain duplicate data and missing data based on the clinical trial data, and analyze duplicate impact data based on the trial duplicate data, and analyze missing impact data based on the trial missing data; the duplicate impact data is associated with the personal basic data and the medical trial data; the missing impact data is associated with the clinical trial data and includes:

[0019] The missing data includes missing feature label data and missing label quantity data;

[0020] Determine missing feature label item data and missing label quantity data based on preset standard feature label items and the clinical trial data;

[0021] Calculate the missing tag item impact data based on the missing feature tag data and the preset tag importance data;

[0022] Calculate missing quantity impact data based on the missing label quantity data;

[0023] Calculate missing label mutation impact data based on the preset label table and the missing feature label item data;

[0024] The deletion impact data is analyzed according to the deletion tag item impact data, the deletion quantity impact data, and the deletion tag mutation impact data.

[0025] Furthermore, the analysis module is further configured to obtain duplicate data and missing data based on the clinical trial data, and analyze duplicate impact data based on the trial duplicate data, and analyze missing impact data based on the trial missing data; the duplicate impact data is associated with the personal basic data and the medical trial data; the missing impact data is associated with the clinical trial data and includes:

[0026] The calculation method of the missing impact data includes:

[0027]

[0028] In the formula, S is the missing impact data; M is the number of missing label data, P i is the preset label importance of the i-th missing feature label data; x is the label quantity data of the missing feature label item in the preset label table; B1 and B2 are the preset quantity weight and preset label weight respectively, where B1+B2=1.

[0029] Furthermore, the determination module is further configured to determine the comprehensive importance data of each clinical trial group based on the basic importance data, the duplication impact data, and the missing impact data, and determine the processing order data of each clinical trial group based on the comprehensive importance data, including:

[0030] The calculation method of the comprehensive importance data includes:

[0031] Z=F+CS

[0032] In the formula, Z is the comprehensive importance data, F is the basic importance data, C is the repeated impact data, and S is the missing impact data;

[0033] Based on the comprehensive importance data, each clinical trial group is ranked in order from high to low to determine the processing order data of each clinical trial group.

[0034] In a second aspect, the present application provides a test data processing method, which is applied to the test data processing system. The method includes:

[0035] Acquire multiple clinical trial groups from a database; each clinical trial group includes clinical trial data of a preset number of patients; the clinical trial data includes the patient's basic personal data and medical trial data;

[0036] Calculating basic importance data based on the clinical trial data; the basic importance data is associated with the clinical trial data;

[0037] Obtaining duplicate data and missing data based on the clinical trial data, and analyzing duplicate impact data based on the trial duplicate data, and analyzing missing impact data based on the trial missing data; the duplicate impact data is associated with the personal basic data and medical trial data; and the missing impact data is associated with the clinical trial data;

[0038] The comprehensive importance data of each clinical trial group is determined according to the basic importance data, the duplication impact data and the missing impact data, and the processing order data of each clinical trial group is determined based on the comprehensive importance data.

[0039] In a third aspect, the present application provides a computer storage medium storing a computer program such as the above-mentioned clinical trial data processing method loaded and executed by a processor.

[0040] It should be understood that the contents described in the Summary of the Invention are not intended to limit the key or important features of the embodiments of the present application, nor are they intended to limit the scope of the present application. Other features of the present application will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The above and other features, advantages and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0042] Figure 1 A block diagram of a test data processing system in an embodiment of the present application is shown;

[0043] Figure 2 A flow chart of a test data processing method in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0044] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0045] In this document, the term "and / or" simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates that the related objects are in an "or" relationship.

[0046] The present application provides a test data processing system, method and storage medium, which can improve the processing efficiency of test data.

[0047] In the first aspect, the present application provides a test data processing system. Figure 1 As shown, the system includes an acquisition module 110, a calculation module 120, an analysis module 130 and a determination module 140; the acquisition module 110 is used to acquire multiple clinical trial groups in the database; each of the clinical trial groups includes clinical trial data of a preset number of patients; the clinical trial data includes the patient's personal basic data and medical trial data; the calculation module 120 is used to calculate basic importance data based on the clinical trial data; the basic importance data is associated with the clinical trial data; the analysis module 130 is used to obtain duplicate data and missing data based on the clinical trial data, and analyze duplicate impact data based on the trial duplicate data, and analyze missing impact data based on the trial missing data; the duplicate impact data is associated with the personal basic data and medical trial data; the missing impact data is associated with the clinical trial data; the determination module 140 is used to determine the comprehensive importance data of each clinical trial group based on the basic importance data, duplicate impact data and missing impact data, and determine the processing order data of each clinical trial group based on the comprehensive importance data.

[0048] It can be understood that the patient's personal basic data here refers to the patient's age, gender and other personal basic data, which are data that can be obtained in advance; the patient's medical trial data here refers to the medical trial data obtained by the patient during the clinical trial. After the completion of the clinical trial, the patient's personal basic data and medical trial data are integrated and stored in the database for subsequent call and use; it should be noted that the multiple clinical trial groups obtained here are clinical trial groups that require data processing and data analysis. These clinical trial groups can be understood as all need to conduct the next stage of the corresponding clinical trial. Therefore, data processing and analysis are required for these clinical trial groups. In this case, due to the limitation of data processing computing power, these clinical trial groups need to be analyzed to determine the processing order of these clinical trial groups, thereby improving the processing efficiency of clinical trial data.

[0049] In an embodiment of the present application, the calculation module 120 is further configured to calculate basic importance data based on the trial time, the number of trial patients and the corresponding clinical trial importance of the clinical trial group; the trial time here represents the completion time of the clinical trial corresponding to the clinical trial group; based on the trial time, the time span from the current moment is calculated and named as completion duration data; the clinical trial importance is determined by a preset project level table, which contains the project level corresponding to each clinical trial and the corresponding clinical trial importance data; specifically, basic importance data = completion duration data * duration weight + number of trial patients * quantity weight + clinical trial Importance * Importance weight; Among them, duration weight + quantity weight + importance weight = 1; It can be understood that, the larger the completion time data, the longer the data time for the corresponding clinical trial group to complete the trial. In order to ensure that the processing and analysis of this group of data will not affect the next stage of clinical trials, data with longer completion time need to be processed in advance, and the higher the processing order; and the more patients there are, the larger the amount of data in the clinical trial group. The larger the amount of data, the more time is consumed for data processing and analysis. In order to avoid affecting the next stage of clinical trials, the more patients there are, the higher the processing order; similarly, the higher the importance of the clinical trial, the higher the processing order.

[0050] In an embodiment of the present application, the analysis module 130 is further configured to obtain duplicate data and missing data based on the clinical trial data, and analyze duplicate impact data based on the trial duplicate data. The analysis of missing impact data based on the trial missing data specifically includes: the duplicate data includes first duplicate ratio data and second duplicate ratio data; the first duplicate ratio data is determined based on the clinical trial data and preset standard reference patient data; the second duplicate ratio data between the clinical trial data of each patient in the same clinical trial group is analyzed based on the personal basic data and the medical trial data; and the duplicate impact data is analyzed based on the first duplicate ratio data and the second duplicate ratio data. It can be understood that when comparing the patient's clinical trial data with the preset label reference patient data, the comparison is between the personal basic data and medical trial data of the two. For each feature label, the proportion of the data occupied by repeated data in all feature labels is the first sub-repetition ratio data; for example, there are ten feature labels, among which the data corresponding to patient A and the five feature labels of the labeled patient are repeated data, then the first sub-repetition ratio data of patient A is 50%; then the average value is calculated based on the first sub-repetition ratio data of all patients in the clinical trial group to obtain the first repetition ratio data; it should be noted that in conducting clinical trials, there is a certain correlation between the selected sample patients and the reference patients, such as all being male, of similar age and weight, etc.; and the higher the first repetition ratio data, the more the clinical trial data of the clinical trial group fits the reference patient, and thus the data trust of the clinical trial for this type of human is higher, so the higher the first repetition ratio data, the higher the processing order of the clinical trial group.

[0051] The second repetition ratio data here is a comparison of the medical trial data between each patient in the clinical trial group. As mentioned above, the data corresponding to the five feature labels of the medical trial data between patient A and patient B are repeated data. There are a total of ten feature labels to characterize the medical trial data, so the second sub-repetition ratio data between patient A and patient B is 50%; and all patients in the clinical trial group are analyzed in pairs for each other's second sub-repetition ratio data, and then the average value of all the second sub-repetition ratio data is calculated to obtain the second repetition ratio data; it can be understood that when processing the data of the clinical trial group, the higher the ratio of repeated data between the data, the less computing power consumed by the data processing, that is, the higher the data processing efficiency. In order to improve the efficiency of clinical trial data processing, the higher the second repetition ratio data, the higher the corresponding clinical processing order.

[0052] The calculation method of the repeated impact data is as follows:

[0053] C=D1×K1+D2×K2

[0054] In the formula, C is the repetition influence data; D1 is the first repetition ratio data, and D2 is the second repetition ratio data; K1 and K2 are the preset first weight and the preset second weight, respectively; and K1+K2=1.

[0055] Duplicate data and missing data are obtained based on the clinical trial data, and duplicate impact data is analyzed based on the trial duplicate data. The analysis of missing impact data based on the trial missing data specifically includes: the missing data includes missing feature label data and missing label quantity data; determining missing feature label item data and missing label quantity data based on preset standard feature label items and the clinical trial data; calculating missing label item impact data based on the missing feature label data and preset label importance data; calculating missing quantity impact data based on the missing label quantity data; calculating missing label mutation impact data based on the preset label table and the missing feature label item data; analyzing missing impact data based on the missing label item impact data, the missing quantity impact data, and the missing label mutation impact data. It can be understood that when analyzing missing impact data, all clinical trial data in the clinical trial group are analyzed, such as the missing label quantity data is the sum of the number of missing labels of the clinical trial data of each patient; for missing data in the clinical trial data, the more missing feature labels there are, the more data missing in the clinical trial data, and the lower the processing order of the clinical trial data; similarly, the higher the preset label importance corresponding to the missing feature label, the higher the overall importance of the data missing in the clinical trial data, and the lower the processing order of the clinical trial data.

[0056] It can be understood that the missing label mutation impact data mentioned above refers to the data obtained by analyzing the missing items in the clinical trial data of all patients in the clinical trial group that are located in the preset label table; it can be understood that the feature labels in the preset label table are feature labels with higher importance, and if the corresponding feature labels in this table are missing one, it will cause a greater impact, but if the corresponding feature labels in this table are missing multiple, then compared to one, the impact will not be greater, and the fluctuation will be smaller, so the activation function is used here to represent the analysis of this part of the content.

[0057] The calculation method of the missing impact data includes:

[0058]

[0059] In the formula, S is the missing impact data; M is the number of missing label data, P iis the preset label importance of the i-th missing feature label data; x is the label quantity data of the missing feature label item in the preset label table; B1 and B2 are the preset quantity weight and preset label weight respectively, where B1+B2=1.

[0060] In an embodiment of the present application, the determining module 140 is further configured to determine the comprehensive importance data of each clinical trial group based on the basic importance data, the duplication impact data, and the missing impact data, and determine the processing order data of each clinical trial group based on the comprehensive importance data, specifically including:

[0061] The calculation method of the comprehensive importance data includes:

[0062] Z=F+CS

[0063] In the formula, Z is the comprehensive importance data, F is the basic importance data, C is the repeated impact data, and S is the missing impact data; based on the comprehensive importance data, each clinical trial group is ranked in sequence from high to low to determine the processing order data of each clinical trial group.

[0064] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to the embodiments of this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required for this application.

[0065] In a second aspect, the present application provides a test data processing method, which is applied to the test data processing system. Figure 2 The specific steps included in the method are as follows.

[0066] Step S210: Acquire multiple clinical trial groups in the database; each clinical trial group includes clinical trial data of a preset number of patients; the clinical trial data includes the patient's personal basic data and medical trial data.

[0067] Step S220: Calculating basic importance data based on the clinical trial data; the basic importance data is associated with the clinical trial data.

[0068] Step S230: obtaining duplicate data and missing data based on the clinical trial data, and analyzing duplicate impact data based on the trial duplicate data, and analyzing missing impact data based on the trial missing data; the duplicate impact data is associated with the personal basic data and medical trial data; the missing impact data is associated with the clinical trial data.

[0069] Step S240: Determine comprehensive importance data of each clinical trial group according to the basic importance data, duplicate impact data and missing impact data, and determine processing order data of each clinical trial group based on the comprehensive importance data.

[0070] In a third aspect, the present application provides a computer storage medium storing a computer program such as the above-mentioned test data processing method loaded and executed by a processor.

[0071] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described device can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0072] The above description is merely a preferred embodiment of the present application and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this application is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but also encompasses other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the aforementioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A test data processing system, characterized in that: It includes an acquisition module (110), a calculation module (120), an analysis module (130) and a determination module (140); The acquisition module (110) is used to acquire multiple clinical trial groups in the database; each clinical trial group includes clinical trial data of a preset number of patients; the clinical trial data includes the patient's personal basic data and medical trial data; The calculation module (120) is used to calculate basic importance data based on the clinical trial data; the basic importance data is associated with the clinical trial data; The analysis module (130) is used to obtain duplicate data and missing data based on the clinical trial data, and analyze duplicate impact data based on the trial duplicate data, and analyze missing impact data based on the trial missing data; the duplicate impact data is associated with the personal basic data and the medical trial data; the missing impact data is associated with the clinical trial data; The determination module (140) is used to determine the comprehensive importance data of each clinical trial group according to the basic importance data, the duplicate impact data and the missing impact data, and to determine the processing order data of each clinical trial group based on the comprehensive importance data.

2. The system according to claim 1, wherein: The analysis module (130) is further configured to obtain duplicate data and missing data based on the clinical trial data, and analyze duplicate impact data based on the trial duplicate data, and analyze missing impact data based on the trial missing data; The repeated impact data is associated with the personal basic data and medical trial data; The missing impact data associated with the clinical trial data include: The repetition data includes first repetition ratio data and second repetition ratio data; determining first repetition ratio data based on the clinical trial data and preset standard reference patient data; Analyzing the second repetition ratio data between the clinical trial data of each patient in the same clinical trial group based on the personal basic data and the medical trial data; Repetition impact data is analyzed based on the first repetition ratio data and the second repetition ratio data.

3. The system according to claim 2, characterized in that The analysis module (130) is further configured to obtain duplicate data and missing data based on the clinical trial data, and analyze duplicate impact data based on the trial duplicate data, and analyze missing impact data based on the trial missing data; The repeated impact data is associated with the personal basic data and medical trial data; The missing impact data associated with the clinical trial data include: The calculation method of the duplication impact data is: C=D1×K1+D2×K2 In the formula, C is the repetition influence data; D1 is the first repetition ratio data, and D2 is the second repetition ratio data; K1 and K2 are the preset first weight and the preset second weight, respectively; and K1+K2=1.

4. The system according to claim 3, characterized in that The analysis module (130) is further configured to obtain duplicate data and missing data based on the clinical trial data, and analyze duplicate impact data based on the trial duplicate data, and analyze missing impact data based on the trial missing data; The repeated impact data is associated with the personal basic data and medical trial data; The missing impact data associated with the clinical trial data include: The missing data includes missing feature label data and missing label quantity data; Determine missing feature label item data and missing label quantity data based on preset standard feature label items and the clinical trial data; Calculate the missing tag item impact data based on the missing feature tag data and the preset tag importance data; Calculate missing quantity impact data based on the missing label quantity data; Calculate missing label mutation impact data based on the preset label table and the missing feature label item data; The deletion impact data is analyzed according to the deletion tag item impact data, the deletion quantity impact data, and the deletion tag mutation impact data.

5. The system according to claim 4, characterized in that The analysis module (130) is further configured to obtain duplicate data and missing data based on the clinical trial data, and analyze duplicate impact data based on the trial duplicate data, and analyze missing impact data based on the trial missing data; The repeated impact data is associated with the personal basic data and medical trial data; The missing impact data associated with the clinical trial data include: The calculation method of the missing impact data includes: In the formula, S is the missing impact data; M is the number of missing label data, P i is the preset label importance of the i-th missing feature label data; x is the label quantity data of the missing feature label item in the preset label table; B1 and B2 are the preset quantity weight and preset label weight respectively, where B1+B2=1.

6. The system according to claim 5, characterized in that The determining module (140) is further configured to determine the comprehensive importance data of each clinical trial group based on the basic importance data, the duplicate impact data and the missing impact data, and determine the processing order data of each clinical trial group based on the comprehensive importance data, including: The calculation method of the comprehensive importance data includes: Z=F+CS In the formula, Z is the comprehensive importance data, F is the basic importance data, C is the repeated impact data, and S is the missing impact data; Based on the comprehensive importance data, each clinical trial group is ranked in order from high to low to determine the processing order data of each clinical trial group.

7. A test data processing method, applied to the test data processing system, characterized in that: include: Acquire multiple clinical trial groups from a database; each clinical trial group includes clinical trial data of a preset number of patients; The clinical trial data includes the patient's personal basic data and medical trial data; Calculating basic importance data based on the clinical trial data; the basic importance data is associated with the clinical trial data; Obtaining duplicate data and missing data based on the clinical trial data, and analyzing duplicate impact data based on the trial duplicate data, and analyzing missing impact data based on the trial missing data; the duplicate impact data is associated with the personal basic data and the medical trial data; The missing impact data is associated with the clinical trial data; The comprehensive importance data of each clinical trial group is determined according to the basic importance data, the duplication impact data and the missing impact data, and the processing order data of each clinical trial group is determined based on the comprehensive importance data.

8. A computer-readable storage medium, characterized in that A computer program is stored which is loaded and executed by a processor according to the method of claim 7.

Images