Clinical test dynamic grasp monitoring method and device, equipment and storage medium
By acquiring real-time enrollment data, dynamically monitoring statistical power, and generating early warning signals, the problem of lack of dynamic monitoring in clinical trials has been solved, improving trial efficiency and success rate, and enabling real-time adjustment and visualization of statistical power.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- PEKING UNIV
- Filing Date
- 2025-12-18
- Publication Date
- 2026-05-01
AI Technical Summary
Existing technologies lack dynamic monitoring of statistical power during clinical trial enrollment, resulting in low efficiency and high risk of failure, and are unable to promptly identify effect sizes lower than designed values due to deviations in population characteristics.
By acquiring real-time enrollment data, the system dynamically monitors statistical power and generates early warning signals. Based on the early warning signals and user-input simulation parameters, the system simulates enrollment strategies and generates a visual display interface, thereby enabling dynamic monitoring of statistical power.
It enables dynamic monitoring of the control of clinical trials, improves trial efficiency and success rate, timely identifies and adjusts enrollment strategies, and reduces the risk of trial failure.
Smart Images
Figure CN121964018A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of clinical trial data processing technology, and in particular to a method, device, equipment, and storage medium for monitoring the dynamic control of clinical trials. Background Technology
[0002] In the clinical development of drugs or medical devices, clinical trials are a crucial step in verifying their safety and efficacy. Statistical power (also known as statistical efficacy) is a core indicator in the trial design phase, used to measure the likelihood that the trial will successfully detect the true therapeutic effect. Typically, researchers will perform a one-time power calculation based on the hypothesized effect size and sample size before the trial begins.
[0003] However, existing technologies have significant shortcomings in the actual clinical trial enrollment phase. Currently, most studies monitor power at a static, pre-emptive level, lacking effective means for dynamic, real-time monitoring of power during enrollment. Research teams typically rely on manual, periodic data export from electronic data acquisition systems or clinical management systems, followed by manual data processing and calculations using spreadsheet software. This approach is not only inefficient and prone to human error, but more importantly, it fails to achieve continuous tracking and quantitative analysis of power changes as enrollment progresses. Due to the lack of dynamic monitoring, when the characteristics of the enrolled population deviate (for example, initially assuming a certain proportion of severe and mild cases, but the actual proportion of mild cases is much higher than expected), the actual effect size of the trial will be lower than the designed value, causing statistical power to continuously decline without the researchers' awareness. This risk is often only discovered during the final data analysis at the end of the trial, at which point no remedial measures can be taken, ultimately leading to the failure of the entire trial and a huge waste of time and economic resources.
[0004] Therefore, there is an urgent need for a dynamic control method for clinical trials, which can enable dynamic monitoring of the control of clinical trials, thereby improving the efficiency and success rate of clinical trials. Summary of the Invention
[0005] The main objective of this invention is to provide a method, device, equipment, and storage medium for monitoring dynamic power in clinical trials, aiming to solve the technical problem of low efficiency and high failure risk in clinical trials due to the lack of real-time, dynamic statistical power monitoring and early warning mechanisms.
[0006] To achieve the above objectives, the present invention provides a method for monitoring dynamic power in clinical trials, the method comprising the following steps: Acquire real-time enrollment data for clinical trials and determine the statistical power at the current trial progress based on the real-time enrollment data; Monitor the changing trend of the statistical power level, and generate an early warning signal when the statistical power level and / or the changing trend meet preset early warning conditions; Based on the warning signal and the simulation parameters input by the user, the grouping strategy is simulated, and simulation result information is generated; A visual display interface is generated based on the changing trend, the early warning signal, and the simulation results.
[0007] Optionally, the step of determining the statistical power at the current trial progress based on the real-time enrollment data includes: The current weight of each subgroup is determined based on the number of participants in different subgroups in the real-time enrollment data. The weighted success rate is determined based on the preset sub-group power and the current weight; Based on the weighted success rate, the current total sample size, the preset significance level, and the preset threshold success rate, the first confidence component is determined; Based on the pre-set total sample size and pre-set effect size, determine the second confidence component; The statistical power is determined based on the first power component and the second power component.
[0008] Optionally, the step of determining the statistical power based on the first power component and the second power component includes: The current evaluated sample size is compared with the invalid sample size threshold and the valid sample size threshold to obtain the comparison results; The smoothing coefficients of the first and second confidence components are determined based on the comparison results. The first power component and the second power component are fused using the smoothing coefficient to obtain the statistical power.
[0009] Optionally, the step of monitoring the changing trend of the statistical power and generating an early warning signal when the statistical power and / or the changing trend meet preset early warning conditions includes: Determine the slope of the statistical power as a function of the cumulative number of enrollees, and determine the trend of the statistical power based on the slope; The statistical power level is compared with a preset first threshold to obtain a first comparison result; The changing trend is compared with a preset second threshold to obtain a second comparison result; An early warning signal is generated when the first comparison result indicates that the statistical power is less than the preset first threshold and / or the second comparison result indicates that the trend of change is greater than the preset second threshold.
[0010] Optionally, the method further includes: Determine the deviation between the current population distribution and the target population distribution, and determine whether the deviation exceeds a preset structural deviation threshold; If the deviation value exceeds the preset structural deviation threshold, the warning signal is generated.
[0011] Optionally, the step of simulating the grouping strategy based on the warning signal and the simulation parameters input by the user, and generating simulation result information, includes: In response to the warning signal, the system receives simulation parameters input by the user, the simulation parameters including simulated group entry data; The real-time enrollment data and the simulated enrollment data are merged to obtain the simulated total population data; The prediction confidence level is determined based on the simulated total population data, and the prediction confidence level is used as simulation result information.
[0012] Optionally, the step of obtaining real-time enrollment data for clinical trials includes: Structured data is periodically retrieved from the clinical trial data management system via an application programming interface (API). The structured data is validated, and the validated structured data is used as real-time enrollment data for clinical trials.
[0013] Furthermore, to achieve the above objectives, the present invention also proposes a device for monitoring the dynamic control of clinical trials, the device comprising: The data acquisition module is used to acquire real-time enrollment data of clinical trials and determine the statistical power of the current trial progress based on the real-time enrollment data. The signal generation module is used to monitor the changing trend of the statistical power and generate an early warning signal when the statistical power and / or the changing trend meet the preset early warning conditions. The group entry simulation module is used to simulate the group entry strategy based on the warning signal and the simulation parameters input by the user, and generate simulation result information; The information display module is used to generate a visual display interface based on the change trend, the early warning signal, and the simulation result information.
[0014] Furthermore, to achieve the above objectives, the present invention also proposes a clinical trial dynamic control monitoring device, the device comprising: a memory, a processor, and a clinical trial dynamic control monitoring program stored in the memory and executable on the processor, the clinical trial dynamic control monitoring program being configured to implement the steps of the clinical trial dynamic control monitoring method described above.
[0015] Furthermore, to achieve the above objectives, the present invention also proposes a storage medium storing a clinical trial dynamic power monitoring program, wherein the clinical trial dynamic power monitoring program, when executed by a processor, implements the steps of the clinical trial dynamic power monitoring method described above.
[0016] This invention discloses a method for acquiring real-time enrollment data of clinical trials and determining the statistical power at the current trial stage based on the real-time enrollment data; monitoring the changing trend of the statistical power and generating an early warning signal when the statistical power and / or the changing trend meet preset early warning conditions; simulating an enrollment strategy based on the early warning signal and user-input simulation parameters to generate simulation result information; and generating a visual display interface based on the changing trend, the early warning signal, and the simulation result information. Because this invention determines the statistical power at the current trial stage based on real-time enrollment data, automatically generates an early warning signal by monitoring the changing trend of the power, then simulates an enrollment strategy based on the early warning signal and user-input simulation parameters, and finally generates a visual interface by integrating the changing trend, the early warning signal, and the simulation results, compared to existing technologies, this invention achieves dynamic monitoring of the power of clinical trials, thereby improving the efficiency and success rate of clinical trials. Attached Figure Description
[0017] Figure 1 This is a flowchart illustrating the first embodiment of the clinical trial dynamic power monitoring method of the present invention; Figure 2 This is a flowchart illustrating the second embodiment of the clinical trial dynamic power monitoring method of the present invention; Figure 3 This is a flowchart illustrating the third embodiment of the clinical trial dynamic power monitoring method of the present invention; Figure 4 This is a structural block diagram of the first embodiment of the clinical trial dynamic control monitoring device of the present invention; Figure 5 This is a schematic diagram of the structure of a clinical trial dynamic control monitoring device for the hardware operating environment involved in the embodiments of the present invention.
[0018] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation
[0019] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.
[0020] This invention provides a method for monitoring dynamic power in clinical trials, referring to... Figure 1 , Figure 1This is a flowchart illustrating the first embodiment of the clinical trial dynamic control monitoring method of the present invention.
[0021] In this embodiment, the method for monitoring the dynamic power of clinical trials includes steps S10 to S40: Step S10: Obtain real-time enrollment data for the clinical trial and determine the statistical power at the current trial progress based on the real-time enrollment data.
[0022] It should be noted that the executing entity in this embodiment can be a computer server device with data processing, network communication, and program execution functions applied in industrial equipment fault analysis scenarios, such as a server, tablet computer, or personal computer, or an electronic device capable of performing the above functions (such as a clinical trial dynamic control monitoring device). The following uses a system including a clinical trial dynamic control monitoring device (hereinafter referred to as the system) as an example to illustrate this embodiment and the following embodiments.
[0023] It should be understood that real-time enrollment data refers to the latest dataset that is dynamically updated and acquired in near real-time as subjects are continuously recruited and evaluated during a clinical trial. Real-time enrollment data can be automatically obtained from the Electronic Data Collection (EDC) system or Clinical Trial Management System (CTMS) of the clinical trial through an API interface. Real-time enrollment data mainly includes the following structured fields: cumulative number of enrollees, primary endpoint assessment results, and key subgroup variables.
[0024] In practice, structured data can be periodically retrieved from the clinical trial data management system via an application programming interface (API). This structured data is then validated, and the validated data is used as the real-time enrollment data for the clinical trial. To improve system response efficiency and computational stability, the real-time enrollment data can be temporarily stored in a local cache (such as Redis or a local database). During subsequent statistical power calculations, the system prioritizes reading data from the cache.
[0025] It should be added that if the verification fails, a log will be automatically generated in the system background and a warning message will be displayed in the visualization interface.
[0026] It should be understood that validation of structured data can include multiple levels of validation, such as data integrity validation, data type and format validation, logical consistency validation, uniqueness validation, and subgroup coverage validation.
[0027] It's important to note that data integrity checks ensure the data retrieved from the interface contains all the fields necessary for analysis, preventing calculation errors or interruptions due to missing fields. Data type and format checks ensure that the data format of each field matches the system's expected statistical model and calculation logic. Logical consistency checks examine the internal and inter-data logical relationships to identify potential data entry or system transmission errors. Uniqueness checks prevent duplicate data from interfering with calculation results. Subgroup coverage checks ensure that the currently retrieved data covers all preset subgroup classifications, preventing deviations in subsequent calculations due to temporary missing data from a particular subgroup.
[0028] It should be understood that subgroup coverage verification can check whether the structured data contains all the subgroup classifications predefined in the experimental design phase. For example, if the experiment pre-defines three subgroups—mild, moderate, and severe—the system will verify that at least one record for each subgroup exists in the structured data.
[0029] Understandably, the cumulative enrollment can refer to the total number of participants who have successfully signed informed consent and entered the trial up to the current time point. The primary endpoint assessment result can refer to whether the outcome for participants who have completed the primary endpoint assessment was successful (e.g., effective, remission) or unsuccessful (e.g., ineffective, progression). The primary endpoint assessment result is crucial for determining the effective sample size. Key subgroup variables are variables used to distinguish participant characteristics, such as disease severity (mild / moderate / severe), age group, gender, and research center. These variables are key to changes in population structure.
[0030] It should be noted that statistical power refers to the probability that the trial can detect a real therapeutic effect under the current trial conditions (including the characteristics of the currently enrolled population, the observed effect size, and the pre-set sample size), also known as statistical efficacy. In traditional studies, power is calculated only once during the design phase, while the statistical power in this embodiment is dynamic, continuously updated and changing as real-time enrollment data continues to flow in.
[0031] In a specific implementation, the current weight of each subgroup can be determined based on the subgroup variables in the real-time induction data; the weighted success rate can be determined based on the current weight and the preset subgroup success rate; and the statistical power can be determined based on the weighted success rate, the preset threshold success rate, the current total sample size, and the preset significance level.
[0032] The formula for calculating the current weights of each subgroup is as follows: ; In the formula, This represents the current cumulative number of participants in the i-th subgroup, and N represents the current total sample size. Let the current weight of the i-th subgroup be such that it satisfies the following conditions: .
[0033] The formula for calculating the weighted success rate is: ; In the formula, This represents the preset success rate of the i-th subgroup; This represents the weighted success rate, indicating the overall success rate of the prediction given the current population composition.
[0034] The formula for calculating statistical power (normal approximation method) is as follows: ; In the formula, The success rate is set to a preset threshold. To preset the significance level, For standard normal distribution quantiles (e.g., when When =0.025, ≈1.96); The cumulative distribution function represents the standard normal distribution.
[0035] Step S20: Monitor the changing trend of the statistical power level, and generate an early warning signal when the statistical power level and / or the changing trend meet the preset early warning conditions.
[0036] It should be understood that the aforementioned trend in statistical power can refer to the direction, rate, and persistence of statistical power changes over time or with the increase of the cumulative sample size. It is a dynamic and continuous sequence feature, rather than a static single-point feature.
[0037] Understandably, preset warning conditions can refer to rules or logical criteria pre-configured in the system to automatically trigger risk alerts. They define the circumstances under which a clinical trial's status changes from normal to requiring attention.
[0038] Accordingly, the warning signal can refer to risk indication information automatically generated by the system when the aforementioned preset warning conditions are met. The warning signal may include at least the warning type, the event in which the warning occurred, and warning-related data, etc., but this embodiment does not impose any limitations on this.
[0039] Step S30: Based on the warning signal and the simulation parameters input by the user, perform grouping strategy simulation and generate simulation result information.
[0040] It should be noted that, in response to the warning signal, the system can receive simulation parameters input by the user, including simulated enrollment data; merge the real-time enrollment data with the simulated enrollment data to obtain simulated total population data; determine the prediction power based on the simulated total population data, and use the prediction power as simulation result information.
[0041] It should be understood that simulation parameters refer to a set of variables that users (such as researchers) input into the system to describe potential future enrollment scenarios in order to predict the effects of different enrollment strategies. These parameters are hypothetical in nature and do not change the actual experimental data.
[0042] It's important to explain that simulated enrollment data can be hypothetical plans set up by users to test specific enrollment strategies, outlining the future recruitment numbers for each subgroup. It serves as a bridge between current problems (early warnings) and future predictions (simulation results), enabling researchers to quantitatively assess the potential effects of different adjustment strategies.
[0043] Furthermore, enrollment strategy simulation refers to the process by which the system, based on simulation parameters provided by the user, merges current real data with hypothesized future data (i.e., simulation parameters) in a virtual environment, and quickly calculates the statistical power that the experiment may ultimately achieve under this scenario.
[0044] In practical implementation, in response to the aforementioned warning signal, researchers can use a visual interactive control (slider) to simulate the impact of different new enrollment structures on statistical power without interrupting the actual experimental progress, thus assisting in evaluating the feasibility and potential effects of adjustment strategies.
[0045] Understandably, the system automatically calculates the current weights of each subgroup after each simulation. Weighted success rate In addition to predictive confidence, this module is a decision support tool and does not automatically change the experimental protocol settings, which complies with ethical and regulatory requirements.
[0046] Step S40: Generate a visual display interface based on the changing trend, the early warning signal, and the simulation result information.
[0047] It should be noted that the visualization interface may include a Power main chart, a stacked bar chart of subgroup composition, a simulation curve chart, and a chart information prompt area.
[0048] It should be understood that the Power main line chart can be generated based on changing trends, with the horizontal axis representing the cumulative number of enrollees and the vertical axis representing the Power value. The line automatically transitions smoothly based on the combination of actual and predicted samples, and generates alert information based on warning signals. The chart can support the overlay of red / orange / blue warning lines for alerts.
[0049] The stacked bar chart of subgroups can intuitively display the proportion of different subgroups in the current population at each time point, reflecting the actual impact of the current population distribution on statistical power. It can also support switching of hierarchical dimensions (such as severity, gender, center). The total height of each bar chart reflects the main line corresponding to the current statistical power.
[0050] The simulated curve can be a predicted power curve generated based on the simulation results. Based on the predicted power curve, the trend of changes in confidence before and after adjustment can be intuitively compared.
[0051] The chart information display area can be fixed at the top of the visualization interface to display the core parameters of the research, such as the threshold success rate, planned sample size, current number of evaluations, and efficacy status (achieved / critical / early warning), thereby enhancing the monitoring center's ability to control risks.
[0052] This embodiment discloses a method for acquiring real-time enrollment data of clinical trials and determining the statistical power at the current trial progress based on the real-time enrollment data; monitoring the changing trend of the statistical power and generating an early warning signal when the statistical power and / or the changing trend meet preset early warning conditions; simulating an enrollment strategy based on the early warning signal and user-input simulation parameters to generate simulation result information; and generating a visual display interface based on the changing trend, the early warning signal, and the simulation result information. Because this embodiment determines the statistical power at the current trial progress based on real-time enrollment data, automatically generates an early warning signal by monitoring the changing trend of the power, then simulates an enrollment strategy based on the early warning signal and user-input simulation parameters, and finally generates a visual interface by integrating the changing trend, the early warning signal, and the simulation results, compared to existing technologies, this embodiment achieves dynamic monitoring of the power of clinical trials, thereby improving the efficiency and success rate of clinical trials.
[0053] refer to Figure 2 , Figure 2 This is a flowchart illustrating the second embodiment of the clinical trial dynamic control monitoring method of the present invention.
[0054] Based on the first embodiment described above, in this embodiment, step S10 includes steps S101 to S105: Step S101: Determine the current weight of each subgroup based on the number of participants in different subgroups in the real-time enrollment data.
[0055] Step S102: Determine the weighted success rate based on the preset subgroup power and the current weight.
[0056] Step S103: Based on the weighted success rate, the current total sample size, the preset significance level, and the preset threshold success rate, determine the first confidence component.
[0057] Step S104: Determine the second power component based on the preset total sample size and preset effect size.
[0058] Step S105: Determine the statistical power based on the first power component and the second power component.
[0059] It should be noted that the first power component, Power_current, is calculated based on currently enrolled subjects who have completed the primary endpoint assessment. It is calculated directly using a statistical formula (i.e., the formula corresponding to the normal approximation) based on the real-time weighted success rate, the current total sample size, the preset significance level, and the preset threshold success rate. It reflects the probability of success at the immediate end of the trial, given the currently available sample; that is, it reflects the probability of success under the current enrollment conditions.
[0060] The second power component, Power_end, is calculated based on the ideal state at the completion of the entire experimental plan. It uses the pre-set total sample size and pre-set effect size (i.e., the true treatment effect assumed in the protocol) as the benchmark, and is obtained by statistical formula according to the expected power at the design stage. It represents the theoretical power if subsequent enrollment continues exactly according to the protocol and the assumed effect size remains unchanged, reflecting the probability of success when the experiment is executed perfectly as originally planned.
[0061] It should be understood that determining the statistical power based on the first and second power components avoids drastic fluctuations in power due to extremely small sample sizes in the early stages of the experiment, and also prevents ignoring deviations already present in the actual data while only considering theoretical values, thus improving the accuracy and reliability of the statistical power. This dual-component fusion mechanism cleverly solves the evaluation challenges at different stages of the experiment, making risk identification both sensitive and robust.
[0062] In practice, when the first confidence component is significantly lower than the second confidence component, the system can immediately identify the risk that the actual effect is lower than the hypothesis or that the population structure is unbalanced, triggering an early warning and providing researchers with a time window to adjust enrollment strategies, extend recruitment, or modify the target sample size.
[0063] To further improve the accuracy of statistical power and prevent abrupt changes in statistical power, the current evaluated sample size can be compared with the invalid sample size threshold and the valid sample size threshold to obtain the comparison result; the smoothing coefficients of the first power component and the second power component can be determined based on the comparison result; the first power component and the second power component can be fused using the smoothing coefficients to obtain the statistical power.
[0064] It should be added that the formula for fusing the first confidence component and the second confidence component to obtain the statistical confidence is as follows: ; In the formula, Power_current represents the first confidence component, and Power_end represents the second confidence component. This represents the smoothing coefficient.
[0065] ; in, This indicates the current sample size that has been evaluated. Indicates the threshold for invalid sample size. This represents the effective sample size threshold.
[0066] This embodiment discloses a method for determining the current weight of each subgroup based on the number of participants in different subgroups from the real-time enrollment data; determining a weighted success rate based on a preset subgroup success rate and the current weight; determining a first confidence component based on the weighted success rate, the current total sample size, a preset significance level, and a preset threshold success rate; determining a second confidence component based on a preset planned total sample size and a preset effect size; and determining statistical confidence based on the first confidence component and the second confidence component. Because this embodiment determines the first confidence component based on the weighted success rate, the current total sample size, the preset significance level, and the preset threshold success rate, then determines the second confidence component based on the preset planned total sample size and the preset effect size, and finally determines the statistical confidence based on the first and second confidence components, compared to existing technologies, this embodiment improves the accuracy and reliability of statistical confidence, thereby enhancing the early detection and resistance to interference in risk identification.
[0067] refer to Figure 3 , Figure 3 This is a flowchart illustrating the third embodiment of the clinical trial dynamic control monitoring method of the present invention.
[0068] Based on the above embodiments, in this embodiment, step S20 further includes steps S201 to S204: Step S201: Determine the slope of the statistical power as the cumulative number of enrollees changes, and determine the trend of the statistical power based on the slope.
[0069] Step S202: Compare the statistical power with a preset first threshold to obtain a first comparison result.
[0070] Step S203: Compare the changing trend with a preset second threshold to obtain a second comparison result.
[0071] Step S204: When the first comparison result indicates that the statistical power is less than the preset first threshold and / or the second comparison result indicates that the trend of change is greater than the preset second threshold, an early warning signal is generated.
[0072] In a specific implementation, the deviation between the current population distribution and the target population distribution can be determined, and it can be determined whether the deviation exceeds a preset structural deviation threshold. If the deviation exceeds the preset structural deviation threshold, the warning signal is generated.
[0073] It should be understood that the current population distribution (from real-time enrollment data) can refer to the actual proportion of each subgroup among the successfully enrolled subjects at the current point in time in the clinical trial. The target population distribution (from the clinical trial protocol or study design document) can refer to the ideal population composition proportion that researchers pre-set based on scientific hypotheses and statistical requirements during the clinical trial design phase.
[0074] For example, a risk warning is triggered when the statistical confidence level is less than a preset first threshold (e.g., 50%), and a corresponding warning signal is generated; a data fluctuation warning is triggered when the trend of change is greater than a preset second threshold, and a corresponding warning signal is generated; a structural warning is triggered when the deviation between the current population distribution and the target population distribution exceeds a preset structural deviation threshold, and a corresponding warning signal is generated.
[0075] This embodiment discloses determining the slope of the statistical power as a function of the cumulative number of enrollees, and determining the trend of the statistical power based on the slope; comparing the statistical power with a preset first threshold to obtain a first comparison result; comparing the trend with a preset second threshold to obtain a second comparison result; and generating an early warning signal when the first comparison result indicates that the statistical power is less than the preset first threshold and / or the second comparison result indicates that the trend is greater than the preset second threshold. Because this embodiment generates an early warning signal based on the first comparison result of the statistical power and the preset first threshold and the second comparison result of the trend with the preset second threshold, compared to existing technologies, this embodiment achieves multi-dimensional early warning triggering, enabling more timely, reliable, and intelligent monitoring of the risk of clinical trial failure.
[0076] Furthermore, this embodiment of the invention also proposes a storage medium storing a clinical trial dynamic power monitoring program, which, when executed by a processor, implements the steps of the clinical trial dynamic power monitoring method described above.
[0077] Reference Figure 4 , Figure 4 This is a structural block diagram of the first embodiment of the clinical trial dynamic control monitoring device of the present invention.
[0078] like Figure 4 As shown, the clinical trial dynamic control monitoring device proposed in this embodiment of the invention includes: a data acquisition module 501, a signal generation module 502, an enrollment simulation module 503, and an information display module 504.
[0079] The data acquisition module 501 is used to acquire real-time enrollment data of clinical trials and determine the statistical power of the current trial progress based on the real-time enrollment data.
[0080] The signal generation module 502 is used to monitor the changing trend of the statistical power and generate an early warning signal when the statistical power and / or the changing trend meet the preset early warning conditions.
[0081] The group entry simulation module 503 is used to simulate the group entry strategy based on the warning signal and the simulation parameters input by the user, and generate simulation result information.
[0082] The information display module 504 is used to generate a visual display interface based on the change trend, the early warning signal, and the simulation result information.
[0083] The data acquisition module 501 is also used to periodically acquire structured data from the clinical trial data management system through an application programming interface; to perform verification processing on the structured data; and to use the verified structured data as real-time enrollment data for the clinical trial.
[0084] The enrollment simulation module 503 is further configured to respond to the warning signal by receiving simulation parameters input by the user, the simulation parameters including simulated enrollment data; merging the real-time enrollment data with the simulated enrollment data to obtain simulated total population data; determining the prediction power based on the simulated total population data, and using the prediction power as simulation result information.
[0085] This device embodiment discloses the following: acquiring real-time enrollment data of clinical trials and determining the statistical power at the current trial progress based on the real-time enrollment data; monitoring the changing trend of the statistical power and generating an early warning signal when the statistical power and / or the changing trend meet preset early warning conditions; simulating an enrollment strategy based on the early warning signal and user-input simulation parameters to generate simulation result information; and generating a visual display interface based on the changing trend, the early warning signal, and the simulation result information. Because this device embodiment determines the statistical power at the current trial progress based on real-time enrollment data, automatically generates an early warning signal by monitoring the changing trend of the power, then simulates an enrollment strategy based on the early warning signal and user-input simulation parameters, and finally generates a visual interface by integrating the changing trend, the early warning signal, and the simulation results, compared to existing technologies, this device embodiment achieves dynamic monitoring of the power of clinical trials, thereby improving the efficiency and success rate of clinical trials.
[0086] Based on the first embodiment of the clinical trial dynamic control monitoring device of the present invention, a second embodiment of the clinical trial dynamic control monitoring device of the present invention is proposed.
[0087] In this embodiment, the data acquisition module 501 is further configured to: determine the current weight of each subgroup based on the number of participants in different subgroups in the real-time enrollment data; determine the weighted success rate based on a preset subgroup success rate and the current weight; determine a first power component based on the weighted success rate, the current total sample size, a preset significance level, and a preset threshold success rate; determine a second power component based on a preset planned total sample size and a preset effect size; and determine statistical power based on the first power component and the second power component.
[0088] The data acquisition module 501 is further configured to compare the current evaluated sample size with the invalid sample size threshold and the valid sample size threshold to obtain a comparison result; determine the smoothing coefficients of the first power component and the second power component based on the comparison result; and fuse the first power component and the second power component using the smoothing coefficients to obtain statistical power.
[0089] This embodiment of the device determines a first confidence component based on the weighted success rate, the current total sample size, a preset significance level, and a preset threshold success rate. Then, it determines a second confidence component based on the preset planned total sample size and a preset effect size. Finally, it determines the statistical confidence based on the first and second confidence components. Compared with the prior art, this embodiment of the device improves the accuracy and reliability of the statistical confidence, thereby enhancing the early detection and anti-interference capabilities of risk identification.
[0090] Based on the above embodiments of the clinical trial dynamic control monitoring device of the present invention, a third embodiment of the clinical trial dynamic control monitoring device of the present invention is proposed.
[0091] In this embodiment, the signal generation module 502 is further configured to determine the slope of the statistical power as the cumulative number of enrollees changes, and determine the trend of the statistical power based on the slope; compare the statistical power with a preset first threshold to obtain a first comparison result; compare the trend of change with a preset second threshold to obtain a second comparison result; and generate a warning signal when the first comparison result indicates that the statistical power is less than the preset first threshold and / or the second comparison result indicates that the trend of change is greater than the preset second threshold.
[0092] The signal generation module 502 is further configured to determine the deviation value between the current population distribution and the target population distribution, and to determine whether the deviation value exceeds a preset structural deviation threshold; if the deviation value exceeds the preset structural deviation threshold, then the warning signal is generated.
[0093] This device embodiment generates an early warning signal based on a first comparison result of statistical power and a preset first threshold and a second comparison result of the trend of change and a preset second threshold. Compared with the prior art, this device embodiment realizes multi-dimensional early warning triggering, and realizes more timely, reliable and intelligent monitoring of the risk of clinical trial failure.
[0094] Other embodiments or specific implementations of the clinical trial dynamic control monitoring device of the present invention can be referred to the above-described method embodiments, and will not be repeated here.
[0095] This application provides a clinical trial dynamic control monitoring device, which 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 to enable the at least one processor to perform the clinical trial dynamic control monitoring method in the above embodiment 1.
[0096] The following is for reference. Figure 5The diagram illustrates a structural schematic suitable for implementing the clinical trial dynamic control monitoring device in the embodiments of this application. The clinical trial dynamic control monitoring device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The clinical trial dynamic control monitoring device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments in this application.
[0097] like Figure 5 As shown, the clinical trial dynamic control monitoring device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.) that can perform various appropriate actions and processes according to a program stored in a read-only memory 1002 or a program loaded from a storage device 1003 into a random access memory 1004. The random access memory 1004 also stores various programs and data required for the operation of the clinical trial dynamic control monitoring device. The processing unit 1001, the read-only memory 1002, and the random access memory 1004 are interconnected via a bus 1005. An input / output interface 1006 is also connected to the bus. Typically, the following systems can be connected to the input / output interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the clinical trial dynamic control monitoring device to communicate wirelessly or wiredly with other devices to exchange data. While the figure shows clinical trial dynamic control monitoring devices with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.
[0098] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from read-only memory 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.
[0099] The clinical trial dynamic power monitoring device provided in this application, employing the clinical trial dynamic power monitoring method described in the above embodiments, can solve the technical problems of low trial efficiency and high failure risk caused by the lack of real-time, dynamic statistical power monitoring and early warning mechanisms in clinical trials. Compared with the prior art, the beneficial effects of the clinical trial dynamic power monitoring device provided in this application are the same as those of the clinical trial dynamic power monitoring method provided in the above embodiments, and other technical features of this clinical trial dynamic power monitoring device are the same as those disclosed in the previous embodiment method, and will not be repeated here.
[0100] It should be understood that the various parts disclosed in this application can be implemented using 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 suitable manner in one or more embodiments or examples.
[0101] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
[0102] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.
[0103] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.
[0104] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this 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. This computer software product is stored in a storage medium (such as read-only memory / random access memory, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.
[0105] The above are merely preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the protection scope of the present invention.
Claims
1. A method for monitoring dynamic power in clinical trials, characterized in that, The method includes: Acquire real-time enrollment data for clinical trials and determine the statistical power at the current trial progress based on the real-time enrollment data; Monitor the changing trend of the statistical power level, and generate an early warning signal when the statistical power level and / or the changing trend meet preset early warning conditions; Based on the warning signal and the simulation parameters input by the user, the grouping strategy is simulated, and simulation result information is generated; A visual display interface is generated based on the changing trend, the early warning signal, and the simulation results.
2. The method for monitoring dynamic power of clinical trials as described in claim 1, characterized in that, The step of determining the statistical power at the current trial progress based on the real-time enrollment data includes: The current weight of each subgroup is determined based on the number of participants in different subgroups in the real-time enrollment data. The weighted success rate is determined based on the preset sub-group power and the current weight; Based on the weighted success rate, the current total sample size, the preset significance level, and the preset threshold success rate, the first confidence component is determined; Based on the pre-set total sample size and pre-set effect size, determine the second confidence component; The statistical power is determined based on the first power component and the second power component.
3. The method for monitoring dynamic power of clinical trials as described in claim 2, characterized in that, The step of determining statistical power based on the first power component and the second power component includes: The current evaluated sample size is compared with the invalid sample size threshold and the valid sample size threshold to obtain the comparison results; The smoothing coefficients of the first and second confidence components are determined based on the comparison results. The first power component and the second power component are fused using the smoothing coefficient to obtain the statistical power.
4. The method for monitoring dynamic power of clinical trials as described in claim 1, characterized in that, The step of monitoring the changing trend of the statistical power and generating an early warning signal when the statistical power and / or the changing trend meet preset early warning conditions includes: Determine the slope of the statistical power as a function of the cumulative number of enrollees, and determine the trend of the statistical power based on the slope; The statistical power level is compared with a preset first threshold to obtain a first comparison result; The changing trend is compared with a preset second threshold to obtain a second comparison result; An early warning signal is generated when the first comparison result indicates that the statistical power is less than the preset first threshold and / or the second comparison result indicates that the trend of change is greater than the preset second threshold.
5. The method for monitoring dynamic power of clinical trials as described in claim 4, characterized in that, The method further includes: Determine the deviation between the current population distribution and the target population distribution, and determine whether the deviation exceeds a preset structural deviation threshold; If the deviation value exceeds the preset structural deviation threshold, the warning signal is generated.
6. The method for monitoring dynamic power of clinical trials as described in claim 1, characterized in that, The step of simulating the grouping strategy based on the warning signal and the simulation parameters input by the user, and generating simulation result information, includes: In response to the warning signal, the system receives simulation parameters input by the user, the simulation parameters including simulated group entry data; The real-time enrollment data and the simulated enrollment data are merged to obtain the simulated total population data; The prediction confidence level is determined based on the simulated total population data, and the prediction confidence level is used as simulation result information.
7. The method for monitoring dynamic power of clinical trials as described in any one of claims 1-6, characterized in that, The steps for obtaining real-time enrollment data from clinical trials include: Structured data is periodically retrieved from the clinical trial data management system via an application programming interface (API). The structured data is validated, and the validated structured data is used as real-time enrollment data for clinical trials.
8. A device for monitoring the dynamic control of clinical trials, characterized in that, The device includes: The data acquisition module is used to acquire real-time enrollment data of clinical trials and determine the statistical power of the current trial progress based on the real-time enrollment data. The signal generation module is used to monitor the changing trend of the statistical power and generate an early warning signal when the statistical power and / or the changing trend meet the preset early warning conditions. The group entry simulation module is used to simulate the group entry strategy based on the warning signal and the simulation parameters input by the user, and generate simulation result information; The information display module is used to generate a visual display interface based on the change trend, the early warning signal, and the simulation result information.
9. A device for monitoring the dynamic control of clinical trials, characterized in that, The device includes: a memory, a processor, and a clinical trial dynamic power monitoring program stored in the memory and executable on the processor, the clinical trial dynamic power monitoring program being configured to implement the steps of the clinical trial dynamic power monitoring method as described in any one of claims 1 to 7.
10. A storage medium, characterized in that, The storage medium stores a clinical trial dynamic power monitoring program, which, when executed by a processor, implements the steps of the clinical trial dynamic power monitoring method as described in any one of claims 1 to 7.