Estimation target analysis method and system, electronic equipment and medium
By acquiring and comparing the expected effects of exposure factor parameters and negative outcome control parameters, bias can be directly detected and quantified, solving the problem of inaccurate estimation of target analysis results in existing technologies and improving the accuracy and reliability of the analysis.
Patent Information
- Application Number
- CN202510183435.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-19
- Publication Date
- 2026-05-01
AI Technical Summary
Existing target estimation analysis methods suffer from bias in practical applications, leading to inaccurate analysis results and failing to meet the needs of high-precision analysis.
By obtaining exposure factor parameters and negative outcome control parameters from the target dataset, calculating and comparing the expected effects of exposure factor parameters on study outcome parameters and negative outcome control parameters, bias can be directly detected and quantified, overcoming the limitations of relying on subjective assumptions or indirect adjustment methods.
It enables direct detection and quantification of bias in analysis results, reduces the risk of erroneous conclusions due to bias, and improves the accuracy and reliability of analysis results.
Smart Images
Figure CN121964168A_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the field of data analysis technology, and relates to a target estimation analysis method, and in particular to a target estimation analysis method, system, electronic device and medium. Background Technology
[0002] Among existing data analysis techniques, target estimation analysis is a commonly used method to assess the impact of exposure factors (such as drug treatment, environmental factors, etc.) on study outcomes (such as disease incidence, economic indicators, etc.). However, existing target estimation analysis methods suffer from a significant problem in practical applications: the results are often influenced by various biases, leading to inaccurate estimates. Bias can stem from multiple factors, such as selection bias, measurement bias, and confounding bias. These biases can cause the expected effect of the exposure factor on the study outcome to deviate from the true value, thus affecting the reliability of the analysis results. For example, in medical research, failure to effectively control confounding factors may lead to biased estimates of drug efficacy, thereby affecting the accuracy of clinical decisions. Although some methods attempt to reduce bias through statistical adjustment or sensitivity analysis, these methods often rely on assumptions about the source of bias and cannot directly quantify the magnitude of bias. Therefore, current target estimation analysis results still have considerable uncertainty and are insufficient to meet the needs of high-precision analysis. Summary of the Invention
[0003] In view of the shortcomings of the prior art described above, the purpose of this application is to provide an estimation target analysis method, system, electronic device and medium to solve the problem that the estimation target analysis results in the prior art are inaccurate and difficult to meet the requirements of high-precision analysis.
[0004] In a first aspect, this application provides a method for estimating a target, the method comprising: acquiring a target dataset, the target dataset including exposure factor parameters, study outcome parameters, and preset negative outcome control parameters; analyzing the estimated target using the negative outcome control parameters to obtain a first expected value of the effect of the exposure factor parameters on the study outcome parameters and a second expected value of the effect of the exposure factor parameters on the negative outcome control parameters; and performing a numerical comparison of the first expected value of the effect and the second expected value of the effect to obtain a bias analysis result of the estimated target.
[0005] In this application, by comparing the expected effect of exposure factor parameters on study outcome parameters and negative outcome control parameters, bias in the results can be directly detected and quantified. This overcomes the limitations of relying on subjective assumptions or indirect adjustment methods, solves the problem that traditional methods cannot clearly distinguish between true effects and bias, and reduces the risk of erroneous conclusions due to bias.
[0006] In one implementation of the first aspect, analyzing the estimated target using negative outcome control parameters to obtain the first expected value of the effect of the exposure factor parameter on the study outcome parameter and the second expected value of the effect of the exposure factor parameter on the negative outcome control parameter includes: analyzing the estimated target using the negative outcome control parameters to obtain the expected value of the effect of the exposure factor parameter on the unmeasured confounding factor parameter; and obtaining the first expected value of the effect of the exposure factor parameter on the study outcome parameter and the second expected value of the effect of the exposure factor parameter on the negative outcome control parameter under the influence of the unmeasured confounding factor, based on the expected value of the effect of the exposure factor parameter on the unmeasured confounding factor parameter.
[0007] In one implementation of the first aspect, the numerical comparison of the first expected effect value and the second expected effect value to obtain the bias analysis result of the estimated target includes: obtaining the effect value of the first confounding bias of the exposure factor parameter on the study outcome parameter based on the first expected effect value; obtaining the effect value of the second confounding bias of the exposure factor parameter on the negative outcome control parameter based on the second expected effect value; and numerically comparing the effect values of the first confounding bias and the second confounding bias to obtain the bias analysis result of the estimated target.
[0008] In one implementation of the first aspect, the effect size of the first confounding bias includes the effect size of the unmeasured confounding factor parameter on the study outcome parameter and the effect size of the exposure factor parameter on the unmeasured confounding factor parameter; the effect size of the second confounding bias includes the effect size of the unmeasured confounding factor parameter on the negative outcome control parameter and the effect size of the exposure factor parameter on the unmeasured confounding factor parameter; and the numerical comparison of the effect size of the first confounding bias and the effect size of the second confounding bias includes: numerically comparing the effect size of the unmeasured confounding factor parameter on the study outcome parameter with the effect size of the unmeasured confounding factor parameter on the negative outcome control parameter.
[0009] In one implementation of the first aspect, a master estimation analysis and at least one sensitivity analysis are included, and the results of the sensitivity analysis and the master estimation analysis are used to perform a comprehensive analysis to obtain the estimation target analysis results.
[0010] In one implementation of the first aspect, the estimated target analysis method includes: analyzing the estimated target using multiple negative outcome control parameters to verify the estimated target analysis results.
[0011] In one implementation of the first aspect, the target estimation analysis method includes: obtaining a bias type based on the bias analysis results of the estimated target; updating the negative outcome control parameters using the bias type to analyze the estimated target and obtain the bias analysis results of the estimated target.
[0012] Secondly, this application provides an estimation target analysis system, comprising: a parameter acquisition module for acquiring a target dataset, the target dataset including exposure factor parameters, study outcome parameters, and preset negative outcome control parameters; a data analysis module for analyzing the estimated target using the negative outcome control parameters to obtain a first expected value of the effect of the exposure factor parameters on the study outcome parameters and a second expected value of the effect of the exposure factor parameters on the negative outcome control parameters; and a bias detection module for numerically comparing the first expected value of the effect and the second expected value of the effect to obtain the bias analysis result of the estimated target.
[0013] Thirdly, this application provides an electronic device comprising: a memory for storing a computer program; and a processor for executing the computer program stored in the memory to cause the electronic device to perform the target estimation analysis method as described in any one of the first aspects.
[0014] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the target estimation analysis method described in any one of the first aspects. Attached Figure Description
[0015] Figure 1 The diagram shown is a schematic representation of the research framework for estimating the target as described in the embodiments of this application.
[0016] Figure 2A The diagram shown illustrates an application scenario of the target estimation analysis method described in this application.
[0017] Figure 2B This diagram illustrates the structure of the mid-cloud interaction scenario in these implementation methods.
[0018] Figure 3 The diagram shown is a flowchart illustrating the target estimation analysis method described in the embodiments of this application.
[0019] Figure 4 The diagram shown is a flowchart illustrating the target estimation analysis method described in the embodiments of this application.
[0020] Figure 5 The diagram shown is an analysis schematic of the negative outcome control described in the embodiments of this application.
[0021] Figure 6 The diagram shown is a schematic representation of the target estimation analysis system described in an embodiment of this application.
[0022] Figure 7 The diagram shown is a structural schematic of the electronic device described in an embodiment of this application.
[0023] Component designation explanation
[0024] 1. Target estimation analysis device
[0025] 11 Storage devices
[0026] 12 Local Processors
[0027] 13 Display Terminals
[0028] 2-Terminal-Cloud Interactive System
[0029] 20 terminals
[0030] 21 Cloud Servers
[0031] 100 Target Estimation Analysis System
[0032] 110 Parameter Acquisition Module
[0033] 120 Data Analysis Module
[0034] 130 Bias Detection Module
[0035] 700 electronic devices
[0036] 710 Memory
[0037] 720 processor
[0038] 730 monitor
[0039] Steps S11 to S13
[0040] Steps S131~S133 Detailed Implementation
[0041] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.
[0042] It should be noted that in the embodiments of this application, the words "optionally" or "for example" indicate examples, illustrations, or descriptions. Any embodiment or design scheme described as "optionally" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the words "optionally" or "for example" is intended to present the relevant concepts in a specific manner.
[0043] In this application embodiment, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.
[0044] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this application. Therefore, the drawings only show the components related to this application and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.
[0045] Figure 1 This diagram illustrates the research framework for estimating the target as described in an embodiment of this application. Figure 1 As shown, the research framework based on estimation objectives clearly outlines the trial purpose, estimation target, estimation method and estimators, estimated values, and sensitivity analysis. This helps researchers design trial protocols, discuss the applicability of clinical trial designs, and provide a clear framework and explicit constraints when interpreting clinical trial results. It also assists regulatory agencies in reviewing trials. Among the attributes of estimation objectives, the prediction of comorbidities and the selection of management strategies are the most challenging. Commonly used comorbidity management strategies include therapeutic strategies, hypothetical strategies, combined strategies, in-treatment strategies, and master-level strategies. Multiple strategies are often used to manage the same comorbidity. Therefore, for an estimation objective, there is usually a master estimation method and one or more sensitivity analyses, yielding one or more sensitivity estimates. Consequently, current estimation objective analysis results still suffer from inconsistencies between master analysis results and sensitivity analyses, making it difficult to meet the needs of high-precision analysis.
[0046] At least to address the above-mentioned problems, embodiments of this application provide an estimation target analysis method, the estimation target analysis method comprising: analyzing the estimated target using a negative outcome control to obtain the expected effect of the exposure factor on the study outcome and the expected effect of the exposure factor on the negative outcome control; determining whether the expected effect of the exposure factor on the study outcome and the expected effect of the exposure factor on the negative outcome control are the same; if so, confirming that the analysis result of the co-occurring event on the study outcome is unbiased; if not, confirming that the analysis result of the co-occurring event on the study outcome is biased.
[0047] In this embodiment of the application, by comparing the expected effect of the exposure factor parameter on the study outcome parameter and the negative outcome control parameter, bias in the results can be directly detected and quantified. This overcomes the limitations of relying on subjective assumptions or indirect adjustment methods, solves the problem that traditional methods cannot clearly distinguish between the true effect and bias, and reduces the risk of incorrect conclusions due to bias.
[0048] Figure 2A This diagram illustrates an application scenario of the target estimation analysis method described in this application. The target estimation analysis device 1 can be used to implement the target estimation analysis method provided in the embodiments of this application, but the application scenarios of the target estimation analysis method provided in the embodiments of this application are not limited to this. Figure 2A The target estimation analysis device 1 is shown. (As shown in the image) Figure 2A As shown, the target estimation analysis device 1 includes a storage device 11, a local processor 12, and a display terminal 13. The target estimation analysis method provided in this application embodiment can be applied to the local processor 12.
[0049] in, Figure 2A The local processor 12 can be a single local processor, a cluster of multiple local processors, or a cloud computing center, etc., and is not specifically limited here. Although Figure 2A Only one storage device 11, one local processor 12, and one display terminal 13 are shown, but it should be understood that... Figure 2A The examples in this paper are only for understanding this solution. The specific number of local processors 12 and display terminals 13 should be flexibly determined based on the actual situation.
[0050] In some other implementations, the target estimation analysis device 1 may not include a display terminal 13, but only a local processor 12 with display functionality and a storage device 11. The target estimation analysis method provided in this application embodiment can be applied to the local processor 12. The local processor 12 with display functionality may include tablet computers, PDAs, mobile phones, personal computers, and voice interaction devices, and is not limited here.
[0051] In some other implementations, the target estimation analysis method described in this application can be applied to edge-cloud interaction scenarios. Figure 2B This diagram illustrates the structure of the endpoint-cloud interaction scenario in these implementation methods. For example... Figure 2B As shown, the terminal-cloud interaction system 2 includes a terminal 20 and a cloud server 21. The terminal 20 and the cloud server 21 can communicate with each other, and the communication method is not limited to wired or wireless.
[0052] The terminal 20 can be mobile or fixed. For example, it can be a wireless terminal or a wired terminal. A wireless terminal can refer to a device with wireless transceiver capabilities, which can be deployed indoors, outdoors, and in medical testing rooms. The terminal 20 can be a mobile phone, tablet computer, laptop computer, etc., and is not limited thereto. The cloud server 21 can include one or more servers, or one or more processing nodes, or one or more virtual machines running on the server. The cloud server 21 can also be referred to as a server cluster, management platform, data processing center, etc., and is not limited thereto in this embodiment.
[0053] The technical solutions in the embodiments of this application will be described in detail below with reference to the accompanying drawings.
[0054] The following embodiments of this application provide a target estimation analysis method, which, for example, can be achieved through... Figure 2A The local processor 12 shown Figure 2B The cloud server 21 shown is used to implement this. Figure 3 The diagram shown is a flowchart illustrating the target estimation analysis method described in the embodiments of this application. Figure 3 As shown, the target estimation analysis method includes steps S11 to S13.
[0055] Step S11: Obtain the target dataset, which includes exposure factor parameters, study outcome parameters, and preset negative outcome control parameters.
[0056] Step S12: Analyze the estimated target using the negative outcome control parameter to obtain the expected first effect of the exposure factor parameter on the study outcome parameter and the expected second effect of the exposure factor parameter on the negative outcome control parameter.
[0057] Step S13: Compare the expected value of the first effect and the expected value of the second effect numerically to obtain the bias analysis results of the estimated target.
[0058] In some possible implementations, the estimated target is a precise description of the specific objective of the clinical trial. It includes five attributes: study treatment, target population, target variable, comorbidities and their management strategies, and study effect at the target population level. Study treatment refers to the relevant treatment conditions, and other treatment conditions for comparison where applicable; the target population refers to the patient population to which the clinical problem is addressed; the target variable refers to the variable obtained from each patient to address the clinical problem; comorbidities refer to events that occur after the start of treatment and can affect the interpretation of observations related to the clinical problem; and the population-level summary refers to the population-level summary statistics specifying the target variable, providing a basis for comparisons between different treatments. During the analysis of comorbidities, a target dataset is obtained, which includes exposure factor parameters, study outcome parameters, and pre-defined negative outcome control parameters. The estimated target is analyzed using the negative outcome control parameters to obtain the first expected value of the effect of the exposure factor parameters on the study outcome parameters and the second expected value of the effect of the exposure factor parameters on the negative outcome control parameters. The first and second expected values are numerically compared to obtain the bias analysis results of the estimated target. If the bias analysis of the estimated target shows no bias, then it is confirmed that there is no causal relationship between the negative outcome control and the co-occurring event, and the co-occurring event shows a zero effect between the negative outcome control and the negative outcome control. If the bias analysis of the estimated target shows bias, then it is confirmed that there is a causal relationship between the negative outcome control and the co-occurring event.
[0059] In other possible implementations, during clinical trials aimed at improving lung function, glucocorticoids were used during acute asthma exacerbations. If a treatment strategy to manage comorbidities is employed, observations with or without glucocorticoid use will be included in the data analysis, potentially interfering with the actual study outcome. In such cases, changes in serum calcium levels are used as a negative outcome control parameter to analyze the estimated target and obtain bias analysis results. Changes in serum calcium levels are affected by glucocorticoids but are independent of drug studies. If the drug and changes in serum calcium levels show a zero effect, the bias analysis result for the estimated target is confirmed to be unbiased.
[0060] In this embodiment of the application, by comparing the expected effect of the exposure factor parameter on the study outcome parameter and the negative outcome control parameter, bias in the results can be directly detected and quantified. This overcomes the limitations of relying on subjective assumptions or indirect adjustment methods, solves the problem that traditional methods cannot clearly distinguish between the true effect and bias, and reduces the risk of incorrect conclusions due to bias.
[0061] In one embodiment of this application, analyzing the estimated target using negative outcome control parameters to obtain the first expected effect value of the exposure factor parameter on the study outcome parameter and the second expected effect value of the exposure factor parameter on the negative outcome control parameter includes: analyzing the estimated target using the negative outcome control parameters to obtain the expected effect value of the exposure factor parameter on the unmeasured confounding factor parameter.
[0062] Based on the expected effect of the exposure factor parameter on the unmeasured confounding factor parameter, the first expected effect of the exposure factor parameter on the study outcome parameter and the second expected effect of the exposure factor parameter on the negative outcome control parameter under the influence of the unmeasured confounding factor are obtained.
[0063] In some possible implementations, the unmeasured confounding factor parameter is often unknown and influenced by unmeasured confounding factors, and the expected value of the first effect of the exposure factor parameter on the study outcome parameter is the effect value of confounding bias. If the negative outcome control parameter is set correctly, an unbiased estimate of the exposure factor parameter on the study outcome parameter can be obtained.
[0064] Figure 4 The diagram shown is a flowchart illustrating the target estimation analysis method described in the embodiments of this application. Figure 4 As shown, step S13 includes steps S131 to S133.
[0065] Step S131: Obtain the effect value of the first confounding bias of the exposure factor parameter on the study outcome parameter based on the first expected effect value.
[0066] Step S132: Obtain the effect value of the second confounding bias of the exposure factor parameter on the negative outcome control parameter based on the second effect expectation value.
[0067] Step S133: The effect values of the first confounding bias and the second confounding bias are numerically compared to obtain the bias analysis results of the estimated target.
[0068] In one embodiment of this application, the effect of confounding bias in the study outcome includes the effect of the unmeasured confounding factor on the study outcome and the effect of the exposure factor on the unmeasured confounding factor. The effect of confounding bias in the negative outcome control includes the effect of the unmeasured confounding factor on the negative outcome control and the effect of the exposure factor on the unmeasured confounding factor. Determining whether the effect of confounding bias in the study outcome is the same as the effect of confounding bias in the negative outcome control includes determining whether the effect of the unmeasured confounding factor on the study outcome is the same as the effect of the unmeasured confounding factor on the negative outcome control.
[0069] Among some possible implementations, Figure 5 This diagram illustrates the analysis of the negative outcome control as described in the embodiments of this application. In a randomized controlled trial (RCT), the randomization variable is a suitable instrumental variable. The directed acyclic graph after introducing the negative outcome control in the RCT is shown below. Figure 5 As shown, the theoretical effect value of exposure factor A is assumed to be β. YA In the case where the confounding factor U is not measured:
[0070] E[Y|A,U]=β Y0 +β YA A+β YU U
[0071] E[W|U]=β W0 +β WU U
[0072] E[U|A]=β U0 +β UA A,
[0073] E[Y|A]=β Y0 +β YA A+β YU E[U|A]=β Y0 +β YA A+β YU (β U0 +β UA A)
[0074] E[W|A]=β W0 +β WU E[U|A]=β W0 +β WU (β U0 +β UA A)
[0075] Where, β Y0 β U0 and β W0 β is a constant term. YU β represents the effect size of unmeasured confounding factor parameters on the study outcome parameter. WU For the effect size of the unmeasured confounding factor parameter on the negative outcome control parameter, β UAE[Y|A,U] represents the effect of the unmeasured confounding parameter on the exposure parameter, E[W|U] represents the expected effect of the exposure parameter on the unmeasured confounding parameter under the influence of the unmeasured confounding parameter, E[U|A] represents the expected effect of the exposure parameter on the unmeasured confounding parameter, E[Y|A] represents the expected effect of the exposure parameter on the study outcome parameter, and E[W|A] represents the expected effect of the exposure parameter on the negative outcome control parameter.
[0076] Without measuring the influence of confounding factors, the effect of the exposure factor parameter is estimated to be β. YA +β YU β UA ,β YU β UA This represents the effect size for the first confounding bias. In the negative outcome control model E[W|A], since there is no causal association between the negative outcome control parameter and the exposure factor parameter, β... WU β UA This is the effect size for the second confounding bias. If the negative outcome control is properly configured, then β... WU =β YU Thus, the bias analysis results of the estimated target are obtained.
[0077] In this embodiment of the application, the bias of the estimated target is detected and quantified, which can make up for the shortcomings of the accompanying event handling strategy, fully consider the problem of bias vacancy, and reduce the risk of incorrect conclusions due to bias.
[0078] In one embodiment of this application, the target estimation analysis method includes a master estimation analysis and at least one sensitivity analysis. The results of the sensitivity analysis and the master estimation analysis are used to perform a comprehensive analysis to obtain the target estimation analysis result.
[0079] Among the possible implementations, five common strategies are used to handle co-occurring events: therapeutic strategy, hypothetical strategy, combined strategy, in-treatment strategy, and master strategy. Multiple strategies are often used to handle the same co-occurring event. Therefore, for an estimation target, there is usually a master estimation method and one or more sensitivity analyses to obtain one or more sensitivity estimates.
[0080] In one embodiment of this application, the target estimation analysis method includes: analyzing the estimated target using multiple negative outcome control parameters to verify the target estimation analysis results.
[0081] In some possible implementations, the exposure factor is vaccination with the experimental vaccine, and the negative outcome control is a placebo. The estimated target analysis results, such as vaccine efficacy, are validated by comparing study outcomes, such as infection rates.
[0082] In one embodiment of this application, the target estimation analysis method includes: obtaining a bias type based on the bias analysis result of the estimated target; updating the negative outcome control parameter using the bias type to analyze the estimated target and obtain the bias analysis result of the estimated target.
[0083] In some possible implementations, post-randomization randomization in clinical trials frequently results in patient transfers due to their condition or subjective preference. These concomitant events pose a significant risk of disrupting randomization and introducing various forms of bias. For example, consider the data analysis of hypofractionated versus conventionally fractionated radiotherapy after breast cancer resection based on implant reconstruction. The treatment groups were hypofractionated and conventionally fractionated radiotherapy. The uniformity of radiation dose distribution within the target area during treatment was an unknown confounding parameter. Bias was controlled by introducing skin condition as a negative outcome control.
[0084] Figure 6 The diagram shown is a structural schematic of the target estimation analysis system described in the embodiments of this application, as follows: Figure 6 As shown, the target estimation analysis system 100 includes a parameter acquisition module 110, a data analysis module 120, and a bias detection module 130.
[0085] The parameter acquisition module 110 is used to acquire the target dataset, which includes exposure factor parameters, study outcome parameters, and preset negative outcome control parameters.
[0086] The data analysis module 120 is used to analyze the estimated target using the negative outcome control parameter, and to obtain the first expected value of the effect of the exposure factor parameter on the study outcome parameter and the second expected value of the effect of the exposure factor parameter on the negative outcome control parameter.
[0087] The bias detection module 130 is used to perform a numerical comparison between the expected value of the first effect and the expected value of the second effect to obtain the bias analysis results of the estimated target.
[0088] In some possible implementations, the estimation objective is a precise description of the specific goals of a clinical trial. It includes five attributes: study treatment, target population, target variable, comorbidities and their management strategies, and study effect at the target population level. Study treatment refers to the relevant treatment conditions, and other treatment conditions for comparison where applicable; the target population refers to the patient population addressing the clinical problem; the target variable refers to the variable obtained from each patient to address the clinical problem; comorbidities refer to events that occur after the start of treatment and can affect the interpretation of observations related to the clinical problem; and the population-level summary refers to the population-level summary statistics specifying the target variable, providing a basis for comparisons between different treatments.
[0089] During the analysis of the comorbidity event, the parameter acquisition module 110 acquires a target dataset, which includes exposure factor parameters, study outcome parameters, and preset negative outcome control parameters. The data analysis module 120 uses the negative outcome control parameters to analyze the estimated target, obtaining the first expected effect value of the exposure factor parameters on the study outcome parameters and the second expected effect value of the exposure factor parameters on the negative outcome control parameters. The bias detection module 130 performs a numerical comparison of the first and second expected effect values to obtain the bias analysis result of the estimated target. If the bias analysis result of the estimated target indicates no bias, it is confirmed that there is no causal relationship between the negative outcome control and the comorbidity event, and the comorbidity event exhibits a zero effect on the negative outcome control. If the bias analysis result of the estimated target indicates bias, it is confirmed that there is a causal relationship between the negative outcome control and the comorbidity event.
[0090] In this embodiment, the bias detection module 130 can directly detect and quantify the bias in the results by comparing the expected values of the effects of the exposure factor parameters on the study outcome parameters and the negative outcome control parameters. This overcomes the limitations of relying on subjective assumptions or indirect adjustment methods, solves the problem that traditional methods cannot clearly distinguish between the true effect and bias, and reduces the risk of incorrect conclusions due to bias.
[0091] In the embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, or methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules / units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or units may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of apparatuses or modules or units may be electrical, mechanical, or other forms.
[0092] The modules / units described as separate components may or may not be physically separate. The components shown as modules / units may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules / units can be selected to achieve the objectives of the embodiments of this application, depending on actual needs. For example, the functional modules / units in the various embodiments of this application may be integrated into one processing module, or each module / unit may exist physically separately, or two or more modules / units may be integrated into one module / unit.
[0093] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0094] This application also provides an electronic device. Figure 7 The diagram shown is a structural schematic of the electronic device 700 described in an embodiment of this application. Figure 7 As shown, in this embodiment, the electronic device 700 includes a memory 710 and a processor 720.
[0095] The memory 710 is used to store computer programs; preferably, the memory 710 includes various media that can store program code, such as ROM, RAM, magnetic disk, USB flash drive, memory card or optical disk.
[0096] Specifically, memory 710 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory. Electronic device 700 may further include other removable / non-removable, volatile / non-volatile computer system storage media. Memory 710 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this application. It is understood that memory 710 may be volatile memory or non-volatile memory, or both. Non-volatile memory may be read-only memory (ROM) or programmable read-only memory (PROM), which serves as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM) and synchronous static random access memory (SSRAM). The memories described in the embodiments of the present invention are intended to include, but are not limited to, these and any other suitable categories of memory.
[0097] The processor 720 is connected to the memory 710 and is used to execute the computer program stored in the memory 710 so that the electronic device 700 performs the target estimation analysis method described in any embodiment of this application.
[0098] Optionally, the processor 720 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.
[0099] Optionally, the electronic device 700 in this embodiment may further include a display 730. The display 730 is communicatively connected to the memory 710 and the processor 720, and is used to display the relevant graphical user interface (GUI) of the target estimation analysis method described in this application embodiment.
[0100] This application also provides a computer-readable storage medium having a computer program stored thereon. When executed by a processor, the program implements the target estimation analysis method described in any embodiment of this application.
[0101] As used in this specification, the terms "component," "module," "system," etc., are used to refer to computer-related entities, hardware, firmware, combinations of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program, and / or a computer. As illustrated, applications running on computing devices and computing devices can both be components. One or more components may reside in a process and / or an execution thread, and components may be located on a single computer and / or distributed among two or more computers. Furthermore, these components can be executed from various computer-readable media on which various data structures are stored. Components can communicate, for example, via local and / or remote processes based on signals having one or more data packets (e.g., data from two components interacting with another component between a local system, a distributed system, and / or a network, such as the Internet interacting with other systems via signals).
[0102] The descriptions of the processes or structures corresponding to the above figures each have their own emphasis. For parts of a process or structure that are not described in detail, please refer to the relevant descriptions of other processes or structures.
[0103] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.
Claims
1. A target estimation analysis method, characterized in that, include: Obtain the target dataset, which includes exposure factor parameters, study outcome parameters, and pre-defined negative outcome control parameters; The estimated target was analyzed using the negative outcome control parameter to obtain the expected first effect of the exposure factor parameter on the study outcome parameter and the expected second effect of the exposure factor parameter on the negative outcome control parameter; The expected values of the first effect and the second effect are numerically compared to obtain the bias analysis results of the estimated target.
2. The target estimation analysis method according to claim 1, characterized in that, Analyzing the estimated target using negative outcome control parameters, the expected first effect of the exposure factor parameter on the study outcome parameter and the expected second effect of the exposure factor parameter on the negative outcome control parameter are obtained, including: The estimated target is analyzed using the negative outcome control parameters to obtain the expected effect of the exposure factor parameters on the unmeasured confounding factor parameters; Based on the expected effect of the exposure factor parameter on the unmeasured confounding factor parameter, the first expected effect of the exposure factor parameter on the study outcome parameter and the second expected effect of the exposure factor parameter on the negative outcome control parameter under the influence of the unmeasured confounding factor are obtained.
3. The target estimation analysis method according to claim 1, characterized in that, The numerical comparison of the expected values of the first effect and the second effect to obtain the bias analysis results of the estimated target includes: The effect value of the first confounding bias of the exposure factor parameter on the study outcome parameter is obtained based on the first expected effect value; The effect value of the second confounding bias of the exposure factor parameter on the negative outcome control parameter is obtained based on the second expected effect value; The effect sizes of the first confounding bias and the second confounding bias are numerically compared to obtain the bias analysis results of the estimated target.
4. The target estimation analysis method according to claim 3, characterized in that, The effect size of the first confounding bias includes the effect size of the unmeasured confounding factor parameter on the study outcome parameter and the effect size of the exposure factor parameter on the unmeasured confounding factor parameter. The effect size of the second confounding bias includes the effect size of the unmeasured confounding factor parameter on the negative outcome control parameter and the effect size of the exposure factor parameter on the unmeasured confounding factor parameter. A numerical comparison of the effect sizes of the first and second confounding biases includes: The effect size of the unmeasured confounding factor parameter on the study outcome parameter is compared numerically with the effect size of the unmeasured confounding factor parameter on the negative outcome control parameter.
5. The target estimation analysis method according to claim 1, characterized in that, It includes a master estimation analysis and at least one sensitivity analysis. The results of the sensitivity analysis and the master estimation analysis are used to conduct a comprehensive analysis to obtain the estimation target analysis results.
6. The target estimation analysis method according to claim 1, characterized in that, include: The estimated target was analyzed using multiple negative outcome control parameters to verify the results of the estimated target analysis.
7. The target estimation analysis method according to claim 1, characterized in that, include: The bias type is obtained based on the bias analysis results of the estimated target; The negative outcome control parameters are updated using the bias type to analyze the estimated target and obtain the bias analysis results of the estimated target.
8. A target estimation analysis system, characterized in that, include: The parameter acquisition module is used to acquire the target dataset, which includes exposure factor parameters, study outcome parameters, and preset negative outcome control parameters. The data analysis module is used to analyze the estimated target using the negative outcome control parameter, and to obtain the expected first effect of the exposure factor parameter on the study outcome parameter and the expected second effect of the exposure factor parameter on the negative outcome control parameter. The bias detection module is used to numerically compare the expected values of the first effect and the expected values of the second effect to obtain the bias analysis results of the estimated target.
9. An electronic device, characterized in that, The electronic device includes: Memory, used to store computer programs; A processor for executing a computer program stored in the memory to cause the electronic device to perform the target estimation analysis method as described in any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the target estimation analysis method as described in any one of claims 1 to 7.