A blockchain-based clinical trial subject management system and method

Abstract

The application relates to a kind of blockchain-based clinical trial subject management system and method, relate to clinical trial technical field, its system includes the management system built based on blockchain network and multiple deployment in medical institution's edge computing node, and edge computing node is encrypted to the case information processing of subject and is transmitted to blockchain network storage, can also generate feature query condition screening target subject, obtains target subject index data to determine test information, follow-up visit and nursing information, predicts follow-up visit time and generates follow-up visit plan;Blockchain network can be based on feature query condition and start smart contract template to screen target subject.The present application achieves the technical effect of using blockchain technology to guarantee the safety of subject data, realize efficient screening, accurate supervision and scientific follow-up visit management of clinical trial subjects.

Description

Technical Field

[0001] This invention relates to the field of clinical trial technology, and in particular to a blockchain-based clinical trial subject management system and method. Background Technology

[0002] A clinical trial project is a scientific research effort designed to verify the safety and effectiveness of a new drug, vaccine, treatment, or diagnostic tool in humans. Clinical trial projects are an indispensable part of medical research and are crucial for advancing medical science, improving patient treatment outcomes, and ensuring the safety of medical products.

[0003] Subjects refer to individuals participating in testing within a clinical trial program. Subjects play a crucial role in clinical trials, and the selection of eligible subjects is essential for the success of such programs.

[0004] Currently, common methods include manually recording and managing participants' medical records. Staff need to manually collect, organize, and analyze each participant's case, which involves a large amount of paperwork and tedious manual operations. Meanwhile, participant screening often relies on the doctor's experience and subjective judgment, determining eligibility through reviewing medical records and face-to-face interviews. During the trial, monitoring and follow-up of participants also largely rely on traditional methods such as telephone communication or regular outpatient visits, with medical staff inquiring about the participants' health and trial progress.

[0005] However, existing management methods have significant shortcomings. Manual recording and management of case information is prone to errors and omissions, and is inefficient, making it difficult to quickly and accurately acquire and process large amounts of case data. Relying on physicians' subjective experience in subject screening may lead to biases and inconsistencies in screening results, affecting the quality and efficiency of the trial. Traditional monitoring and follow-up methods lack real-time responsiveness and accuracy, failing to promptly grasp subjects' vital signs and behavioral information, and making it difficult to identify and address problems that arise during the trial. Summary of the Invention

[0006] The technical problem to be solved by the present invention is to provide a blockchain-based clinical trial subject management system and method, which aims to solve at least one of the above-mentioned technical problems.

[0007] The technical solution of the present invention to solve the above-mentioned technical problems is as follows:

[0008] Firstly, this application provides an artificial intelligence-based clinical trial subject management system, which adopts the following technical solution:

[0009] A blockchain-based clinical trial subject management system includes a blockchain network and multiple edge computing nodes deployed in various medical institutions. The blockchain network is equipped with smart contract templates, including screening contracts.

[0010] Each of the aforementioned edge computing nodes includes:

[0011] A data processing module is used to acquire the medical records of each subject in the medical institution, the medical records including structured and unstructured data; for each subject's medical records, feature extraction is performed on the medical records to obtain feature information; based on the feature information and a preset mapping method, the structured feature information of the subject is determined; the structured feature information of each subject is homomorphically encrypted to obtain multiple encrypted feature information; and the multiple encrypted feature information is sent to the blockchain network.

[0012] The subject screening module is used to obtain the target trial protocol, generate feature query conditions based on the target trial protocol, and send the feature query conditions to the blockchain network to screen multiple target subjects corresponding to the target trial protocol based on the blockchain network.

[0013] The subject monitoring module is used to acquire indicator data for each target subject, the indicator data representing vital sign data; determine trial information based on the indicator data, the trial information including normal trial information or abnormal trial information; and determine the follow-up questionnaire and nursing information for the target subject based on the trial information.

[0014] The follow-up management module is used to acquire behavioral information and trial requirement information of each target subject, predict the follow-up time based on the behavioral information and trial requirement information, generate a follow-up plan based on the follow-up time and trial information, and push the follow-up questionnaire to the target subject.

[0015] The blockchain network is used to store the encrypted feature information of subjects from each of the medical institutions, and to activate corresponding smart contract templates based on feature query conditions to screen multiple target subjects corresponding to the target trial plan.

[0016] The beneficial effects of this invention are as follows: This invention constructs a closed-loop management system for the entire process of clinical trial subject management through a collaborative architecture of blockchain and edge computing nodes. Edge computing nodes, based on homomorphic encryption technology, achieve privacy processing and distributed storage of case information, breaking down data barriers between medical institutions while ensuring data security. The blockchain network automatically executes feature matching, inclusion / exclusion criterion verification, and quota allocation through smart contract templates, improving screening accuracy and reducing the risk of human intervention. The follow-up management module generates personalized follow-up plans and pushes dynamic questionnaires based on real-time analysis of subject behavior data and trial progress. The subject monitoring module, through real-time monitoring of vital signs and abnormal warnings, links information allocation with nursing staff, forming a rapid response mechanism for trial safety. The overall solution achieves breakthroughs in privacy protection, process automation, dynamic adaptability, and compliance, providing an efficient, safe, and intelligent integrated solution for multi-center clinical trials.

[0017] Based on the above technical solution, the present invention can be further improved as follows.

[0018] Furthermore, the subject monitoring module, when determining the follow-up questionnaire of the target subject based on the trial information, specifically uses the following:

[0019] Based on the trial information of the target subjects, the basic information of the questionnaire is determined, which includes the target subject's identity information, trial stage, trial type, clinical indicators, behavioral characteristics, and risk level.

[0020] Keyword features are extracted from the basic information of the questionnaire to obtain multiple keywords of the basic information of the questionnaire;

[0021] Based on the number of each keyword and the preset ratio, the questionnaire theme and questionnaire content are determined;

[0022] Based on the target subject's identity information, the questionnaire type is determined. The target subject's identity information includes age, behavioral ability, and cognitive ability. The questionnaire type includes paper questionnaires with different font sizes and word explanation levels, and voice questionnaires with different word explanation levels.

[0023] Based on the questionnaire type, several recommended packaging templates were determined;

[0024] Based on the usage frequency of each recommended packaging template, a first weight is determined for each of the recommended packaging templates;

[0025] Based on the target subjects' historical usage frequency of each of the recommended packaging templates, a second weight for each of the recommended packaging templates is determined;

[0026] Based on the mid-term dropout rate of the questionnaire corresponding to each of the recommended packaging templates, a third weight is determined for each of the recommended packaging templates;

[0027] The disease response coefficient is determined based on the trial information of the target subjects, and the fourth weight of each of the recommended packaging templates is determined based on the disease response coefficient.

[0028] The target packaging template is determined based on the first weight, second weight, third weight, and fourth weight of each of the recommended packaging templates;

[0029] Based on the questionnaire topic, the questionnaire content, the questionnaire type, and the target packaging template, a follow-up questionnaire is generated.

[0030] The beneficial effects of adopting the above-mentioned further approach are as follows: First, keywords are extracted based on the trial information of the target subjects (such as trial stage, clinical indicators, and risk level) to generate questionnaire topics and content, ensuring that the questionnaire content is highly relevant to the trial progress; Second, the paper or voice questionnaire type is automatically selected based on the subjects' identity information (age, behavioral ability, and cognitive ability), and the font size and word explanation are adjusted to solve the comprehension barrier caused by the monotonous format of traditional questionnaires; Third, through dynamic weight calculation of recommended packaging templates (comprehensive use frequency, historical usage count, mid-course dropout rate, and disease response coefficient), the preferences of subjects and trial needs are accurately matched, reducing the risk of mid-course dropout; Finally, the generated follow-up questionnaire has the characteristics of targeted content, format adaptability, and execution reliability, significantly improving subject compliance, ensuring the integrity and accuracy of trial data collection, and providing high-quality data support for the analysis of clinical trial results.

[0031] Furthermore, the subject monitoring module, when determining the target subject's care information based on the trial information, is specifically used for:

[0032] Based on the experimental information and the preset K-means clustering model, the category level of the target subjects is determined;

[0033] Based on the category level of the target subjects, nursing needs are determined, including the frequency of nursing care.

[0034] Based on the target subjects' historical nursing records and trial phases, predict the nursing time and duration for the target subjects within the target time interval;

[0035] Based on the location of the target subject, multiple management personnel are matched within the current medical institution;

[0036] Based on preset matching rules and multiple managers of the current medical institution, the nursing staff of the target subject are determined, and nursing information is determined based on the nursing time, nursing duration and nursing staff.

[0037] The beneficial effects of adopting the above-mentioned further approach are as follows: By classifying the trial information (such as clinical indicators, risk levels, and trial stages) of the target subjects based on the K-means clustering model, and dynamically adjusting the frequency of nursing care in conjunction with historical nursing records, the problem of resource waste or demand mismatch caused by traditional fixed-frequency nursing care is solved; by predicting the nursing time and duration within the target time interval and combining the real-time location of the subjects with the current medical institution's management personnel, the timeliness of nursing response is ensured; by pre-setting matching rules to comprehensively consider the expertise and workload of management personnel and the nursing needs of the subjects, the allocation of nursing staff is optimized, improving the professionalism and efficiency of nursing services; the final generated nursing information has the dual advantages of personalized demand satisfaction and optimized resource allocation, significantly improving the quality of subject care, reducing the risks caused by improper nursing care during the trial, and providing strong protection for the safety of clinical trials.

[0038] Furthermore, the subject monitoring module, based on preset matching rules and multiple administrators at the current medical institution, determines the caregivers for the target subject, including:

[0039] Obtain the current subject information corresponding to each of the aforementioned managers, wherein the current subject information includes the location, nursing time, and nursing duration of the subject to be treated, as well as the location, nursing time, and nursing duration of the currently managed subject;

[0040] Based on the timeliness information of each manager in the historical time period and the current subject information corresponding to each manager, the multiple managers are screened to obtain multiple first managers;

[0041] Based on the nursing time and duration of the target subject and the current subject information corresponding to each of the first management personnel, the multiple management personnel are screened to obtain multiple second management personnel;

[0042] Based on the location of the target subject and the current subject information corresponding to each second manager, a distance coefficient for each second manager is determined;

[0043] Based on the distance coefficient of each second manager, a first priority value is determined for each second manager;

[0044] Based on the historical care information of each second manager, the degree of match between each second manager and the target subject in terms of trial type and trial phase is determined;

[0045] A second priority value is determined for each second manager based on the degree of match between each second manager and the target subject in terms of trial type and trial phase;

[0046] Based on the number of errors made by each second manager within a historical time period, a third priority value is determined for each second manager;

[0047] Based on the matching degree between each second manager and the subject, a fourth priority value is determined for each second manager;

[0048] The caregivers for the target subjects are determined based on the first priority value, second priority value, third priority value, and fourth priority value of each second manager.

[0049] The beneficial effects of adopting the above-mentioned further solutions are as follows: By combining historical timeliness information of management personnel with current task load to screen available personnel, resource conflicts and overload are avoided, and basic allocation efficiency is improved; by matching nursing personnel based on proximity through distance coefficients, nursing response time is significantly shortened, and service professionalism is ensured by combining expertise matching based on trial type and stage; by introducing a dual priority value of historical error count and subject matching degree, operational risks are reduced; finally, a weighted decision-making model integrating the four priority values ​​achieves an optimal balance between timeliness, professionalism, safety, and user experience. This solves the subjectivity and inefficiency of traditional manual allocation and realizes dynamic optimization of nursing resource allocation.

[0050] Furthermore, the follow-up management module is specifically used for:

[0051] Obtain the location information of the target subject;

[0052] Based on the target subject's location information and the target subject's historical behavioral data, predict the target subject's location;

[0053] Based on the behavioral information of the target subjects, the trial requirements information, the historical behavioral data of the target subjects, and the LSTM model, the initial follow-up time is predicted;

[0054] The initial follow-up time is adjusted based on the predicted location of the target subject to obtain the target follow-up time for the target subject;

[0055] Based on the target follow-up time and trial information, a follow-up plan is generated and sent to the target subjects.

[0056] The beneficial effects of adopting the above-mentioned further approach are: combining the real-time location information and historical behavioral data of the target subjects to predict their future location, solving the problem of inconvenience or lateness caused by traditional fixed follow-up locations; dynamically predicting the initial follow-up time based on the analysis of behavioral information and test requirements using the LSTM model, improving the accuracy of time scheduling; and adaptively adjusting the initial time according to the predicted location to ensure that the follow-up plan is highly matched with the actual activity trajectory of the subjects, avoiding plan failure due to location changes.

[0057] Furthermore, the blockchain network, when used to initiate corresponding smart contract templates based on feature query conditions to screen multiple target subjects corresponding to the target experimental protocol, is specifically used for:

[0058] Obtain a number directory from a preset number directory smart contract. The number directory includes multiple numbers, each number corresponds to multiple data names, each data name represents a case name, and each data name is associated with at least one first keyword set.

[0059] Based on the encrypted feature information and number directory of each subject, determine the matching number of each subject and the number of matching fields corresponding to the matching number;

[0060] Based on the feature query conditions, determine the set of second keywords;

[0061] The second keyword set is matched with the first keyword set associated with each of the data names, and multiple matching degree values ​​are calculated;

[0062] Based on the matching number of each subject, the number of matching fields corresponding to the matching number, and multiple matching degree values, multiple candidate subjects are determined;

[0063] Based on the inclusion and exclusion criteria of the target trial protocol, multiple candidate subjects are screened to generate a target subject list. The inclusion and exclusion criteria represent the conditions that subjects must meet and the conditions that must be excluded.

[0064] After verifying the consensus of the target subject list, the data is stored in the target subject smart contract and the data association in the numbered directory smart contract is updated to obtain multiple target subjects.

[0065] The beneficial effects of adopting the above-mentioned further solutions are as follows: Based on the smart contract of the numbered directory, structured association and privacy-preserving storage of multi-center case data are achieved, solving the data silos and privacy leakage risks of traditional centralized databases; through multi-dimensional matching of encrypted feature information and keyword sets (matching number, number of fields, and matching degree value), the accuracy and efficiency of candidate subject screening are improved; the smart contract automatically executes the verification of inclusion and exclusion criteria, ensuring that the screening results strictly meet the requirements of the trial protocol and reducing human error; the target subject list and numbered directory update mechanism, which is stored through node consensus, not only ensures process compliance but also achieves dynamic optimization of data association relationships.

[0066] Furthermore, the blockchain network is used to determine multiple candidate subjects based on each subject's matching number, the number of matching fields corresponding to the matching number, and multiple matching degree values, specifically for:

[0067] Based on multiple matching scores, a target number is determined from the target number directory;

[0068] Based on the matching number of each subject, the number of matching fields corresponding to the matching number, and the target number, multiple initial subjects are determined;

[0069] Based on the number of matching fields for each initial subject, the medication time difference, and the semantic similarity between the case text of each initial subject and the feature query conditions, a weighted matching degree for each initial subject is calculated. The medication time difference represents the difference between the historical medication time and the time of the target trial protocol.

[0070] Based on the weighted matching degree of each initial subject, multiple candidate subjects are identified.

[0071] The beneficial effects of adopting the above-mentioned further scheme are as follows: By using a dynamic determination mechanism based on target number, combined with matching number and number of fields, the initial subject group highly correlated with the feature query conditions can be quickly identified, improving the efficiency of basic screening; by introducing medication time difference as a key parameter, the temporal correlation between historical medication and trial protocol can be quantified, avoiding the influence of drug interference on trial results and significantly improving the scientific nature of screening; by integrating semantic similarity analysis of case text and query conditions, the semantic accuracy of feature association can be ensured; and by weighted fusion of the number of matching fields, medication time difference, and semantic similarity, the objectivity and comprehensiveness of candidate subject ranking can be achieved.

[0072] Secondly, this application provides a blockchain-based method for managing clinical trial subjects, employing the following technical solution:

[0073] A blockchain-based method for managing clinical trial participants, comprising:

[0074] Edge computing nodes acquire medical records of each subject in the medical institution, the medical records including structured and unstructured data; for each subject's medical records, feature extraction is performed on the medical records to obtain feature information; based on the feature information and a preset mapping method, the subject's structured feature information is determined; the structured feature information of each subject is homomorphically encrypted to obtain multiple encrypted feature information; the multiple encrypted feature information is sent to the blockchain network;

[0075] An edge computing node acquires a target trial plan, generates feature query conditions based on the target trial plan, and sends the feature query conditions to the blockchain network to filter multiple target subjects corresponding to the target trial plan based on the blockchain network.

[0076] For each target subject, the edge computing node acquires the target subject's indicator data, which represents vital sign data; determines trial information based on the indicator data, which includes normal or abnormal trial information; and determines the target subject's follow-up questionnaire and caregiver information based on the trial information.

[0077] For each target subject, the edge computing node acquires the target subject's behavioral information and trial requirement information, predicts the follow-up time based on the target subject's behavioral information and trial requirement information, generates a follow-up plan based on the follow-up time and trial information, and pushes the follow-up questionnaire to the target subject;

[0078] The blockchain network stores encrypted feature information of subjects from various medical institutions and initiates corresponding smart contract templates based on feature query conditions. The smart contract templates include dynamic matching contracts, informed consent contracts, and dynamic quota contracts.

[0079] Thirdly, this application provides an electronic device that adopts the following technical solution:

[0080] An electronic device includes a memory and a processor, wherein the memory stores a computer program capable of being loaded by the processor and executing a blockchain-based clinical trial subject management method as described in any of the first aspects.

[0081] Fourthly, this application provides a computer-readable storage medium, which adopts the following technical solution:

[0082] A computer-readable storage medium storing a computer program capable of being loaded by a processor and executing a blockchain-based clinical trial subject management method as described in any of the first aspects.

[0083] Additional aspects and advantages of this application will be set forth in part in the description which follows, and will become apparent from the description or may be learned by practice of this application. Attached Figure Description

[0084] Figure 1 A schematic diagram of a blockchain-based clinical trial subject management system provided in one embodiment of the present invention;

[0085] Figure 2 A flowchart illustrating a blockchain-based clinical trial subject management method according to an embodiment of the present invention;

[0086] Figure 3 This is a schematic diagram of the structure of an electronic device provided by the present invention. Detailed Implementation

[0087] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0088] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0089] like Figure 1 As shown, a blockchain-based clinical trial subject management system 100 includes a blockchain network 102 and multiple edge computing nodes 101. The edge computing nodes 101 are deployed in various medical institutions. The blockchain network 102 is equipped with smart contract templates, including screening contracts.

[0090] Each of the edge computing nodes 101 includes:

[0091] A data processing module is used to acquire the medical records of each subject in the medical institution, the medical records including structured and unstructured data; for each subject's medical records, feature extraction is performed on the medical records to obtain feature information; based on the feature information and a preset mapping method, the structured feature information of the subject is determined; the structured feature information of each subject is homomorphically encrypted to obtain multiple encrypted feature information; and the multiple encrypted feature information is sent to the blockchain network.

[0092] The subject screening module is used to obtain the target trial protocol, generate feature query conditions based on the target trial protocol, and send the feature query conditions to the blockchain network to screen multiple target subjects corresponding to the target trial protocol based on the blockchain network.

[0093] The subject monitoring module is used to acquire indicator data for each target subject, the indicator data representing vital sign data; determine trial information based on the indicator data, the trial information including normal trial information or abnormal trial information; and determine the follow-up questionnaire and nursing information for the target subject based on the trial information.

[0094] The follow-up management module is used to acquire behavioral information and trial requirement information of each target subject, predict the follow-up time based on the behavioral information and trial requirement information, generate a follow-up plan based on the follow-up time and trial information, and push the follow-up questionnaire to the target subject.

[0095] The blockchain network is used to store the encrypted feature information of subjects from each of the medical institutions, and to activate corresponding smart contract templates based on feature query conditions to screen multiple target subjects corresponding to the target trial plan.

[0096] This invention constructs a closed-loop management system for the entire process of clinical trial subject management through a collaborative architecture of blockchain and edge computing nodes: edge computing nodes achieve privacy processing and distributed storage of case information based on homomorphic encryption technology, breaking down data barriers between medical institutions while ensuring data security; the blockchain network automatically executes feature matching, inclusion and exclusion criterion verification, and quota allocation through smart contract templates, improving screening accuracy and reducing the risk of human intervention; the follow-up management module generates personalized follow-up plans and pushes dynamic questionnaires based on real-time analysis of subject behavior data and trial progress; the subject monitoring module, through real-time monitoring of vital signs and abnormal warnings, links information allocation with nursing staff to form a rapid response mechanism for trial safety. The overall solution achieves breakthroughs in privacy protection, process automation, dynamic adaptability, and compliance, providing an efficient, safe, and intelligent integrated solution for multi-center clinical trials.

[0097] In this embodiment of the application, the data processing module is specifically used for:

[0098] The subject's medical records are obtained through the medical institution's information system interface or electronic medical record (EMR) system. The structured data includes fields that can be directly parsed, such as age, gender, laboratory test result values, and diagnostic codes; the unstructured data includes unstructured text or image data such as imaging examination report text and pathology slide descriptions.

[0099] For structured data, key fields are directly extracted as feature information;

[0100] For unstructured text data, natural language processing technology is used for entity recognition and relation extraction to extract features such as symptoms, medication records, and past medical history.

[0101] For unstructured image data, a convolutional neural network model is used to extract features such as the location and size of lesions.

[0102] Next, based on the feature information and a predefined mapping method, structured feature information is generated. This process achieves feature standardization through a predefined rule engine or machine learning model (such as random forest). For example, the extracted symptom "headache" is mapped to standard medical terminology codes.

[0103] Finally, the structured feature information is encrypted using a homomorphic encryption algorithm to generate encrypted feature information, which is then uploaded to the blockchain.

[0104] Optionally, the subject monitoring module, when determining the follow-up questionnaire of the target subject based on the trial information, is specifically used for:

[0105] Based on the trial information of the target subjects, the basic information of the questionnaire is determined. The basic information of the questionnaire includes the target subject's identity information, trial stage, trial type, clinical indicators, behavioral characteristics information, and risk level. Behavioral characteristics can reflect whether the subject takes medication on time and whether they follow dietary restrictions, etc.

[0106] Keyword features are extracted from the basic information of the questionnaire to obtain multiple keywords of the basic information of the questionnaire;

[0107] Based on the number of each keyword and the preset ratio, the questionnaire theme and questionnaire content are determined;

[0108] Based on the target subject's identity information, the questionnaire type is determined. The target subject's identity information includes age, behavioral ability, and cognitive ability. The questionnaire type includes paper questionnaires with different font sizes and word explanation levels, and voice questionnaires with different word explanation levels.

[0109] Based on the questionnaire type, several recommended packaging templates were determined;

[0110] Based on the usage frequency of each recommended packaging template, a first weight is determined for each of the recommended packaging templates;

[0111] Based on the target subjects' historical usage frequency of each of the recommended packaging templates, a second weight for each of the recommended packaging templates is determined;

[0112] Based on the mid-term dropout rate of the questionnaire corresponding to each of the recommended packaging templates, a third weight is determined for each of the recommended packaging templates;

[0113] The disease response coefficient is determined based on the trial information of the target subjects, and the fourth weight of each of the recommended packaging templates is determined based on the disease response coefficient.

[0114] The target packaging template is determined based on the first weight, second weight, third weight, and fourth weight of each of the recommended packaging templates;

[0115] Based on the questionnaire topic, the questionnaire content, the questionnaire type, and the target packaging template, a follow-up questionnaire is generated.

[0116] In this embodiment, identity information is extracted from the trial information, such as age, behavioral ability, cognitive ability assessment results, trial stage, trial type, clinical indicators, behavioral characteristics, and risk level. Clinical indicators include, for example, the white blood cell count in the most recent blood routine test, and risk level, such as high risk defined as a history of serious adverse reactions.

[0117] Then, the TF-IDF algorithm was used to extract keywords from the basic information of the questionnaire, such as "white blood cell count", "phase II" and "high risk" as core keywords, and the questionnaire theme and content framework were constructed according to the preset ratio.

[0118] Next, the questionnaire type was selected based on the identity information; if the subject's age was ≥75 years or the cognitive ability score was ≤24 points, a paper questionnaire with large font and word explanation level of "basic medical terminology + everyday language" was selected first.

[0119] If the participant has a visual impairment or meets the required level of smartphone proficiency, an audio questionnaire will be provided.

[0120] Next, recommended packaging templates are selected from the preset template library, and the weight of each template is calculated. The first weight is based on the template usage frequency, such as the percentage of times the template has been used in the entire system in the past 3 months. The second weight is the historical usage frequency of the target subject, such as the subject choosing the graphic version in the past 3 follow-ups. The third weight is the template dropout rate, such as the dropout rate of the process guidance version being only 5%. The fourth weight is adjusted by the disease response coefficient. Finally, a linear weighted model is used to determine the target template.

[0121] Finally, the questionnaire topic and content are filled into the target template to generate a follow-up questionnaire, which is then sent to the participants via the medical institution's app or SMS. This accurately matches the participants' preferences with the trial's needs, reducing the risk of them dropping out midway through the questionnaire.

[0122] Optionally, the subject monitoring module, used to determine the target subject's care information based on the trial information, is specifically used for:

[0123] Based on the experimental information and the preset K-means clustering model, the category level of the target subjects is determined;

[0124] Based on the category level of the target subjects, nursing needs are determined, including the frequency of nursing care.

[0125] Based on the target subjects' historical nursing records and trial phases, predict the nursing time and duration for the target subjects within the target time interval;

[0126] Based on the location of the target subject, multiple management personnel are matched within the current medical institution;

[0127] Based on preset matching rules and multiple managers of the current medical institution, the nursing staff of the target subject are determined, and nursing information is determined based on the nursing time, nursing duration and nursing staff.

[0128] In this embodiment, feature vectors are constructed based on trial information (such as clinical indicators, risk levels, and trial stages), and input into a preset K-means clustering model to divide subjects into different categories. The categories can be high-risk groups or stable groups, and the category level is directly related to nursing needs.

[0129] By combining the subjects' historical nursing records with the current trial phase, a time series prediction model is used to predict the nursing time and duration for the target time interval. Real-time location is obtained through a subject positioning module (GPS or indoor Bluetooth positioning), and the subject is matched with the nearest management personnel within the current medical institution. The management personnel's information includes their current workload (number of subjects assigned) and area of ​​expertise (such as oncology nursing, chronic disease management).

[0130] In this embodiment of the application, the subject monitoring module, based on preset matching rules and multiple managers of the current medical institution, determines the caregivers of the target subject, including:

[0131] Obtain the current subject information corresponding to each of the aforementioned managers, wherein the current subject information includes the location, nursing time, and nursing duration of the subject to be treated, as well as the location, nursing time, and nursing duration of the currently managed subject;

[0132] Based on the timeliness information of each manager in the historical time period and the current subject information corresponding to each manager, the multiple managers are screened to obtain multiple first managers;

[0133] Based on the nursing time and duration of the target subject and the current subject information corresponding to each of the first management personnel, the multiple first management personnel are screened to obtain multiple second management personnel;

[0134] Based on the location of the target subject and the current subject information corresponding to each second manager, a distance coefficient for each second manager is determined;

[0135] Based on the distance coefficient of each second manager, a first priority value is determined for each second manager;

[0136] Based on the historical care information of each second manager, the degree of match between each second manager and the target subject in terms of trial type and trial phase is determined;

[0137] A second priority value is determined for each second manager based on the degree of match between each second manager and the target subject in terms of trial type and trial phase;

[0138] Based on the number of errors made by each second manager within a historical time period, a third priority value is determined for each second manager;

[0139] Based on the matching degree between each second manager and the subject, a fourth priority value is determined for each second manager;

[0140] The caregivers for the target subjects are determined based on the first priority value, second priority value, third priority value, and fourth priority value of each second manager.

[0141] By combining historical timeliness information from management personnel with current workload to select available personnel, resource conflicts and overload are avoided, improving basic allocation efficiency. Distance coefficients are used to match nurses based on proximity, significantly shortening nursing response time. Specialty matching based on trial type and phase ensures service professionalism. Introducing a dual priority value of historical error count and subject matching reduces operational risk. Finally, a weighted decision-making model integrating these four priority values ​​achieves an optimal balance between timeliness, professionalism, safety, and user experience. This addresses the subjectivity and inefficiency of traditional manual allocation, enabling dynamic optimization of nursing resource allocation.

[0142] Optional, follow-up management module, specifically used for:

[0143] Obtain the location information of the target subject;

[0144] Based on the target subject's location information and the target subject's historical behavioral data, predict the target subject's location;

[0145] Based on the behavioral information of the target subjects, the trial requirements information, the historical behavioral data of the target subjects, and the LSTM model, the initial follow-up time is predicted;

[0146] The initial follow-up time is adjusted based on the predicted location of the target subject to obtain the target follow-up time for the target subject;

[0147] Based on the target follow-up time and trial information, a follow-up plan is generated and sent to the target subjects.

[0148] In this embodiment, real-time location information is obtained through the GPS module built into the smart terminal carried by the target subject. Based on historical behavioral data, a time-space sequence model is constructed. This model, combined with current location information, predicts future location distribution. Behavioral information, experimental requirements, and historical behavioral data are input into a pre-trained LSTM model, which outputs the initial follow-up time. The time is adjusted according to the predicted location: if the predicted location is local, the original time is maintained; if the predicted location is not local, the initial follow-up time is adjusted to obtain the target follow-up time for the target subject.

[0149] Optionally, when the blockchain network is used to initiate a corresponding smart contract template based on feature query conditions to screen multiple target subjects corresponding to the target experimental protocol, it is specifically used for:

[0150] Obtain a number directory from a preset number directory smart contract. The number directory includes multiple numbers, each number corresponds to multiple data names, each data name represents a case name, and each data name is associated with at least one first keyword set.

[0151] Based on the encrypted feature information and number directory of each subject, determine the matching number of each subject and the number of matching fields corresponding to the matching number;

[0152] Based on the feature query conditions, determine the set of second keywords;

[0153] The second keyword set is matched with the first keyword set associated with each of the data names, and multiple matching degree values ​​are calculated;

[0154] Based on the matching number of each subject, the number of matching fields corresponding to the matching number, and multiple matching degree values, multiple candidate subjects are determined;

[0155] Based on the inclusion and exclusion criteria of the target trial protocol, multiple candidate subjects are screened to generate a target subject list. The inclusion and exclusion criteria represent the conditions that subjects must meet and the conditions that must be excluded.

[0156] After verifying the consensus of the target subject list, the data is stored in the target subject smart contract and the data association in the numbered directory smart contract is updated to obtain multiple target subjects.

[0157] In this embodiment of the application, a pre-set number directory smart contract is invoked, for example, an on-chain structured table that stores case data indexes, where each number corresponds to multiple data names such as “Case-001” and “Case-002”, and the data names are associated with a first set of keywords such as “breast cancer” and “HER2 positive”, to obtain the full number directory.

[0158] Subsequently, encrypted feature information uploaded by the subject monitoring module is matched with the number directory in encrypted form. By calculating the number of overlaps between the field of each subject feature and the corresponding data name (e.g., “45 years old” matches the “age=40-50 years old” field in “Case-001”), the matching number and the number of corresponding matching fields are determined (e.g., “Case-001” matches 3 fields).

[0159] Next, based on the feature query conditions, the first keyword set is extracted. For example, the first keyword set includes "breast cancer", "HER2 positive", "non-targeted therapy", etc., and semantic matching is performed with the second keyword set associated with each data name. The matching degree value is calculated using the TF-IDF algorithm.

[0160] Next, candidate subjects are selected by combining the number of fields of the matching number and the matching degree value.

[0161] The inclusion and exclusion criteria are automatically verified through smart contracts, generating a list of target subjects. Finally, through consensus verification by blockchain nodes, using the PBFT consensus algorithm, the list of target subjects is stored in the target subject smart contract, and the data relationships in the numbered directory smart contract are updated to ensure that already enrolled cases are excluded during subsequent screening.

[0162] In this embodiment of the application, the blockchain network is used to determine multiple candidate subjects based on the matching number of each subject, the number of matching fields corresponding to the matching number, and multiple matching degree values, specifically for:

[0163] Based on multiple matching scores, a target number is determined from the target number directory;

[0164] Based on the matching number of each subject, the number of matching fields corresponding to the matching number, and the target number, multiple initial subjects are determined;

[0165] Based on the number of matching fields for each initial subject, the medication time difference, and the semantic similarity between the case text of each initial subject and the feature query conditions, a weighted matching degree for each initial subject is calculated. The medication time difference represents the difference between the historical medication time and the time of the target trial protocol.

[0166] Based on the weighted matching degree of each initial subject, multiple candidate subjects are identified.

[0167] By employing a dynamic determination mechanism based on target IDs, combined with matching IDs and the number of fields, the system quickly identifies the initial subject population highly correlated with the feature query conditions, improving basic screening efficiency. Introducing medication time difference as a key parameter quantifies the temporal correlation between historical medication and the trial protocol, avoiding the impact of drug interference on trial results and significantly improving the scientific rigor of the screening. By integrating semantic similarity analysis of case texts and query conditions, the system ensures the semantic accuracy of feature associations. Finally, by weighted fusion of the number of matching fields, medication time difference, and semantic similarity, the system achieves objectivity and comprehensiveness in ranking candidate subjects.

[0168] Figure 2 A flowchart illustrating a blockchain-based clinical trial subject management method is shown.

[0169] like Figure 2 As shown, a blockchain-based method for managing clinical trial participants mainly includes:

[0170] S201, the edge computing node acquires the medical records of each subject in the medical institution, the medical records including structured and unstructured data; for each subject's medical records, feature extraction is performed on the medical records to obtain feature information; based on the feature information and a preset mapping method, the subject's structured feature information is determined; the structured feature information of each subject is homomorphically encrypted to obtain multiple encrypted feature information; the multiple encrypted feature information is sent to the blockchain network;

[0171] S202, the edge computing node obtains the target test plan, generates feature query conditions based on the target test plan, and sends the feature query conditions to the blockchain network to filter multiple target subjects corresponding to the target test plan based on the blockchain network;

[0172] S203, for each target subject, the edge computing node acquires the target subject's indicator data, the indicator data representing vital sign data; determines trial information based on the indicator data, the trial information including normal trial information or abnormal trial information; and determines the target subject's follow-up questionnaire and nursing staff information based on the trial information.

[0173] S204, for each target subject, the edge computing node acquires the target subject's behavioral information and trial requirement information, predicts the follow-up time based on the target subject's behavioral information and trial requirement information, generates a follow-up plan based on the follow-up time and trial information, and pushes the follow-up questionnaire to the target subject;

[0174] S205, the blockchain network stores the encrypted feature information of the subjects in each of the medical institutions, and initiates the corresponding smart contract template based on the feature query conditions. The smart contract template includes a dynamic matching contract, an informed consent contract, and a dynamic quota contract.

[0175] Figure 3 This is a structural block diagram of an electronic device 300 according to an embodiment of this application.

[0176] like Figure 3 As shown, the electronic device 300 includes a processor 301 and a memory 302, and may further include one or more of an information input / output (I / O) interface 303, a communication component 304, and a communication bus 305.

[0177] The processor 301 controls the overall operation of the electronic device 300 to complete all or part of the steps in the blockchain-based clinical trial subject management method described above. The memory 302 stores various types of data to support the operation of the electronic device 300. This data may include, for example, instructions for any application or method operating on the electronic device 300, as well as application-related data. The memory 302 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as one or more of Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0178] I / O interface 303 provides an interface between processor 301 and other interface modules, such as keyboards, mice, and buttons. These buttons can be virtual or physical. Communication component 304 is used to test wired or wireless communication between electronic device 300 and other devices. Wireless communication includes Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination thereof. Therefore, the corresponding communication component 304 may include a Wi-Fi component, a Bluetooth component, and an NFC component.

[0179] The communication bus 305 may include a path for transmitting information between the aforementioned components. The communication bus 305 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus 305 may be divided into an address bus, a data bus, a control bus, etc.

[0180] The electronic device 300 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to execute a blockchain-based clinical trial subject management method given in the above embodiments.

[0181] The following describes the computer-readable storage medium provided in the embodiments of this application. The computer-readable storage medium described below can be referred to in conjunction with the blockchain-based clinical trial subject management method described above.

[0182] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the blockchain-based clinical trial subject management method described above.

[0183] The computer-readable storage medium may include various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0184] The terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0185] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the foregoing application concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions claimed in this application.

Claims

1. A blockchain-based clinical trial subject management system, characterized in that, It includes a blockchain network and multiple edge computing nodes, which are deployed in various medical institutions. The blockchain network is deployed with smart contract templates, including screening contracts. Each of the aforementioned edge computing nodes includes: A data processing module is used to acquire the medical records of each subject in the medical institution, the medical records including structured and unstructured data; for each subject's medical records, feature extraction is performed on the medical records to obtain feature information; based on the feature information and a preset mapping method, the structured feature information of the subject is determined; the structured feature information of each subject is homomorphically encrypted to obtain multiple encrypted feature information; and the multiple encrypted feature information is sent to the blockchain network. The subject screening module is used to obtain the target trial protocol, generate feature query conditions based on the target trial protocol, and send the feature query conditions to the blockchain network to screen multiple target subjects corresponding to the target trial protocol based on the blockchain network. The subject monitoring module is used to acquire indicator data for each target subject, the indicator data representing vital sign data; determine trial information based on the indicator data, the trial information including normal trial information or abnormal trial information; and determine the follow-up questionnaire and nursing information for the target subject based on the trial information. The follow-up management module is used to acquire behavioral information and trial requirement information of each target subject, predict the follow-up time based on the behavioral information and trial requirement information, generate a follow-up plan based on the follow-up time and trial information, and push the follow-up questionnaire to the target subject. The blockchain network is used to store the encrypted feature information of the subjects in each of the medical institutions, and to activate the corresponding smart contract template based on the feature query conditions to screen multiple target subjects corresponding to the target trial plan. The blockchain network, used to initiate corresponding smart contract templates based on feature query conditions to screen multiple target subjects corresponding to the target experimental protocol, is specifically used for: Obtain a number directory from a preset number directory smart contract. The number directory includes multiple numbers, each number corresponds to multiple data names, each data name represents a case name, and each data name is associated with at least one first keyword set. Based on the encrypted feature information and number directory of each subject, determine the matching number of each subject and the number of matching fields corresponding to the matching number; Based on the feature query conditions, determine the set of second keywords; The second keyword set is matched with the first keyword set associated with each of the data names, and multiple matching degree values ​​are calculated; Based on the matching number of each subject, the number of matching fields corresponding to the matching number, and multiple matching degree values, multiple candidate subjects are determined; Based on the inclusion and exclusion criteria of the target trial protocol, multiple candidate subjects are screened to generate a target subject list. The inclusion and exclusion criteria represent the conditions that subjects must meet and the conditions that must be excluded. After verifying the consensus of the target subject list, the data is stored in the target subject smart contract and the data association in the numbered directory smart contract is updated to obtain multiple target subjects.

2. The blockchain-based clinical trial subject management system according to claim 1, characterized in that, The subject monitoring module, when determining the follow-up questionnaire of the target subject based on the trial information, is specifically used for: Based on the trial information of the target subjects, the basic information of the questionnaire is determined, which includes the target subject's identity information, trial stage, trial type, clinical indicators, behavioral characteristics, and risk level. Keyword features are extracted from the basic information of the questionnaire to obtain multiple keywords of the basic information of the questionnaire; Based on the number of each keyword and the preset ratio, the questionnaire theme and questionnaire content are determined; Based on the target subject's identity information, the questionnaire type is determined. The target subject's identity information includes age, behavioral ability, and cognitive ability. The questionnaire type includes paper questionnaires with different font sizes and word explanation levels, and voice questionnaires with different word explanation levels. Based on the questionnaire type, several recommended packaging templates were determined; Based on the usage frequency of each recommended packaging template, a first weight is determined for each of the recommended packaging templates; Based on the target subjects' historical usage frequency of each of the recommended packaging templates, a second weight for each of the recommended packaging templates is determined; Based on the mid-term dropout rate of the questionnaire corresponding to each of the recommended packaging templates, a third weight is determined for each of the recommended packaging templates; The disease response coefficient is determined based on the trial information of the target subjects, and the fourth weight of each of the recommended packaging templates is determined based on the disease response coefficient. The target packaging template is determined based on the first weight, second weight, third weight, and fourth weight of each of the recommended packaging templates; Based on the questionnaire topic, the questionnaire content, the questionnaire type, and the target packaging template, a follow-up questionnaire is generated.

3. The blockchain-based clinical trial subject management system according to claim 2, characterized in that, The subject monitoring module, when determining the target subject's care information based on the trial information, is specifically used for: Based on the experimental information and the preset K-means clustering model, the category level of the target subjects is determined; Based on the category level of the target subjects, nursing needs are determined, including the frequency of nursing care. Based on the target subjects' historical nursing records and trial phases, predict the nursing time and duration for the target subjects within the target time interval; Based on the location of the target subject, multiple management personnel are matched within the current medical institution; Based on preset matching rules and multiple managers of the current medical institution, the nursing staff of the target subject are determined, and nursing information is determined based on the nursing time, nursing duration and nursing staff.

4. The blockchain-based clinical trial subject management system according to claim 3, characterized in that, The subject monitoring module, based on preset matching rules and multiple managers within the current medical institution, determines the caregivers for the target subject, including: Obtain the current subject information corresponding to each of the aforementioned managers, wherein the current subject information includes the location, nursing time, and nursing duration of the subject to be treated, as well as the location, nursing time, and nursing duration of the currently managed subject; Based on the timeliness information of each manager in the historical time period and the current subject information corresponding to each manager, the multiple managers are screened to obtain multiple first managers; Based on the nursing time and duration of the target subject and the current subject information corresponding to each of the first management personnel, the multiple first management personnel are screened to obtain multiple second management personnel; Based on the location of the target subject and the current subject information corresponding to each second manager, a distance coefficient for each second manager is determined; Based on the distance coefficient of each second manager, a first priority value is determined for each second manager; Based on the historical care information of each second manager, the degree of match between each second manager and the target subject in terms of trial type and trial phase is determined; A second priority value is determined for each second manager based on the degree of match between each second manager and the target subject in terms of trial type and trial phase; Based on the number of errors made by each second manager within a historical time period, a third priority value is determined for each second manager; Based on the matching degree between each second manager and the subject, a fourth priority value is determined for each second manager; The caregivers for the target subjects are determined based on the first priority value, second priority value, third priority value, and fourth priority value of each second manager.

5. A blockchain-based clinical trial subject management system according to claim 1, characterized in that, The follow-up management module is specifically used for: Obtain the location information of the target subject; Based on the target subject's location information and the target subject's historical behavioral data, predict the target subject's location; Based on the behavioral information of the target subjects, the trial requirements information, the historical behavioral data of the target subjects, and the LSTM model, the initial follow-up time is predicted; The initial follow-up time is adjusted based on the predicted location of the target subject to obtain the target follow-up time for the target subject; Based on the target follow-up time and trial information, a follow-up plan is generated and sent to the target subjects.

6. The blockchain-based clinical trial subject management system according to claim 1, characterized in that, The blockchain network is used to determine multiple candidate subjects based on each subject's matching number, the number of matching fields corresponding to the matching number, and multiple matching degree values, specifically for: Based on multiple matching scores, the target number is determined from the target number directory; Based on the matching number of each subject, the number of matching fields corresponding to the matching number, and the target number, multiple initial subjects are determined; Based on the number of matching fields for each initial subject, the medication time difference, and the semantic similarity between the case text of each initial subject and the feature query conditions, a weighted matching degree for each initial subject is calculated. The medication time difference represents the difference between the historical medication time and the time of the target trial protocol. Based on the weighted matching degree of each initial subject, multiple candidate subjects are identified.

7. A blockchain-based method for managing clinical trial subjects, characterized in that, include: Edge computing nodes acquire medical records of each subject in a medical institution, the medical records including structured and unstructured data; for each subject's medical records, feature extraction is performed on the medical records to obtain feature information; based on the feature information and a preset mapping method, the subject's structured feature information is determined; the structured feature information of each subject is homomorphically encrypted to obtain multiple encrypted feature information; the multiple encrypted feature information is sent to a blockchain network; An edge computing node acquires a target trial plan, generates feature query conditions based on the target trial plan, and sends the feature query conditions to the blockchain network to filter multiple target subjects corresponding to the target trial plan based on the blockchain network. For each target subject, the edge computing node acquires the target subject's indicator data, which represents vital sign data; determines trial information based on the indicator data, which includes normal or abnormal trial information; and determines the target subject's follow-up questionnaire and caregiver information based on the trial information. For each target subject, the edge computing node acquires the target subject's behavioral information and trial requirement information, predicts the follow-up time based on the target subject's behavioral information and trial requirement information, generates a follow-up plan based on the follow-up time and trial information, and pushes the follow-up questionnaire to the target subject; The blockchain network stores the encrypted feature information of the subjects in each of the medical institutions, and initiates corresponding smart contract templates based on feature query conditions. The smart contract templates include screening contracts, dynamic quota contracts, and informed consent contracts. The blockchain network initiates a corresponding smart contract template based on feature query conditions to screen multiple target subjects corresponding to the target experimental protocol, including: Obtain a number directory from a preset number directory smart contract. The number directory includes multiple numbers, each number corresponds to multiple data names, each data name represents a case name, and each data name is associated with at least one first keyword set. Based on the encrypted feature information and number directory of each subject, determine the matching number of each subject and the number of matching fields corresponding to the matching number; Based on the feature query conditions, determine the set of second keywords; The second keyword set is matched with the first keyword set associated with each of the data names, and multiple matching degree values ​​are calculated; Based on the matching number of each subject, the number of matching fields corresponding to the matching number, and multiple matching degree values, multiple candidate subjects are determined; Based on the inclusion and exclusion criteria of the target trial protocol, multiple candidate subjects are screened to generate a target subject list. The inclusion and exclusion criteria represent the conditions that subjects must meet and the conditions that must be excluded. After verifying the consensus of the target subject list, the data is stored in the target subject smart contract and the data association in the numbered directory smart contract is updated to obtain multiple target subjects.

8. An electronic device, characterized in that, Includes a processor, which is coupled to a memory; The processor is configured to execute a computer program stored in the memory, so that the electronic device performs the method as described in claim 7.

9. A computer-readable storage medium, characterized in that, The computer program is stored and can be loaded by a processor and executed as described in claim 7, which is a blockchain-based clinical trial subject management method.

Images