Adaptive Randomization-Based Clinical Trial Allocation Method, System, Device, and Storage Medium

Abstract

The present invention discloses a clinical trial allocation method, system, device and storage medium based on adaptive randomization. The method includes: randomly allocating subjects to each treatment group according to a preset ratio, and obtaining the current efficacy data of each treatment group; determining the posterior probability of each treatment group based on the current efficacy data of each treatment group, and adjusting the random allocation probability according to the posterior probability; determining the conditional test power of each treatment group, and performing a preset resource optimization strategy on each treatment group according to the conditional test power to obtain the test result; determining the current posterior probability of each treatment group according to the test result, and determining the optimal treatment group based on the current posterior probability. Since the present invention dynamically adjusts the random allocation probability of each treatment group during the trial process, performs a preset resource optimization strategy on each treatment group according to the conditional test power, and determines the target treatment group based on the test result, it optimizes the allocation of subjects in the trial and improves the reliability and accuracy of the test result.

Description

Technical Field

[0001] The present invention relates to the technical field of clinical trial design and statistics, and particularly to a clinical trial allocation method, system, device and storage medium based on adaptive randomization. Background Art

[0002] In traditional clinical trial designs, subjects are usually randomly assigned to different treatment groups at a fixed ratio (such as 1:1:1...) to ensure the fairness and scientific nature of the trial. However, this fixed randomization method may result in a large number of subjects receiving less effective or ineffective treatments. Especially in multi-arm clinical trials, some treatment groups may show poor efficacy in the early stage of the trial, but still need to continue recruiting a large number of patients, leading to low utilization rate of trial resources and increasing the risk of patients receiving ineffective treatments.

[0003] For this reason, the adaptive randomization (AR) method has been proposed, in which the allocation probability of subjects is dynamically adjusted based on mid-term data, so that the treatment plan with better efficacy is more likely to obtain newly enrolled patients, thereby improving the trial efficiency and being more reasonable ethically. However, the existing adaptive randomization methods (such as Bayesian adaptive randomization, "random winner rule", etc.) have the following problems: 1. Unstable early data: Due to the small sample size, the early trial data may have large random fluctuations, resulting in some methods (such as randomization based entirely on posterior probability) may "stick" to a certain treatment group, affecting the fairness of the trial. 2. Extreme allocation risk: Some adaptive randomization methods may cause some treatment groups to be quickly eliminated, making the trial data overly biased towards some treatment groups, affecting the reliability of the final statistical inference. 3. Optimization of resource utilization problem: When some treatment groups face elimination due to poor efficacy, whether to reallocate their sample sizes and how to optimize the allocation of subjects to make the trial both efficient and fair is a problem that needs in-depth study.

[0004] Therefore, there is an urgent need for a clinical trial allocation method based on adaptive randomization, which can enhance the trial adaptability, optimize the allocation of subjects, and thus improve the reliability and accuracy of the trial results. Summary of the Invention

[0005] The main purpose of the present invention is to provide a clinical trial allocation method, system, device and storage medium based on adaptive randomization, aiming to solve the technical problem in the prior art that the resource allocation in the clinical trial stage is not flexible, resulting in insufficient reliability and accuracy of the trial results.

[0006] To achieve the above purpose, the present invention provides a clinical trial allocation method based on adaptive randomization, and the method includes the following steps:

[0007] Randomly allocate the subjects to each treatment group according to a preset ratio, and obtain the current efficacy data of each said treatment group;

[0008] Determine the posterior probability of each said treatment group based on the current efficacy data of each said treatment group, and adjust the random allocation probability according to the posterior probability;

[0009] Determine the conditional test power of each said treatment group, and perform a preset resource optimization strategy on each said treatment group according to the conditional test power to obtain the test results;

[0010] Determine the current posterior probability of each said treatment group according to the test results, and determine the best treatment group of the target treatment group based on the current posterior probability.

[0011] Optionally, the step of determining the conditional test power of each said treatment group, and performing a preset resource optimization strategy on each said treatment group according to the conditional test power to obtain the test results includes:

[0012] Determine the conditional test power of each said treatment group according to the conditional test power calculation formula;

[0013] Compare the conditional test power of each said treatment group with a first preset threshold and a second preset threshold to obtain a comparison result;

[0014] Perform a preset resource optimization strategy on each said treatment group according to the comparison result to obtain the test results, and the preset resource optimization strategy includes no reallocation of the sample size and randomization probability compensation.

[0015] Optionally, the step of performing a preset resource optimization strategy on each said treatment group according to the comparison result to obtain the test results includes:

[0016] If the comparison result indicates that the conditional test power of the treatment group is greater than the first preset threshold or the conditional test power of the treatment group is less than the second preset threshold, terminate the recruitment of subjects in the treatment group, and the first preset threshold is greater than the second preset threshold;

[0017] Take the treatment group corresponding to the terminated subject recruitment as the termination group, no longer reallocate the sample size of the termination group, and obtain the corresponding test results.

[0018] Optionally, the step of performing a preset resource optimization strategy on each said treatment group according to the comparison result to obtain the test results includes:

[0019] If the comparison result indicates that the conditional test power of the treatment group is less than the first preset threshold and greater than the second preset threshold, determine whether the conditional test power of the treatment group is within a preset invalid interval;

[0020] If the conditional test power of the treatment group is within the preset null interval, then within the preset null interval, perform randomized probability compensation on the treatment group with the worst efficacy, and obtain the corresponding test results.

[0021] Optionally, the formula for the conditional test power is:

[0022] ;

[0023] In the formula, represents the standardized test statistic of treatment group k , is the critical value of the significance test, represents the conditional test power of treatment group k , represents the test data that has been collected currently.

[0024] Optionally, the step of determining the posterior probability of each treatment group based on the current efficacy data of each treatment group and adjusting the random allocation probability according to the posterior probability includes:

[0025] Determine the posterior probability of each treatment group based on the current efficacy data of each treatment group and the posterior probability calculation formula;

[0026] Determine the random allocation probability of each treatment group according to the posterior probability and the random allocation probability calculation formula;

[0027] Adjust the random allocation probability of each treatment group based on the upper and lower limits of the preset random allocation probability to obtain the adjusted random allocation probability of each treatment group;

[0028] The posterior probability calculation formula is:

[0029] ;

[0030] In the formula, represents the efficacy parameter of treatment group k, represents the test data that has been collected currently, is the marker variable indicating that the efficacy of treatment group k is better than that of the remaining treatment groups;

[0031] The random allocation probability calculation formula is:

[0032] ;

[0033] In the formula, the exponent c is used to control the degree of randomization, is the marker variable indicating that the efficacy of treatment group j is better than that of the remaining treatment groups, represents the random allocation probability of treatment group k.

[0034] Optionally, the step of randomly allocating the subjects to each treatment group according to a preset ratio and obtaining the current efficacy data of each treatment group includes:

[0035] Determining the sample size of the subjects at the initial stage of the trial according to the trial scale and the preset between-group difference;

[0036] Randomly allocating the corresponding subjects to each treatment group according to the preset ratio based on the sample size of the subjects, and obtaining the current efficacy data of each treatment group.

[0037] In addition, to achieve the above object, the present invention also provides a clinical trial allocation system based on adaptive randomization, and the system includes:

[0038] An experiment allocation module, configured to randomly allocate subjects to each treatment group according to a preset ratio and obtain the current efficacy data of each treatment group;

[0039] A probability adjustment module, configured to determine the posterior probability of each treatment group based on the current efficacy data of each treatment group and adjust the random allocation probability according to the posterior probability;

[0040] A resource optimization module, configured to determine the conditional test power of each treatment group and execute a preset resource optimization strategy on each treatment group according to the conditional test power to obtain the test result;

[0041] A treatment recommendation module, configured to determine the current posterior probability of each treatment group according to the test result and determine the best treatment group based on the current posterior probability.

[0042] In addition, to achieve the above object, the present invention also provides a clinical trial allocation device based on adaptive randomization, and the device includes: a memory, a processor, and an adaptive randomization-based clinical trial allocation program stored on the memory and executable on the processor, and the adaptive randomization-based clinical trial allocation program is configured to implement the steps of the adaptive randomization-based clinical trial allocation method as described above.

[0043] In addition, to achieve the above object, the present invention also provides a storage medium, and an adaptive randomization-based clinical trial allocation program is stored on the storage medium, and when the adaptive randomization-based clinical trial allocation program is executed by a processor, the steps of the adaptive randomization-based clinical trial allocation method as described above are implemented.

[0044] The present invention discloses randomly allocating subjects to each treatment group according to a preset ratio, and obtaining the current efficacy data of each treatment group; determining the posterior probability of each treatment group based on the current efficacy data of each treatment group, and adjusting the random allocation probability according to the posterior probability; determining the conditional test power of each treatment group, and performing a preset resource optimization strategy on each treatment group according to the conditional test power to obtain a test result; determining the current posterior probability of each treatment group according to the test result, and determining the optimal treatment group based on the current posterior probability. Since the present invention dynamically adjusts the random allocation probability of each treatment group during the test process, performs a preset resource optimization strategy on each treatment group according to the conditional test power, and finally determines the current posterior probability of each treatment group according to the test result, and determines the optimal treatment group based on the current posterior probability, compared with the prior art, the present invention optimizes the allocation of subjects during the test process, thereby improving the reliability and accuracy of the test result. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 is a schematic flowchart of the first embodiment of the clinical trial allocation method based on adaptive randomization of the present invention;

[0046] Figure 2 is a schematic flowchart of the second embodiment of the clinical trial allocation method based on adaptive randomization of the present invention;

[0047] Figure 3 is a schematic flowchart of the third embodiment of the clinical trial allocation method based on adaptive randomization of the present invention;

[0048] Figure 4 is a structural block diagram of the first embodiment of the clinical trial allocation system based on adaptive randomization of the present invention;

[0049] Figure 5 is a schematic structural diagram of the device for clinical trial allocation based on adaptive randomization in the hardware operating environment involved in the embodiment solution of the present invention.

[0050] The implementation, functional features and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0051] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0052] The embodiment of the present invention provides a clinical trial allocation method based on adaptive randomization. Refer to Figure 1 , Figure 1 is a schematic flowchart of the first embodiment of the clinical trial allocation method based on adaptive randomization of the present invention.

[0053] In this embodiment, the adaptive randomization-based clinical trial allocation method includes steps S10 to S40:

[0054] Step S10: Randomly allocate the subjects to each treatment group according to a preset ratio, and obtain the current efficacy data of each treatment group.

[0055] It should be noted that the execution subject of this embodiment can be a computer server device with data processing, network communication, and program running functions applied to the clinical trial design scenario, such as a server, a tablet computer, a personal computer, etc., or an electronic device, an adaptive randomization-based clinical trial allocation device, etc. that can implement the above functions. Hereinafter, the adaptive randomization-based clinical trial allocation device will be taken as an example to illustrate this embodiment and the following embodiments.

[0056] It should be understood that the above preset ratio can be custom-set, and this embodiment does not limit it. For example, evenly distribute it to each treatment group according to the preset ratio of 1:1:1..., to ensure good comparability and stability of the data in the initial stage of the trial.

[0057] It can be understood that the sample size in the initial stage of the trial can be set according to the trial scale and the expected size of the between-group difference. For example, the first 50 patients (i.e., subjects) are randomly allocated evenly.

[0058] In a specific implementation, in a clinical trial, the sample size of the subjects in the initial stage of the trial can be determined according to the trial scale and the preset between-group difference; based on the sample size of the subjects, the corresponding subjects are randomly allocated to each treatment group according to a preset ratio, and the current efficacy data of each treatment group are obtained.

[0059] It should be explained that the current efficacy data can include but are not limited to binary response rate, continuous effect value, survival analysis data, etc.

[0060] Step S20: Determine the posterior probability of each treatment group based on the current efficacy data of each treatment group, and adjust the random allocation probability according to the posterior probability.

[0061] In a specific implementation, the posterior probability of each treatment group can be determined based on the current efficacy data of each treatment group and the posterior probability calculation formula.

[0062] The posterior probability calculation formula is:

[0063] ;

[0064] In the formula, represents the efficacy parameter of treatment group k, represents the currently collected trial data, It is a marker variable indicating that the efficacy of treatment group k is better than that of the remaining treatment groups, and Pr represents the probability function.

[0065] It should be noted that the above random allocation probability refers to the dynamic probability that newly enrolled subjects in a clinical trial are assigned to different treatment groups. Different from the traditional fixed ratio (such as 1:1:1), in this embodiment, the allocation probability of each group is dynamically adjusted according to the current efficacy data, so that the treatment group with better efficacy obtains a higher allocation probability, while avoiding extreme allocations.

[0066] In a specific implementation, the random allocation probability can be adjusted according to the random allocation probability calculation formula and the posterior probability:

[0067] The random allocation probability calculation formula is:

[0068] ;

[0069] In the formula, the exponent c is used to control the degree of randomization, is a marker variable indicating that the efficacy of treatment group j is better than that of the remaining treatment groups, represents the random allocation probability of treatment group k.

[0070] Step S30: Determine the conditional test power of each of the treatment groups, and perform a preset resource optimization strategy on each of the treatment groups according to the conditional test power to obtain the test results.

[0071] It should be noted that it is possible to determine whether to terminate the recruitment of subjects in each of the treatment groups through the conditional test power of each of the treatment groups. For example, if the conditional test power of a certain treatment group is higher than a certain preset threshold (such as 0.90), or lower than a certain preset threshold (such as 0.10), then the recruitment of subjects in that treatment group is stopped.

[0072] It should be explained that the above preset resource optimization strategy includes no reallocation of the sample size and randomization probability compensation.

[0073] In a specific implementation, if the efficacy of a certain treatment group k is significantly lower than that of the control group (or all other treatment groups), and it is impossible to meet the established efficacy criteria in the remaining trials, then the recruitment of subjects in that treatment group is terminated:

[0074]

[0075] In the formula, is the efficacy of the control group, δ is the preset clinically significant between-group difference, α is the statistical confidence level (such as 0.01).

[0076] Step S40: Determine the current posterior probability of each treatment group according to the test results, and determine the optimal treatment group based on the current posterior probability.

[0077] It should be noted that at the end of the trial, the optimal treatment group is recommended based on the current posterior probability of each treatment group: where γ is the treatment selection threshold (e.g., 0.95).

[0078] It can be understood that the significance of the optimal treatment group is to ensure that the selected treatment plan is significant and clinically meaningful in terms of efficacy through scientific and statistical methods, so as to provide a reliable basis for the final decision of the clinical trial, optimize resource allocation, and improve the treatment effect and safety of patients.

[0079] This embodiment discloses randomly allocating subjects to each treatment group according to a preset ratio and obtaining the current efficacy data of each treatment group; determining the posterior probability of each treatment group based on the current efficacy data of each treatment group, and adjusting the random allocation probability according to the posterior probability; determining the conditional test power of each treatment group, and performing a preset resource optimization strategy on each treatment group according to the conditional test power to obtain test results; determining the current posterior probability of each treatment group according to the test results, and determining the optimal treatment group based on the current posterior probability. Since this embodiment dynamically adjusts the random allocation probability of each treatment group during the trial process, performs a preset resource optimization strategy on each treatment group according to the conditional test power, finally determines the current posterior probability of each treatment group according to the test results, and determines the optimal treatment group based on the current posterior probability, compared with the prior art, this embodiment optimizes the allocation of subjects during the trial, thereby improving the reliability and accuracy of the test results.

[0080] Reference Figure 2 , Figure 2 is a schematic flowchart of the second embodiment of the clinical trial allocation method based on adaptive randomization of the present invention.

[0081] Based on the above first embodiment, in this embodiment, the step S30 includes steps S301 to S303:

[0082] Step S301: Determine the conditional test power of each treatment group according to the conditional test power calculation formula.

[0083] It should be explained that the conditional test power calculation formula is:

[0084] ;

[0085] In the formula, represents the standardized test statistic of treatment group k , is the critical value for significance testing. represents the treatment group k conditional power of test, represents the currently collected trial data.

[0086] Step S302: Compare the conditional power of test of each said treatment group with a first preset threshold and a second preset threshold to obtain a comparison result.

[0087] It should be understood that whether to terminate the recruitment of subjects in each said treatment group in advance can be judged by the conditional power of test of each said treatment group. For example, if the conditional power of test of a certain treatment group is higher than the first preset threshold (such as 0.90), or lower than the second preset threshold (such as 0.10), then stop the recruitment of subjects in this treatment group, that is, high-power termination and low-power termination. Hereinafter, an example will be given with the first preset threshold being 0.90 and the second preset threshold being 0.10.

[0088] High-power termination (Early Success Stopping): If , it indicates that this treatment group is very likely to be significantly superior to the control group, and the recruitment can be terminated in advance, and consideration can be given to preferentially promoting this treatment group.

[0089] Low-power termination (Futility Stopping): If , it indicates that this treatment group is almost impossible to achieve a significant effect in the remaining trials, and the recruitment should be terminated to save resources.

[0090] Step S303: Execute a preset resource optimization strategy for each said treatment group according to the comparison result to obtain a test result. The preset resource optimization strategy includes no reallocation of sample size and randomized probability compensation.

[0091] It should be noted that the preset resource optimization strategy includes no reallocation of sample size and randomized probability compensation. No reallocation of sample size means that after a certain treatment group is terminated, its originally planned sample size is no longer reallocated to maintain the independence and interpretability of data analysis. Randomized probability compensation means setting a conditional power null interval. When the conditional power of test of a certain treatment group is within this null interval (such as 0.30 - 0.70), it indicates that the curative effect of its treatment group is neither significantly superior to the control group nor significantly lower than the control group, belonging to an uncertain area; then within this null interval, except for the control group, a randomized probability compensation is set for the treatment group with the worst curative effect, that is, increasing the random allocation probability of the subjects in this treatment group to help it reach the decision standard (such as termination or preference) as soon as possible.

[0092] In a specific implementation, if the comparison result indicates that the conditional test power of the treatment group is greater than the first preset threshold or the conditional test power of the treatment group is less than the second preset threshold, the recruitment of subjects in the treatment group is terminated, where the first preset threshold is greater than the second preset threshold; the treatment group corresponding to the terminated subject recruitment is used as the termination group, the sample size of the termination group is not reallocated, and the corresponding test results are obtained.

[0093] Further, if the comparison result indicates that the conditional test power of the treatment group is less than the first preset threshold and greater than the second preset threshold, it is determined whether the conditional test power of the treatment group is within a preset invalid interval; if the conditional test power of the treatment group is within the preset invalid interval, then within the preset invalid interval, a randomized probability compensation is performed on the treatment group with the worst curative effect, and the corresponding test results are obtained.

[0094] It should be noted that the above-mentioned preset invalid interval, first preset threshold, and second preset threshold can be set customarily, where the first preset threshold is greater than the second preset threshold, and the preset invalid interval is between the first preset threshold and the second preset threshold. The specific values are not limited in this embodiment.

[0095] This embodiment discloses randomly allocating subjects to each treatment group according to a preset ratio and obtaining the current curative effect data of each treatment group; determining the posterior probability of each treatment group based on the current curative effect data of each treatment group, and adjusting the random allocation probability according to the posterior probability; determining the conditional test power of each treatment group according to the conditional test power calculation formula; comparing the conditional test power of each treatment group with the first preset threshold and the second preset threshold to obtain a comparison result; performing a preset resource optimization strategy on each treatment group according to the comparison result to obtain test results, where the preset resource optimization strategy includes not reallocating the sample size and randomized probability compensation; determining the current posterior probability of each treatment group according to the test results, and determining the best treatment group based on the current posterior probability. Since this embodiment determines whether to terminate the recruitment of subjects in each treatment group according to the conditional test power of each treatment group, and performs a preset resource optimization strategy on each treatment group according to the comparison result, including not reallocating the sample size and randomized probability compensation, compared with the prior art, this embodiment effectively improves the test efficiency and saves test resources.

[0096] Reference Figure 3 , Figure 3 is a schematic flowchart of the third embodiment of the clinical trial allocation method based on adaptive randomization of the present invention.

[0097] Based on the above embodiments, in this embodiment, the step S20 includes steps S201 to S203:

[0098] Step S201: Determine the posterior probability of each treatment group based on the current efficacy data of each treatment group and the posterior probability calculation formula.

[0099] The posterior probability calculation formula is:

[0100] ;

[0101] In the formula, represents the efficacy parameter of treatment group k, represents the currently collected trial data, is a marker variable indicating that the efficacy of treatment group k is better than the remaining treatment groups.

[0102] Step S202: Determine the random allocation probability of each treatment group according to the posterior probability and the random allocation probability calculation formula.

[0103] It should be added that for the case with a fixed control group (such as a placebo group), the control group is forced . Accordingly, the random allocation probability calculation formula is:

[0104] ;

[0105] In the formula, the exponent c is used to control the degree of randomization, is a marker variable indicating that the efficacy of treatment group j is better than the remaining treatment groups, represents the random allocation probability of treatment group k.

[0106] It should be noted that the smaller c is, the more consistent the allocation probabilities of each group tend to be (for example, c = 0.5 can reduce extreme randomization). Step S203: Adjust the random allocation probability of each treatment group based on the upper and lower limits of the preset random allocation probability to obtain the adjusted random allocation probability of each treatment group.

[0107] It should be understood that the above adjusted random allocation probability can be the final random allocation probability obtained after the random allocation probability is adjusted based on the upper and lower limits of the preset random allocation probability.

[0108] It should be noted that in order to prevent a certain treatment group from being eliminated prematurely or concentrated excessively, the upper and lower limits of the preset random allocation probability are set , effectively ensuring the reliability and scientificity of the test results:

[0109]

[0110] Among them, ϵ is a threshold less than 0.5 (such as 0.10), ensuring that all treatment groups have reasonable subject allocation probabilities during the test. For the newly added intervention group, the initial allocation probability can be set as 。

[0111] This embodiment discloses randomly allocating subjects to each treatment group according to a preset ratio, and obtaining the current efficacy data of each of the treatment groups; determining the posterior probability of each of the treatment groups based on the current efficacy data of each of the treatment groups and a posterior probability calculation formula; determining the random allocation probability of each of the treatment groups according to the posterior probability and a random allocation probability calculation formula; adjusting the random allocation probability of each of the treatment groups based on the upper and lower limits of a preset random allocation probability to obtain the adjusted random allocation probability of each of the treatment groups; determining the conditional test power of each of the treatment groups, and performing a preset resource optimization strategy on each of the treatment groups according to the conditional test power to obtain a test result; determining the current posterior probability of each of the treatment groups according to the test result, and determining the optimal treatment group based on the current posterior probability. Since this embodiment determines the random allocation probability of each treatment group according to the posterior probability and the random allocation probability calculation formula, and adjusts the random allocation probability of each treatment group based on the upper and lower limits of the preset random allocation probability to obtain the adjusted random allocation probability of each treatment group, compared with the prior art, this embodiment effectively prevents a certain treatment group from being prematurely eliminated or overly concentrated, thereby improving the reliability and scientific nature of the test result.

[0112] In addition, an embodiment of the present invention further provides a storage medium, on which a clinical trial allocation program based on adaptive randomization is stored. When the clinical trial allocation program based on adaptive randomization is executed by a processor, the steps of the clinical trial allocation method based on adaptive randomization as described above are implemented.

[0113] Refer to Figure 4 , Figure 4 which is a structural block diagram of the first embodiment of the clinical trial allocation system based on adaptive randomization of the present invention.

[0114] As Figure 4 shown, the clinical trial allocation system based on adaptive randomization proposed by an embodiment of the present invention includes: a trial allocation module 501, a probability adjustment module 502, a resource optimization module 503, and a treatment recommendation module 504.

[0115] The trial allocation module 501 is configured to randomly allocate subjects to each treatment group according to a preset ratio, and obtain the current efficacy data of each of the treatment groups.

[0116] The probability adjustment module 502 is configured to determine the posterior probability of each of the treatment groups based on the current efficacy data of each of the treatment groups, and adjust the random allocation probability according to the posterior probability.

[0117] The resource optimization module 503 is configured to determine the conditional test power of each treatment group, and perform a preset resource optimization strategy on each treatment group according to the conditional test power to obtain a test result.

[0118] The treatment recommendation module 504 is configured to determine the current posterior probability of each treatment group according to the test result, and determine the optimal treatment group based on the current posterior probability.

[0119] The test allocation module 501 is further configured to determine the sample size of the subjects at the initial stage of the test according to the test scale and the preset between-group difference; randomly allocate the corresponding subjects to each treatment group according to the preset ratio based on the sample size of the subjects, and obtain the current efficacy data of each treatment group.

[0120] This system embodiment discloses randomly allocating subjects to each treatment group according to a preset ratio, and obtaining the current efficacy data of each treatment group; determining the posterior probability of each treatment group based on the current efficacy data of each treatment group, and adjusting the random allocation probability according to the posterior probability; determining the conditional test power of each treatment group, and performing a preset resource optimization strategy on each treatment group according to the conditional test power to obtain a test result; determining the current posterior probability of each treatment group according to the test result, and determining the optimal treatment group based on the current posterior probability. Since this system embodiment dynamically adjusts the random allocation probability of each treatment group during the test process, performs a preset resource optimization strategy on each treatment group according to the conditional test power, and finally determines the current posterior probability of each treatment group according to the test result and determines the optimal treatment group based on the current posterior probability, compared with the prior art, this system embodiment optimizes the allocation of subjects during the test, thereby improving the reliability and accuracy of the test result.

[0121] Based on the first embodiment of the clinical trial allocation system based on adaptive randomization of the present invention, a second embodiment of the clinical trial allocation system based on adaptive randomization of the present invention is proposed.

[0122] In this embodiment, the resource optimization module 503 is further configured to determine the conditional test power of each treatment group according to the conditional test power calculation formula; compare the conditional test power of each treatment group with a first preset threshold and a second preset threshold to obtain a comparison result; perform a preset resource optimization strategy on each treatment group according to the comparison result to obtain a test result, and the preset resource optimization strategy includes no reallocation of the sample size and randomization probability compensation.

[0123] The resource optimization module 503 is further configured to terminate the recruitment of subjects in the treatment group if the comparison result indicates that the conditional test power of the treatment group is greater than the first preset threshold or the conditional test power of the treatment group is less than the second preset threshold, where the first preset threshold is greater than the second preset threshold; use the treatment group corresponding to the terminated subject recruitment as the termination group, no longer reallocate the sample size of the termination group, and obtain the corresponding test results.

[0124] The resource optimization module 503 is further configured to, if the comparison result indicates that the conditional test power of the treatment group is less than the first preset threshold and greater than the second preset threshold, determine whether the conditional test power of the treatment group is within a preset invalid interval; if the conditional test power of the treatment group is within the preset invalid interval, perform randomized probability compensation on the treatment group with the worst curative effect within the preset invalid interval, and obtain the corresponding test results.

[0125] Other embodiments or specific implementation manners of the clinical trial allocation system based on adaptive randomization of the present invention may refer to the above method embodiments, and details are not described herein again.

[0126] This application provides a clinical trial allocation device based on adaptive randomization. The clinical trial allocation device based on adaptive randomization 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 when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the clinical trial allocation method based on adaptive randomization in Embodiment 1 above.

[0127] Next, refer to Figure 5 , which shows a schematic structural diagram of a clinical trial allocation device based on adaptive randomization suitable for implementing the embodiments of the present application. The clinical trial allocation device based on adaptive randomization in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The shown clinical trial allocation device based on adaptive randomization is only an example, and should not impose any limitation on the functions and usage scopes of the embodiments of the present application.

[0128] As Figure 5As shown, the adaptive randomization-based clinical trial allocation device may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory 1002 or the program loaded from the storage device 1003 into the random access memory 1004. In the random access memory 1004, various programs and data required for the operation of the adaptive randomization-based clinical trial allocation device are also stored. The processing device 1001, the read-only memory 1002, and the random access memory 1004 are connected to each other through a bus 1005. The input / output interface 1006 is also connected to the bus. Generally, the following systems may be connected to the input / output interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the adaptive randomization-based clinical trial allocation device to communicate with other devices wirelessly or wiredly to exchange data. Although the figure shows an adaptive randomization-based clinical trial allocation device with various systems, it should be understood that it is not required to implement or have all the shown systems. More or fewer systems can be alternatively implemented or had.

[0129] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program codes for performing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device, or installed from the storage device 1003, or installed from the read-only memory 1002. When the computer program is executed by the processing device 1001, the above functions defined in the methods of the embodiments disclosed in the present application are executed.

[0130] The adaptive randomization-based clinical trial allocation device provided by the present application adopts the adaptive randomization-based clinical trial allocation method in the above embodiments, and can solve the technical problem in the prior art that the resource allocation in the clinical trial stage is not flexible, resulting in insufficient reliability and accuracy of the test results. Compared with the prior art, the beneficial effects of the adaptive randomization-based clinical trial allocation device provided by the present application are the same as those of the adaptive randomization-based clinical trial allocation method provided by the above embodiments, and the other technical features in the adaptive randomization-based clinical trial allocation device are the same as the features disclosed in the method of the previous embodiment, and will not be elaborated here.

[0131] It should be understood that each part disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in a suitable manner in any one or more embodiments or examples.

[0132] As described above, the above are only specific embodiments of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application, and all should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

[0133] It should be noted that in this article, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or system. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or system including that element.

[0134] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0135] Through the description of the above embodiments, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, 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 a read-only memory / random access memory, magnetic disk, optical disk), and includes several instructions for causing a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0136] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structure or equivalent process transformation made by using the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be similarly included in the patent protection scope of the present invention.

Claims

1. A clinical trial allocation method based on adaptive randomization, characterized in that: The method comprises: Randomly assigning subjects to treatment groups according to a preset ratio, and obtaining current efficacy data of each treatment group; Determine the posterior probability of each of the treatment groups based on the current efficacy data of each of the treatment groups, and adjust the random allocation probability according to the posterior probability; Determine the conditional test efficacy of each of the treatment groups, and execute a preset resource optimization strategy for each of the treatment groups according to the conditional test efficacy to obtain a test result; Determine the current posterior probability of each of the treatment groups according to the test results, and determine the best treatment group based on the current posterior probability; The step of determining the conditional test efficacy of each treatment group, and executing a preset resource optimization strategy for each treatment group according to the conditional test efficacy to obtain the test results includes: Determining the conditional test efficacy of each treatment group according to a conditional test efficacy calculation formula; Comparing the conditional test efficacy of each of the treatment groups with a first preset threshold and a second preset threshold to obtain a comparison result; Executing a preset resource optimization strategy on each of the treatment groups according to the comparison results to obtain a test result, wherein the preset resource optimization strategy includes no more sample size reallocation and randomization probability compensation; The conditional test efficiency calculation formula is: ； In the formula, Treatment group k The standardized test statistic, is the critical value of the significance test, Treatment group k The conditional test efficiency of Represents the experimental data currently collected.

2. The clinical trial allocation method based on adaptive randomization according to claim 1, characterized in that: The step of executing a preset resource optimization strategy on each of the treatment groups according to the comparison results to obtain the test results comprises: If the comparison result indicates that the conditional test power of the treatment group is greater than the first preset threshold or the conditional test power of the treatment group is less than the second preset threshold, then terminating the recruitment of subjects for the treatment group, and the first preset threshold is greater than the second preset threshold; The treatment group corresponding to the terminated subject recruitment is taken as the terminated group, the sample size of the terminated group is no longer reallocated, and the corresponding test results are obtained.

3. The clinical trial allocation method based on adaptive randomization according to claim 1, characterized in that: The step of executing a preset resource optimization strategy on each of the treatment groups according to the comparison results to obtain the test results comprises: If the comparison result indicates that the conditional test efficacy of the treatment group is less than the first preset threshold and greater than the second preset threshold, determining whether the conditional test efficacy of the treatment group is in a preset invalid interval; If the conditional test efficacy of the treatment group is in a preset invalid interval, then within the preset invalid interval, randomization probability compensation is performed on the treatment group with the worst efficacy, and the corresponding test results are obtained.

4. The clinical trial allocation method based on adaptive randomization according to claim 1, characterized in that: The step of determining the posterior probability of each treatment group based on the current efficacy data of each treatment group, and adjusting the random allocation probability according to the posterior probability, comprises: Determine the posterior probability of each of the treatment groups based on the current efficacy data of each of the treatment groups and a posterior probability calculation formula; Determine the random assignment probability of each treatment group according to the posterior probability and the random assignment probability calculation formula; Adjusting the random allocation probability of each treatment group based on the preset upper and lower limits of the random allocation probability to obtain the adjusted random allocation probability of each treatment group; The posterior probability calculation formula is: ； In the formula, represents the efficacy parameter of treatment group k, Represents the test data currently collected. It is a marker variable indicating that the efficacy of treatment group k is better than that of the remaining treatment groups; The random allocation probability calculation formula is: ； In the formula, the index c is used to control the degree of randomization. is a marker variable indicating that the efficacy of treatment group j is better than that of the remaining treatment groups, represents the probability of random assignment to treatment group k.

5. The clinical trial allocation method based on adaptive randomization according to claim 1, characterized in that: The step of randomly allocating the subjects to each treatment group according to a preset ratio and obtaining the current efficacy data of each treatment group includes: Determine the sample size of subjects in the initial stage of the trial based on the trial scale and the pre-set differences between the groups; Based on the sample size of the subjects, the corresponding subjects are randomly assigned to each treatment group according to a preset ratio, and the current efficacy data of each treatment group is obtained.

6. A clinical trial allocation system based on adaptive randomization, characterized in that: The system comprises: A trial allocation module, used to randomly allocate subjects to treatment groups according to a preset ratio and obtain current efficacy data of each treatment group; A probability adjustment module, configured to determine the posterior probability of each of the treatment groups based on the current efficacy data of each of the treatment groups, and adjust the random allocation probability according to the posterior probability; A resource optimization module, used to determine the conditional test efficacy of each of the treatment groups, and execute a preset resource optimization strategy for each of the treatment groups according to the conditional test efficacy to obtain a test result; A treatment recommendation module, used to determine the current posterior probability of each treatment group according to the test results, and determine the best treatment group based on the current posterior probability; The resource optimization module is further used to determine the conditional test efficacy of each of the treatment groups according to the conditional test efficacy calculation formula; compare the conditional test efficacy of each of the treatment groups with the first preset threshold and the second preset threshold to obtain a comparison result; and execute a preset resource optimization strategy on each of the treatment groups according to the comparison result to obtain a test result, wherein the preset resource optimization strategy includes no more sample size reallocation and randomization probability compensation; The conditional test efficiency calculation formula is: ； In the formula, Treatment group k The standardized test statistic, is the critical value of the significance test, Treatment group k The conditional test efficiency of Represents the experimental data currently collected.

7. A clinical trial allocation device based on adaptive randomization, characterized in that: The device includes: a memory, a processor, and a clinical trial allocation program based on adaptive randomization stored in the memory and executable on the processor, wherein the clinical trial allocation program based on adaptive randomization is configured to implement the steps of the clinical trial allocation method based on adaptive randomization as described in any one of claims 1 to 5.

8. A storage medium, characterized in that: The storage medium stores a clinical trial allocation program based on adaptive randomization, and when the clinical trial allocation program based on adaptive randomization is executed by a processor, the steps of the clinical trial allocation method based on adaptive randomization as described in any one of claims 1 to 5 are implemented.

Images