Treatment sensitive population screening method, system and equipment based on test data and storage medium

Abstract

The invention discloses a test data-based sensitive population treatment screening method, system and device and a storage medium, and the method comprises the steps: obtaining clinical test data, analyzing alternative variables in the clinical test data, and obtaining a variable analysis result; performing full-variable combination traversal according to a variable analysis result, and screening the clinical test data based on a traversal result to obtain a plurality of subgroups; based on the effect quantity, the statistical test value, the condition test efficiency, the merging variance and the number of alternative variables of each subgroup, determining a comprehensive score of each subgroup through a radar map; and according to the comprehensive score of each sub-group, screening a treatment sensitive sub-group from each sub-group. According to the method, all possible variable combinations can be traversed, and the treatment-sensitive subgroups are screened from the subgroups based on the effect quantity, the statistical test value, the condition test efficiency, the merging variance and the number of the alternative variables of the subgroups, so that the screening efficiency and accuracy of the treatment-sensitive population are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of clinical trial data analysis, and in particular to a method, system, device and storage medium for screening treatment-sensitive populations based on trial data. Background Art

[0002] In clinical trials and individualized treatment studies, the efficacy of the same treatment regimen may vary significantly among different patients. Therefore, in the process of analyzing trial data, it is crucial to identify patient subgroups that are more sensitive to specific treatments (i.e., treatment-sensitive populations). However, traditional subgroup analysis methods are usually based on univariate or preset stratification criteria, and fail to fully utilize multivariate information in trial data, which may lead to the omission of effective subgroups or unstable analysis conclusions. In addition, the sample size of some subgroups is small, resulting in insufficient statistical power and affecting the reliability of the results.

[0003] Therefore, there is an urgent need for a method for screening treatment-sensitive populations based on trial data, which can improve the efficiency and accuracy of screening treatment-sensitive populations and thus optimize clinical trial data analysis. Summary of the invention

[0004] The main purpose of the present invention is to provide a method, system, device and storage medium for screening treatment sensitive populations based on test data, aiming to solve the technical problems in the prior art of low efficiency and accuracy in screening treatment sensitive populations in clinical trial data analysis.

[0005] To achieve the above object, the present invention provides a method for screening a treatment-sensitive population based on test data, the method comprising the following steps: Acquire clinical trial data, and parse candidate variables in the clinical trial data to obtain variable parsing results; Performing a full variable combination traversal according to the variable analysis results, and screening the clinical trial data based on the traversal results to obtain multiple subgroups; Based on the effect size, statistical test value, conditional test power, combined variance and number of alternative variables of each subgroup, a comprehensive score of each subgroup is determined by a radar chart; According to the comprehensive scores of each of the subgroups, a treatment-sensitive subgroup is screened out from each of the subgroups.

[0006] Optionally, the step of acquiring clinical trial data, parsing candidate variables in the clinical trial data, and obtaining variable parsing results includes: Acquire clinical trial data, identify the variable type of each candidate variable in the clinical trial data, and obtain an identification result; If the variable type of the candidate variable in the identification result is a continuous variable, the corresponding candidate variable is divided into two-category variables according to the median to obtain a first analysis result; If the variable type of the candidate variable in the recognition result is a categorical variable, determining the original value of the corresponding candidate variable to obtain a second parsing result; The first analysis result and the second analysis result are used as variable analysis results.

[0007] Optionally, the step of performing a full variable combination traversal according to the variable analysis result, and screening the clinical trial data based on the traversal result to obtain a plurality of subgroups includes: Performing a full variable combination traversal on each candidate variable based on the value range of each candidate variable in the variable analysis result to obtain a traversal result; Matching each variable-value combination in the traversal result in the clinical trial data, and determining the proportion of the number of people in each variable-value combination in the clinical trial data; The clinical trial data is screened based on the population proportion information to obtain multiple subgroups.

[0008] Optionally, before the step of determining the comprehensive score of each subgroup through a radar chart based on the effect size, statistical test value, conditional test power, combined variance and number of candidate variables of each subgroup, the step further includes: Determine the effect size of each subgroup according to the mean difference between two groups, risk ratio or survival analysis index between different treatment groups; Determine the statistical test value of each subgroup according to the t value, p value or confidence interval of each subgroup; Determine the conditional test efficacy of each of the subgroups based on a conditional test efficacy calculation formula; The combined variance of the experimental group and the control group in each of the subgroups was determined based on the combined variance calculation formula.

[0009] Optionally, the conditional test efficiency calculation formula is: ; In the formula, represents the standardized test statistic for subgroup k, is the critical value of the significance test, represents the conditional test power for subgroup k, Represents the test data currently collected; The combined variance calculation formula is: ; In the formula, and Respectively represent the sample size of the experimental group and the control group in each subgroup, and Represent the sample variance of the experimental group and the control group in each subgroup, respectively.

[0010] Optionally, the step of determining the comprehensive score of each subgroup through a radar chart based on the effect size, statistical test value, conditional test power, combined variance and number of candidate variables of each subgroup includes: The effect size, statistical test value, conditional test power, reciprocal of the combined variance and reciprocal of the number of alternative variables of each subgroup are standardized to obtain standardized indicators; The standardized index is used as the radar chart axis to generate a radar chart, and the area enclosed by the radar chart is used as the comprehensive score of each subgroup.

[0011] Optionally, the step of screening out treatment-sensitive subgroups from each of the subgroups according to the comprehensive scores of each of the subgroups comprises: Arrange the subgroups in descending order according to their comprehensive scores to obtain a ranking result; Comparing the comprehensive score of each of the subgroups in the sorting result with a preset score threshold to obtain a comparison result; Based on the comparison results, a treatment-sensitive subgroup is screened out from each of the subgroups.

[0012] In addition, to achieve the above-mentioned purpose, the present invention also proposes a treatment sensitive population screening system based on test data, the system comprising: A variable analysis module, used to obtain clinical trial data, and analyze candidate variables in the clinical trial data to obtain variable analysis results; A combination variable module, used for performing a full variable combination traversal according to the variable analysis results, and screening the clinical trial data based on the traversal results to obtain multiple subgroups; A comprehensive scoring module, used to determine the comprehensive score of each of the subgroups through a radar chart based on the effect size, statistical test value, conditional test power, combined variance and number of alternative variables of each of the subgroups; The subgroup screening module is used to screen out treatment-sensitive subgroups from each of the subgroups based on the comprehensive scores of each of the subgroups.

[0013] In addition, to achieve the above-mentioned objectives, the present invention also proposes a device for screening treatment-sensitive populations based on test data, the device comprising: a memory, a processor, and a program for screening treatment-sensitive populations based on test data stored on the memory and executable on the processor, the program for screening treatment-sensitive populations based on test data being configured to implement the steps of the method for screening treatment-sensitive populations based on test data as described above.

[0014] In addition, to achieve the above-mentioned objectives, the present invention also proposes a storage medium, on which is stored a treatment sensitive population screening program based on test data, and when the treatment sensitive population screening program based on test data is executed by a processor, the steps of the treatment sensitive population screening method based on test data as described above are implemented.

[0015] The present invention discloses obtaining clinical trial data, parsing the candidate variables in the clinical trial data, and obtaining the variable parsing results; performing a full variable combination traversal according to the variable parsing results, and screening the clinical trial data based on the traversal results to obtain multiple subgroups; determining the comprehensive score of each subgroup through a radar chart based on the effect size, statistical test value, conditional test efficiency, combined variance and number of candidate variables of each subgroup; and screening out treatment-sensitive subgroups from each subgroup based on the comprehensive score of each subgroup. Since the present invention performs a full variable combination traversal according to the variable parsing results, and screens the clinical trial data based on the traversal results, and determines the comprehensive score of each subgroup through a radar chart based on the effect size, statistical test value, conditional test efficiency, combined variance and number of candidate variables of each subgroup, and then screens out treatment-sensitive subgroups, compared with the prior art, the present invention improves the efficiency and accuracy of screening treatment-sensitive populations, and then optimizes clinical trial data analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a schematic flow chart of a first embodiment of a method for screening a treatment-sensitive population based on test data of the present invention; Figure 2 This is a flow chart of a second embodiment of the method for screening treatment-sensitive populations based on test data of the present invention; Figure 3 It is a structural block diagram of the first embodiment of the treatment sensitive population screening system based on test data of the present invention; Figure 4 It is a structural schematic diagram of a device for screening treatment-sensitive populations based on test data in a hardware operating environment according to an embodiment of the present invention.

[0017] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0018] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0019] The present invention provides a method for screening a treatment-sensitive population based on test data, referring to Figure 1 , Figure 1This is a schematic flow chart of the first embodiment of the method for screening treatment-sensitive populations based on test data of the present invention.

[0020] In this embodiment, the method for screening treatment-sensitive populations based on test data includes steps S10 to S40: Step S10: Acquire clinical trial data, and parse candidate variables in the clinical trial data to obtain variable parsing results.

[0021] It should be noted that the execution subject of this embodiment can be a computer server device with data processing, network communication and program running functions used in clinical trial data analysis scenarios, such as a server, a tablet computer, a personal computer, etc., or an electronic device capable of realizing the above functions, a treatment sensitive population screening device based on test data, etc. The following takes the treatment sensitive population screening device based on test data as an example to illustrate this embodiment and the following embodiments.

[0022] It should be understood that clinical trial data are structured information collected through systematic medical research (such as the testing of drugs, devices, or treatment regimens) designed to evaluate the safety, effectiveness, and appropriateness of the intervention.

[0023] It should be explained that candidate variables refer to a set of potential variables pre-selected in clinical trial data for use in defining and analyzing patient subgroups that may respond differently to a specific treatment regimen.

[0024] It should be noted that the alternative variables are derived from various patient characteristics recorded in the clinical trial data. The variable types of alternative variables include but are not limited to: continuous variables (such as age, weight, biomarker concentration, disease score, etc.); categorical variables (such as gender, gene mutation status, disease stage, treatment history, etc.).

[0025] In specific implementations, potential patient subgroup division schemes can be generated by combining the values ​​of different candidate variables, and used to evaluate the differences in treatment effects (such as efficacy, safety, etc.) among different subgroups.

[0026] It should be noted that subgroup division needs to be based on clear combinations of variable values ​​(such as "age>50 years old and positive for gene mutation"), while the unlimited values ​​of continuous variables (such as age, blood sugar level) will lead to combinatorial explosion and cannot be exhausted. Therefore, continuous variables can be converted into discrete variables by median, quantile or clinical threshold dichotomy (such as "high / low"), so that the subgroup definition is clear and the number of combinations is controllable. For example, if the trial contains the continuous variable "age", it can be divided into "≤50 years old" and ">50 years old" according to the median of 50 years old, and it can be combined with other categorical variables (such as gender) to generate limited subgroups (such as "male and age>50 years old"). Direct analysis of continuous variables may reduce statistical power due to insufficient sample size or skewed distribution (such as t-test is not robust under small samples). Therefore, the sample size of subgroups can be balanced (such as median split to ensure that the number of people in the two groups is similar) to reduce the impact of extreme values.

[0027] In a specific implementation, in order to improve the feasibility, efficiency and interpretability of subgroup screening, step S10 includes: steps S101 to S104: Step S101: Acquire clinical trial data, identify the variable type of each candidate variable in the clinical trial data, and obtain an identification result.

[0028] Step S102: If the variable type of the candidate variable in the identification result is a continuous variable, the corresponding candidate variable is divided into binary variables according to the median to obtain a first analysis result.

[0029] Step S103: If the variable type of the candidate variable in the recognition result is a categorical variable, the original value of the corresponding candidate variable is determined to obtain a second parsing result.

[0030] Step S104: taking the first analysis result and the second analysis result as variable analysis results.

[0031] It should be noted that the effect size of continuous variables (such as regression coefficients) is not intuitive enough for clinicians and is difficult to directly guide treatment decisions. Therefore, this embodiment divides the candidate variables into binary variables according to the median. The binary variables provide clear clinical boundaries (such as "hypertension: yes / no") to facilitate the formulation of personalized treatment strategies.

[0032] In addition, if continuous variables are retained, the computational complexity of combinatorial traversal increases exponentially (for example, 3 continuous variables need to be divided into intervals, and the number of combinations cannot be exhausted). Therefore, the candidate variables are divided into binary variables according to the median, so that the possible values ​​of each variable are limited to 2 (such as "high / low"), which changes the number of combinations from infinite to finite (for example, 5 variables → = 32 combinations), ensuring that the system can complete the traversal efficiently and avoid missing valid subgroups.

[0033] Step S20: performing a full variable combination traversal according to the variable analysis results, and screening the clinical trial data based on the traversal results to obtain multiple subgroups.

[0034] It should be explained that full variable combination traversal refers to the systematic enumeration and evaluation of all possible combinations of candidate variable values ​​in clinical trial data analysis to identify patient subgroups with significant differences in response to specific treatment regimens. This process is designed to ensure that no potential effective subgroup division schemes are missed.

[0035] In the specific implementation, all possible value levels of all candidate variables are traversed to ensure that all possible subgroup division schemes are covered. The full variable combination traversal provides a comprehensive, efficient and interpretable solution for subgroup screening in clinical trials by exhaustively enumerating all variable combinations and combining multi-dimensional scores (such as radar charts).

[0036] Step S30: Based on the effect size, statistical test value, conditional test power, combined variance and number of candidate variables of each subgroup, a comprehensive score of each subgroup is determined through a radar chart.

[0037] In a specific implementation, before step S30, it also includes: determining the effect size of each subgroup according to the difference between the two group means, the risk ratio or the survival analysis index between each subgroup in different treatment groups; determining the statistical test value of each subgroup according to the t value, p value or confidence interval of each subgroup; determining the conditional test power of each subgroup based on the conditional test power calculation formula; determining the combined variance of the experimental group and the control group in each subgroup based on the combined variance calculation formula.

[0038] It should be noted that for each variable combination, the effect size between different treatment groups (such as the mean difference between the two groups, the risk ratio or the survival analysis indicator) is calculated to evaluate the differences in treatment response.

[0039] It should be noted that the statistical significance of the subgroup can be evaluated by calculating the statistical test value (such as t value, p value or confidence interval) of each subgroup under the hypothetical condition that the sample size of the subgroup population is enlarged to the trial population (that is, all the samples of this trial are from this subgroup).

[0040] The conditional test efficiency calculation formula is: ; In the formula, represents the standardized test statistic for subgroup k, is the critical value of the significance test, represents the conditional test power for subgroup k, Represents the test data currently collected; The combined variance calculation formula is: ; In the formula, and Respectively represent the sample size of the experimental group and the control group in each subgroup, and Represent the sample variance of the experimental group and the control group in each subgroup, respectively.

[0041] It should be explained that the inverse of the pooled variance It can be used to measure the stability of the data within the subgroup.

[0042] It should be understood that the radar chart, also known as the spider web chart or star chart, is a multi-dimensional data visualization tool that intuitively displays the comprehensive performance of each indicator by mapping multiple indicators to different positions on concentric axes. Features include: multi-axis layout: each axis represents an independent indicator (such as effect size, statistical significance, etc.); closed polygon: a closed figure is formed by connecting the numerical points of each axis, and the larger the area, the better the comprehensive performance; comparative analysis: radar charts of multiple subgroups can be displayed at the same time, which is convenient for horizontal comparison.

[0043] In a specific implementation, the effect size, statistical test value, conditional test power, inverse of the combined variance and inverse of the number of alternative variables of each of the subgroups can be standardized to obtain standardized indicators; the standardized indicators are used as radar chart axes to generate a radar chart, and the area enclosed by the radar chart is used as the comprehensive score of each of the subgroups.

[0044] For example, the five axes of a radar chart can be represented as follows: Axis 1: effect size (such as mean difference, risk ratio); Axis 2: statistical test value (such as t value); Axis 3: conditional test power; Axis 4: inverse of the combined variance; Axis 5: inverse of the number of variables (used to encourage more concise subgroup definitions).

[0045] In a specific implementation, the area enclosed by the radar chart can be determined according to a radar chart area calculation formula, and the area enclosed by the radar chart is used as the comprehensive score of each of the subgroups. The radar chart area calculation formula is: ; In the formula, represents the normalized value of each axis, is the angle between the radar chart axes.

[0046] Step S40: Screening out treatment-sensitive subgroups from each of the subgroups based on the comprehensive scores of each of the subgroups.

[0047] It should be noted that all subgroups can be sorted in descending order according to the comprehensive scores, and subgroups with higher scores can be given priority to ensure that the screened subgroups are at the optimal level in terms of efficacy, statistical significance, stability, statistical power and operability.

[0048] In a specific implementation, each of the subgroups can be arranged in descending order according to the comprehensive score of each subgroup to obtain a sorting result; the comprehensive score of each of the subgroups in the sorting result is compared with a preset score threshold to obtain a comparison result; and a treatment-sensitive subgroup is screened out from each of the subgroups based on the comparison result.

[0049] This embodiment discloses obtaining clinical trial data, parsing the candidate variables in the clinical trial data, and obtaining the variable parsing results; performing a full variable combination traversal according to the variable parsing results, and screening the clinical trial data based on the traversal results to obtain multiple subgroups; determining the comprehensive score of each subgroup through a radar chart based on the effect size, statistical test value, conditional test efficiency, combined variance and number of candidate variables of each subgroup; and screening out treatment-sensitive subgroups from each subgroup based on the comprehensive score of each subgroup. Since this embodiment performs a full variable combination traversal according to the variable parsing results, and screens the clinical trial data based on the traversal results, and determines the comprehensive score of each subgroup through a radar chart based on the effect size, statistical test value, conditional test efficiency, combined variance and number of candidate variables of each subgroup, and then screens out treatment-sensitive subgroups, compared with the prior art, this embodiment improves the efficiency and accuracy of screening treatment-sensitive populations, and thus optimizes clinical trial data analysis.

[0050] refer to Figure 2 , Figure 2 This is a schematic flow chart of the second embodiment of the method for screening treatment-sensitive populations based on test data of the present invention.

[0051] Based on the above first embodiment, in this embodiment, step S20 includes steps S201 to S203: Step S201: performing a full variable combination traversal on each candidate variable based on the value range of each candidate variable in the variable analysis result to obtain a traversal result.

[0052] Step S202: Match each variable-value combination in the traversal result in the clinical trial data, and determine the proportion of the number of people in each variable-value combination in the clinical trial data.

[0053] Step S203: Screening the clinical trial data based on the population ratio information to obtain multiple subgroups.

[0054] It should be explained that by matching each variable-value combination in the traversal results in the clinical trial data and determining the population ratio information of each variable-value combination in the clinical trial data, it is possible to eliminate subgroups whose population ratio is lower than a threshold (such as <5%) and avoid insufficient statistical power (since small samples can easily lead to inrobust statistical tests (such as large fluctuations in p-values)).

[0055] It should be noted that this example systematically extracts statistically significant subgroups from clinical trial data by traversing all variable combinations, matching data, and screening by population proportion. This method combines computational optimization with scientific threshold setting to ensure that the results are both comprehensive (covering all potential combinations) and reliable (excluding small sample interference), providing a data-driven subgroup analysis basis for precision medicine.

[0056] This embodiment discloses performing a full variable combination traversal on each of the candidate variables based on the value range of each of the candidate variables in the variable analysis result to obtain a traversal result; matching each variable-value combination in the traversal result in the clinical trial data, and determining the population ratio information of each variable-value combination in the clinical trial data; screening the clinical trial data based on the population ratio information to obtain multiple subgroups. Compared with the prior art, since this embodiment matches each variable-value combination in the traversal result in the clinical trial data, and determines the population ratio information of each variable-value combination in the clinical trial data, and screens the clinical trial data based on the population ratio information, it is possible to extract statistically significant subgroups from the clinical trial data, and ensure the reliability of subsequent clinical trial data analysis.

[0057] In addition, an embodiment of the present invention also proposes a storage medium, on which is stored a treatment sensitive population screening program based on test data, and when the treatment sensitive population screening program based on test data is executed by a processor, the steps of the treatment sensitive population screening method based on test data as described above are implemented.

[0058] Reference Figure 3 , Figure 3 This is a structural block diagram of the first embodiment of the treatment sensitive population screening system based on test data of the present invention.

[0059] like Figure 3 As shown, the treatment sensitive population screening system based on test data proposed in the embodiment of the present invention includes: a variable analysis module 501, a combination variable module 502, a comprehensive scoring module 503 and a subgroup screening module 504.

[0060] The variable analysis module 501 is used to obtain clinical trial data, and analyze candidate variables in the clinical trial data to obtain variable analysis results.

[0061] The combination variable module 502 is used to perform a full variable combination traversal according to the variable analysis results, and screen the clinical trial data based on the traversal results to obtain multiple subgroups.

[0062] The comprehensive scoring module 503 is used to determine the comprehensive score of each subgroup through a radar chart based on the effect size, statistical test value, conditional test power, combined variance and number of alternative variables of each subgroup.

[0063] The subgroup screening module 504 is used to screen out treatment-sensitive subgroups from each of the subgroups according to the comprehensive scores of each of the subgroups.

[0064] The variable analysis module 501 is also used to obtain clinical trial data, identify the variable type of each candidate variable in the clinical trial data, and obtain an identification result; if the variable type of the candidate variable in the identification result is a continuous variable, the corresponding candidate variable is divided into two-category variables according to the median to obtain a first analysis result; if the variable type of the candidate variable in the identification result is a categorical variable, the original value of the corresponding candidate variable is determined to obtain a second analysis result; the first analysis result and the second analysis result are used as variable analysis results.

[0065] The comprehensive scoring module 503 is also used to determine the effect size of each subgroup based on the difference between the two group means, the risk ratio or the survival analysis index between different treatment groups of each subgroup; determine the statistical test value of each subgroup based on the t value, p value or confidence interval of each subgroup; determine the conditional test power of each subgroup based on the conditional test power calculation formula; determine the combined variance of the experimental group and the control group in each subgroup based on the combined variance calculation formula.

[0066] The comprehensive scoring module 503 is also used to standardize the effect size, statistical test value, conditional test power, inverse of the combined variance and inverse of the number of alternative variables of each subgroup to obtain standardized indicators; use the standardized indicators as the radar chart axis to generate a radar chart, and use the area enclosed by the radar chart as the comprehensive score of each subgroup.

[0067] The subgroup screening module 504 is further used to arrange each of the subgroups in descending order according to the comprehensive score of each of the subgroups to obtain a sorting result; compare the comprehensive score of each of the subgroups in the sorting result with a preset score threshold to obtain a comparison result; and screen out a treatment-sensitive subgroup from each of the subgroups based on the comparison result.

[0068] The present system embodiment discloses obtaining clinical trial data, and parsing the candidate variables in the clinical trial data to obtain the variable parsing results; performing a full variable combination traversal according to the variable parsing results, and screening the clinical trial data based on the traversal results to obtain multiple subgroups; determining the comprehensive score of each subgroup through a radar chart based on the effect size, statistical test value, conditional test efficiency, combined variance and number of candidate variables of each subgroup; and screening out treatment-sensitive subgroups from each subgroup based on the comprehensive score of each subgroup. Since the present system embodiment performs a full variable combination traversal according to the variable parsing results, and screens the clinical trial data based on the traversal results, and determines the comprehensive score of each subgroup through a radar chart based on the effect size, statistical test value, conditional test efficiency, combined variance and number of candidate variables of each subgroup, and then screens out treatment-sensitive subgroups, compared with the prior art, the present system embodiment improves the efficiency and accuracy of screening treatment-sensitive populations, and thus optimizes the analysis of clinical trial data.

[0069] Based on the first embodiment of the system for screening a treatment-sensitive population based on test data of the present invention, a second embodiment of the system for screening a treatment-sensitive population based on test data of the present invention is proposed.

[0070] In this embodiment, the combination variable module 502 is also used to perform a full variable combination traversal on each of the candidate variables based on the value range of each of the candidate variables in the variable analysis results to obtain a traversal result; match each variable-value combination in the traversal result in the clinical trial data, and determine the population proportion information of each variable-value combination in the clinical trial data; and screen the clinical trial data based on the population proportion information to obtain multiple subgroups.

[0071] Other embodiments or specific implementations of the treatment sensitive population screening system based on test data of the present invention can refer to the above-mentioned method embodiments, which will not be described in detail here.

[0072] The present application provides a device for screening a treatment-sensitive population based on test data, and the device for screening a treatment-sensitive population based on test data includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for screening a treatment-sensitive population based on test data in the above-mentioned embodiment one.

[0073] Reference below Figure 4, which shows a schematic diagram of the structure of a treatment-sensitive population screening device based on test data suitable for implementing the embodiment of the present application. The treatment-sensitive population screening device based on test data in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 4 The treatment-sensitive population screening device based on test data is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0074] like Figure 4 As shown, the treatment sensitive population screening device based on test data may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory 1002 or the program loaded from the storage device 1003 to the random access memory 1004. In the random access memory 1004, various programs and data required for the operation of the treatment sensitive population screening device based on test data are also stored. The processing device 1001, the read-only memory 1002 and the random access memory 1004 are connected to each other through a bus 1005. The input / output interface 1006 is also connected to the bus. Generally, the following systems can be connected to the input / output interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the treatment sensitive population screening device based on test data to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows the treatment sensitive population screening device based on test data with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0075] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a read-only memory 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0076] The treatment sensitive population screening device based on test data provided by the present application adopts the treatment sensitive population screening method based on test data in the above-mentioned embodiment, which can solve the technical problem of low efficiency and accuracy of treatment sensitive population screening in clinical trial data analysis in the prior art. Compared with the prior art, the beneficial effects of the treatment sensitive population screening device based on test data provided by the present application are the same as the beneficial effects of the treatment sensitive population screening method based on test data provided by the above-mentioned embodiment, and the other technical features of the treatment sensitive population screening device based on test data are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0077] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0078] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0079] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0080] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0081] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0082] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for screening treatment-sensitive populations based on experimental data, characterized in that: The method comprises: Acquire clinical trial data, and parse candidate variables in the clinical trial data to obtain variable parsing results; Performing a full variable combination traversal according to the variable analysis results, and screening the clinical trial data based on the traversal results to obtain multiple subgroups; Based on the effect size, statistical test value, conditional test power, combined variance and number of alternative variables of each subgroup, a comprehensive score of each subgroup is determined by a radar chart; According to the comprehensive scores of each of the subgroups, a treatment-sensitive subgroup is screened out from each of the subgroups.

2. The method for screening treatment-sensitive populations based on test data according to claim 1, characterized in that: The step of acquiring clinical trial data, parsing candidate variables in the clinical trial data, and obtaining variable parsing results includes: Acquire clinical trial data, identify the variable type of each candidate variable in the clinical trial data, and obtain an identification result; If the variable type of the candidate variable in the identification result is a continuous variable, the corresponding candidate variable is divided into two-category variables according to the median to obtain a first analysis result; If the variable type of the candidate variable in the recognition result is a categorical variable, determining the original value of the corresponding candidate variable to obtain a second parsing result; The first analysis result and the second analysis result are used as variable analysis results.

3. The method for screening treatment-sensitive populations based on test data according to claim 1, characterized in that: The step of performing a full variable combination traversal according to the variable analysis result, and screening the clinical trial data based on the traversal result to obtain multiple subgroups includes: Performing a full variable combination traversal on each candidate variable based on the value range of each candidate variable in the variable analysis result to obtain a traversal result; Matching each variable-value combination in the traversal result in the clinical trial data, and determining the proportion of the number of people in each variable-value combination in the clinical trial data; The clinical trial data is screened based on the population proportion information to obtain multiple subgroups.

4. The method for screening treatment-sensitive populations based on test data according to claim 1, characterized in that: Before the step of determining the comprehensive score of each subgroup through a radar chart based on the effect size, statistical test value, conditional test efficiency, combined variance and number of candidate variables of each subgroup, the step further includes: Determine the effect size of each subgroup according to the mean difference between two groups, risk ratio or survival analysis index between different treatment groups; Determine the statistical test value of each subgroup according to the t value, p value or confidence interval of each subgroup; Determine the conditional test efficacy of each of the subgroups based on a conditional test efficacy calculation formula; The combined variance of the experimental group and the control group in each of the subgroups was determined based on the combined variance calculation formula.

5. The method for screening treatment-sensitive populations based on test data according to claim 4, characterized in that: The conditional test efficiency calculation formula is: ； In the formula, represents the standardized test statistic for subgroup k, is the critical value of the significance test, represents the conditional test power for subgroup k, Represents the test data currently collected; The combined variance calculation formula is: ； In the formula, and Respectively represent the sample size of the experimental group and the control group in each subgroup, and Represent the sample variance of the experimental group and the control group in each subgroup, respectively.

6. The method for screening treatment-sensitive populations based on test data according to claim 1, characterized in that: The step of determining the comprehensive score of each subgroup through a radar chart based on the effect size, statistical test value, conditional test power, combined variance and number of candidate variables of each subgroup comprises: The effect size, statistical test value, conditional test power, reciprocal of the combined variance and reciprocal of the number of alternative variables of each subgroup are standardized to obtain standardized indicators; The standardized index is used as the radar chart axis to generate a radar chart, and the area enclosed by the radar chart is used as the comprehensive score of each subgroup.

7. The method for screening treatment-sensitive populations based on test data according to claim 1, characterized in that: The step of screening out treatment-sensitive subgroups from each of the subgroups according to the comprehensive scores of each of the subgroups comprises: Arrange the subgroups in descending order according to their comprehensive scores to obtain a ranking result; Comparing the comprehensive score of each of the subgroups in the sorting result with a preset score threshold to obtain a comparison result; Based on the comparison results, a treatment-sensitive subgroup is screened out from each of the subgroups.

8. A treatment-sensitive population screening system based on test data, characterized in that: The system comprises: A variable analysis module, used to obtain clinical trial data, and analyze candidate variables in the clinical trial data to obtain variable analysis results; A combination variable module, used for performing a full variable combination traversal according to the variable analysis results, and screening the clinical trial data based on the traversal results to obtain multiple subgroups; A comprehensive scoring module, used to determine the comprehensive score of each of the subgroups through a radar chart based on the effect size, statistical test value, conditional test power, combined variance and number of alternative variables of each of the subgroups; The subgroup screening module is used to screen out treatment-sensitive subgroups from each of the subgroups based on the comprehensive scores of each of the subgroups.

9. A device for screening treatment-sensitive populations based on test data, characterized in that: The device includes: a memory, a processor, and a treatment sensitive population screening program based on test data stored in the memory and executable on the processor, wherein the treatment sensitive population screening program based on test data is configured to implement the steps of the treatment sensitive population screening method based on test data as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a treatment sensitive population screening program based on test data, and when the treatment sensitive population screening program based on test data is executed by the processor, the steps of the treatment sensitive population screening method based on test data as described in any one of claims 1 to 7 are implemented.

Images