Research object determination method and device, electronic equipment and medium

Abstract

The invention relates to the field of medical data processing, in particular to a research object determination method and device, electronic equipment and a medium. The method comprises the following steps: acquiring description information of candidate objects; performing first review on the candidate object according to the description information, and determining the candidate object as an alternative research object of the target disease research project under the condition that a review result of the first review indicates that the candidate object is qualified; interaction information is sent to the alternative research objects, the interaction information is used for obtaining symptom information input by the alternative research objects, and the symptom information is used for representing physical symptoms of the candidate objects; and according to the symptom information, performing second review on the alternative research object, and determining the alternative research object as the research object of the target disease research project under the condition that the review result of the second review indicates that the alternative research object is qualified. Therefore, the subjectivity in the research object determination process is effectively reduced, and the research object matching degree and the determination accuracy are improved.

Description

Technical Field

[0001] The present invention relates to the field of medical data processing, and in particular to a method, device, electronic equipment and medium for determining a research object. Background Art

[0002] The existing methods for determining clinical research subjects (i.e., disease patients), especially in the recruitment process of subjects for TCM chronic disease research, mainly rely on doctors' recommendations or hospitals to recruit patient candidates, that is, they rely on the subjective judgment of relevant personnel to determine the research subjects, resulting in low accuracy in the determination of research subjects, and it is difficult for disease research projects to obtain suitable and matched patients to participate in related research. Summary of the Invention

[0003] Embodiments of the present invention provide a method, apparatus, electronic device, and medium for determining a research subject, aiming to improve the accuracy of determining the research subject of a disease research project.

[0004] In a first aspect, an embodiment of the present application provides a method for determining a research object, the method comprising:

[0005] Get the description information of the candidate object;

[0006] performing a first review of the candidate subject based on the descriptive information, and determining the candidate subject as a candidate research subject for a target disease research project if a review result of the first review indicates that the candidate subject is qualified;

[0007] Sending interaction information to the candidate research subject, wherein the interaction information is used to obtain symptom information input by the candidate research subject, wherein the symptom information is used to characterize the physical symptoms of the candidate subject;

[0008] A second review is performed on the candidate research subject based on the symptom information. When the review result of the second review indicates that the candidate research subject is qualified, the candidate research subject is determined as the research subject of the target disease research project.

[0009] In some embodiments, the descriptive information includes first descriptive information regarding the candidate subject's physical symptoms, the first descriptive information including first sub-information in multiple dimensions, and the first review of the candidate subject based on the descriptive information includes:

[0010] For each piece of first sub-information, multiply the information score of the first sub-information by the dimension weight of the dimension to which the first sub-information belongs, to obtain a first product, wherein the information score and the dimension weight are pre-configured;

[0011] determining a first score of the candidate object based on a plurality of the first products;

[0012] A first review is performed on the candidate object according to the first score.

[0013] In some embodiments, the symptom information includes second sub-information of multiple dimensions, and performing a second review of the candidate research subject based on the symptom information includes:

[0014] For each second sub-information, multiply the information score of the second sub-information by the dimension weight of the dimension to which the second sub-information belongs, to obtain a second product, wherein the information score and the dimension weight are pre-configured;

[0015] determining a second score for the candidate research subject based on the plurality of second products;

[0016] Determining the disease type and disease severity level of the candidate research subject based on the second score;

[0017] A second review is conducted on the candidate research subjects based on the disease type and the severity of the disease.

[0018] In some embodiments, the second review of the candidate research subjects based on the disease type and the disease severity level includes:

[0019] Obtaining medical history information and drug use information of the candidate research subjects;

[0020] Determining whether the candidate research subject meets the preset exclusion criteria based on the medical history information and the drug use information;

[0021] In the case that the candidate research subject does not meet the preset exclusion criteria, a second review is conducted on the candidate research subject based on the disease type and the severity level of the disease.

[0022] In some embodiments, the method further comprises:

[0023] In the case that the candidate research subject meets the preset exclusion criteria, a third review is performed on the symptom information of the candidate research subject to determine whether the candidate research subject is a research subject for other disease research projects.

[0024] In some embodiments, obtaining description information of the candidate object includes:

[0025] Obtaining original description information of the candidate subject, wherein the original description information includes the identity information and condition description information of the candidate subject;

[0026] Determining, based on the identity information, whether the candidate subject has served as a research subject for the target disease research project;

[0027] In the case that the candidate subject has never been a research subject of the target disease research project, term conversion is performed on the condition description information to convert the condition description information into common terms for symptom description to obtain the description information.

[0028] In some embodiments, after determining that the candidate research subject is a research subject for the target disease, the method further comprises:

[0029] Collecting physical condition information of the research subject;

[0030] Based on the physical condition information, a modification suggestion is output for a research step on the target disease.

[0031] In a second aspect, an embodiment of the present application provides a device for determining a research object, the device comprising:

[0032] An acquisition module is used to obtain description information of candidate objects;

[0033] a first review module, configured to perform a first review on the candidate subject according to the description information, and determine the candidate subject as a candidate research subject for a target disease research project if a review result of the first review indicates that the candidate subject is qualified;

[0034] a sending module, configured to send interaction information to the candidate research subject, wherein the interaction information is used to obtain symptom information input by the candidate research subject, wherein the symptom information is used to characterize the physical symptoms of the candidate subject;

[0035] The second review module is used to perform a second review on the candidate research subject based on the symptom information, and determine the candidate research subject as the research subject of the target disease research project when the review result of the second review indicates that the candidate research subject is qualified.

[0036] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;

[0037] Memory for storing computer programs;

[0038] The processor is used to implement the steps of the research object determination method provided in the first aspect of the embodiment of the present application when executing the program stored in the memory.

[0039] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the research object determination method provided in the first aspect of the embodiment of the present application.

[0040] In an embodiment of the present application, the processor first obtains the descriptive information of the candidate object and performs a first review based on the descriptive information. When the result of the first review indicates that the candidate object is qualified, it is confirmed as an alternative research object for the target disease research project. Subsequently, interactive information is sent to the alternative research object to obtain the symptom information input by it, and then a second review is performed based on the symptom information. When the result of the second review indicates that the candidate research object is qualified, it is finally determined to be a research object. In this way, compared with the traditional method of relying on the subjective judgment of doctors or hospital recruitment, through multiple rounds of objective and standard fixed descriptive information review and symptom information review, the subjectivity in the research object determination process is effectively reduced, the matching degree and determination accuracy of the research object are improved, and the problem of difficulty in obtaining suitable patients in existing disease research projects, especially in clinical research on chronic diseases of traditional Chinese medicine, is solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0042] Figure 1 Schematic diagram of the process of determining the research object provided in the embodiment of the present application;

[0043] Figure 2 yes Figure 1 Flow diagram of step S200;

[0044] Figure 3 yes Figure 1 Flow diagram of step S400;

[0045] Figure 4 Schematic diagram of the structure of the research object determination device provided in an embodiment of the present application;

[0046] Figure 5 It is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0047] The following will be combined with the accompanying drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of this application.

[0048] The terms "first," "second," and the like in the specification and claims of this application are used to distinguish similar objects, and are not used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of this application can be implemented in an order other than that illustrated or described herein, and that the objects distinguished by "first," "second," and the like are generally of the same type, and do not limit the number of objects; for example, the first object can be one or more. In addition, the term "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0049] The following, in conjunction with the accompanying drawings, describes in detail the research object determination method, device, electronic device and medium provided in the embodiments of the present application through specific embodiments and their application scenarios.

[0050] Figure 1 This is a flow chart of the method for determining the research object provided in the embodiment of the present application. Figure 1 As shown, the first aspect of the embodiment of the present application provides a method for determining a research object, including the following steps S100 to S400:

[0051] Step S100: Obtain description information of candidate objects.

[0052] In this step, the processor collects descriptive information from potential participants, i.e., candidate subjects, through a pre-designed collection portal (e.g., a mobile application, a web registration form, an offline questionnaire, or a patient information database). Those skilled in the art will appreciate that there may be multiple candidate subjects, and the processor simultaneously obtains descriptive information for multiple candidate subjects and screens the multiple candidate subjects based on this descriptive information.

[0053] Descriptive information may include demographic information (such as name, gender, and age), identity information (name and ID number), contact information (such as mobile phone number and email address), medical history (such as chronic disease diagnosis, surgical history, allergy history, and medication history), lifestyle habits (such as smoking and drinking habits), and basic descriptions of the condition or symptoms (such as whether there are any obvious physical discomforts at present). The processor will perform necessary preprocessing on the directly collected information to obtain the above descriptive information.

[0054] For example, a candidate fills in the following information on the mobile terminal:

[0055] Name: Zhang

[0056] Gender: Female

[0057] Age: 52

[0058] Contact information: Mobile phone number 138xxxx1234

[0059] Past medical history: hypertension (diagnosed in 2021), mild anxiety;

[0060] Main symptoms: "Insomnia" in the past six months, accompanied by "frequent heart palpitations";

[0061] Lifestyle habits: occasional drinking, no smoking history;

[0062] After the processor obtains the above information, it desensitizes the mobile phone number (such as displaying it as 138****1234) to protect the privacy of the candidate, corrects "can't sleep" to "insomnia", and classifies "heart palpitations" as the standard Chinese medicine term "heart palpitations", and saves it as the complete description information of the candidate.

[0063] Step S200: performing a first review on the candidate subject according to the description information, and determining the candidate subject as a candidate research subject for the target disease research project if the review result of the first review indicates that the candidate subject is qualified.

[0064] In this step, the processor performs a first review of the candidate subject based on the descriptive information. If the result of the first review indicates that the candidate subject is qualified, the candidate subject is determined to be a candidate research subject for the target disease research project. Specifically, the processor uses the standardized descriptive information obtained in the previous step and reviews the descriptive information according to the review criteria of the target disease research project.

[0065] Specifically, the review criteria for the first review may include preliminary inclusion / exclusion criteria, that is, technicians may define a set of "inclusion criteria" and "exclusion criteria" for the target disease in advance, such as:

[0066] Inclusion criteria: Age between 18 and 65 years old; no severe liver and kidney damage; presence of relevant TCM syndrome characteristics (such as "liver depression and qi stagnation syndrome" and "blood deficiency syndrome");

[0067] Exclusion criteria: pregnant or breastfeeding women; women with a clear history of severe mental illness (such as schizophrenia, major depression with suicide attempts); patients undergoing other clinical studies concurrently; patients who have recently (within 3 months) received similar experimental drug treatment.

[0068] The processor submits the candidate subject to the rule engine composed of the aforementioned inclusion and exclusion criteria, automatically comparing its description information to see if it complies with the aforementioned rules. If it meets all inclusion criteria and none of the exclusion criteria, it is deemed qualified and automatically marked as a candidate for research. Otherwise, the subject is placed in the ineligible candidate pool or referred to relevant professionals for a second evaluation.

[0069] For example, the processor reads Zhang's description information from:

[0070] Aged 52, meeting the age range of "18 to 65";

[0071] Past medical history: hypertension (controlled with medication, normal renal function on angiography), mild anxiety, but no history of severe psychiatric illness;

[0072] Main symptoms: insomnia and palpitations are consistent with the TCM syndrome characteristics of chronic insomnia with deficiency of both heart and spleen;

[0073] Lifestyle habits: Occasional drinking, no major bad habits.

[0074] The processor determined that Zhang was neither pregnant or breastfeeding nor participating in other clinical studies. Furthermore, her age and basic physical characteristics met the inclusion criteria and did not meet any exclusion criteria. Therefore, after conducting the aforementioned first review, the processor determined Zhang qualified and changed her status from a candidate to an alternate research subject.

[0075] Step S300: sending interactive information to the candidate research subject, where the interactive information is used to obtain symptom information input by the candidate research subject, and the symptom information is used to characterize the physical symptoms of the candidate subject.

[0076] In this step, for the candidate research subjects that have passed the first review and are marked as candidates, the processor needs to further obtain more detailed and structured symptom information. To this end, the processor can send interactive information to the candidate research subjects in the following ways:

[0077] Push channels: This may include SMS push, in-app messaging, email, or WeChat official account customer service chat. The message content will include a clickable link or QR code to guide the candidate research subjects to fill out a standardized symptom questionnaire;

[0078] Interactive content: The symptom questionnaire is pre-designed as multiple-choice + fill-in-the-blank questions, with the purpose of collecting the core symptom dimensions required for the target disease research project (such as onset time, duration of disease, symptom severity score, accompanying physical signs, etc.). For example:

[0079] "Please select the symptoms of insomnia you have experienced in the past month from the following options: 1. Occasional difficulty falling asleep; 2. Frequently waking up in the early morning; 3. Trouble sleeping all night; 4. Occasionally able to fall asleep but waking up easily" etc.

[0080] After the processor receives the symptom information submitted by the candidate research subject, it can be stored in a structured manner (eg, each field has a timestamp, value / option number), providing a basis for the subsequent second review.

[0081] For example, the processor sends an App push message to Zhang, the content of which is as follows:

[0082] Dear Ms. Zhang, you have passed the first round of screening. Please click the link below to complete the detailed insomnia and related symptom questionnaire so that we can further assess whether you meet the final inclusion criteria. Link:…

[0083] Thank you for your cooperation.”

[0084] After Zhang clicked the link, he entered the symptom information filling interface and selected the following symptom options from the multiple-choice options:

[0085] Insomnia in the past six months: It takes an average of 1.5 hours to fall asleep every night, usually at 2 a.m.

[0086] Average sleep duration: only 3 to 4 hours a day;

[0087] Accompanied by palpitations: occurring every morning for the past two weeks and lasting about 30 minutes;

[0088] Mental state: Occasionally experienced anxiety and irritability, but did not take anti-anxiety drugs;

[0089] Diet: Appetite is good, no obvious indigestion.

[0090] The processor archives all the above answers according to preset fields to form a symptom information data packet.

[0091] Step S400: Based on the symptom information, a second review is conducted on the candidate research subject. If the review result of the second review indicates that the candidate research subject is qualified, the candidate research subject is determined as the research subject of the target disease research project.

[0092] In this step, the processor compares the acquired symptom information with the project's in-depth inclusion / exclusion criteria to ensure that the selected subjects not only meet the initial requirements at the descriptive level, but also that the intensity and characteristics of their clinical manifestations (or self-reported symptoms) meet the requirements of the study design. Specifically, technicians can further configure detailed inclusion / exclusion criteria for the target disease research project. These criteria can be quantitative and focus on the severity, duration, accompanying signs, laboratory test results, or imaging indicators of specific symptoms.

[0093] The processor can calculate scores for each item in the symptom information and preliminarily determine whether the candidate meets the inclusion criteria for the secondary review. If so, the processor will mark the candidate research subject as qualified and automatically convert the candidate research subject into a research subject for the officially confirmed target disease research project. Alternatively, the processor can push their information to the manual review module for further review by a professional Chinese medicine practitioner or research coordinator. Only after confirmation can they be finally determined as research subjects for the target disease research project. The processor can inform the research subjects of the completed target disease research project of the study start time, research process, precautions, and potential benefits via email or app push.

[0094] In this way, through the above steps S100-S400, the processor first obtains the descriptive information of the candidate object and performs a first review based on the descriptive information. When the first review result indicates that the candidate object is qualified, it is confirmed as an alternative research object for the target disease research project. Subsequently, interactive information is sent to the alternative research object to obtain the symptom information input by it, and then a second review is performed based on the symptom information. When the second review result indicates that the alternative research object is qualified, it is finally determined as a research object. In this way, compared with the traditional method of relying on the subjective judgment of doctors or hospital recruitment, through multiple rounds of objective and standard fixed descriptive information review and symptom information review, the subjectivity in the research object determination process is effectively reduced, the matching degree and determination accuracy of the research objects are improved, and the problem of difficulty in obtaining suitable patients in existing disease research projects, especially in clinical research on chronic diseases of traditional Chinese medicine, is solved.

[0095] The research subjects determined through steps 100 to S400 above can subsequently be used as subjects for disease treatment in target disease research projects. Key information such as demographic information, past medical history, and lifestyle habits in the descriptive information collected during the research subject determination process can be combined with the research subject's laboratory test information to be used in a machine learning model to predict the effect of disease treatment. Those skilled in the art will appreciate that the key information such as demographic information, past medical history, and lifestyle habits in the descriptive information collected during the research subject determination process, as well as the research subject's laboratory test information, can be used as components of the machine model's training set, and can also be used as model inputs for obtaining prediction results after the machine learning model training is completed.

[0096] Specifically, the processor first needs to obtain key information such as demographic information, medical history, and lifestyle habits from the descriptive information collected from multiple research subjects, as well as laboratory test data including blood pressure, heart rate, renal function, liver function, electrolytes, blood sugar, and blood lipids. At the same time, the processor can also record the patient's disease course characteristics, concomitant medication status, and lifestyle-related factors such as eating habits and exercise frequency.

[0097] Next, the processor can perform preprocessing and feature engineering on the raw data composed of the above information according to the settings of the technicians, such as filling missing values, normalizing or standardizing continuous variables, and one-hot encoding categorical variables. It may also introduce some derived features, such as previous treatment response time and biochemical index change rate, to improve the predictive ability of the model. The processor also needs to use the treatment effect (such as cure probability, remission probability) to annotate the raw data after preprocessing and feature processing.

[0098] The processor then divides the processed data into training and test sets. The machine learning models that can be selected include logistic regression, linear regression, decision tree, random forest, support vector machine (SVM), etc. Multiple models can be trained in parallel and hyperparameters can be optimized through cross-validation, grid search and other technologies to select the model with the best performance in the test set.

[0099] Ultimately, the processor inputs key information from the new research subject's descriptive information, including demographic information, medical history, and lifestyle habits, along with laboratory test data including blood pressure, heart rate, renal function, liver function, electrolytes, blood sugar, and blood lipids, into the selected model. This allows the processor to calculate the probability that the research subject will achieve the desired therapeutic effect (such as complete symptom relief, achievement of target indicators, or stable condition) after receiving a specific treatment regimen (e.g., the model predicts an 85% probability of complete relief for a 50-year-old male with chronic insomnia after eight weeks of treatment with 10g / day of Shengjiang San). In actual applications, clinicians can stratify research subjects into high, medium, and low risk categories based on the probability output by the model, and then develop personalized follow-up and adjustment plans.

[0100] Figure 2 yes Figure 1 The flow chart of step S200 is as follows: Figure 2 As shown, in some embodiments, the description information includes first description information of the candidate subject's physical symptoms, the first description information includes first sub-information of multiple dimensions, and a first review of the candidate subject is performed based on the description information (step S200), including:

[0101] Step S210: For each first sub-information, multiply the information score of the first sub-information by the dimension weight of the dimension to which the first sub-information belongs to obtain a first product, wherein the information score and the dimension weight are pre-configured;

[0102] Step S220: determining a first score of the candidate object based on the multiple first products;

[0103] Step S230: Perform a first review of the candidate objects based on the first scores.

[0104] In this embodiment, the descriptive information not only includes the first descriptive information of the candidate object but also includes the first descriptive information for the candidate object's physical symptoms, wherein the first descriptive information is further subdivided into first sub-information of multiple dimensions, and each first sub-information represents the degree of performance of the candidate object in a certain symptom dimension. For example, if the research project focuses on candidates with chronic insomnia accompanied by deficiency of both heart and spleen, the first descriptive information may include dimensions such as time taken to fall asleep, sleep duration, number of awakenings at night, etc., and the first sub-information under each dimension is composed of options selected by the candidate object (such as time taken to fall asleep every day, total actual sleep duration per night, number of awakenings at night). The processor pre-configures an information score and a dimension weight of the dimension to which it belongs for each first sub-information - the information score is used to quantify the candidate's specific situation on the sub-information, and the dimension weight is used to identify the importance of the sub-information in the overall evaluation.

[0105] During the first review of a candidate, the processor first reads the corresponding information score and the dimension weight of each sub-information item and calculates the first product. This product multiplies the information score by the dimension weight to reflect the contribution of the sub-information item to the candidate's overall assessment. For example, if the "Time to Fall Asleep" information score is 3 points and the corresponding dimension weight is 0.4, the first product for this sub-information item is 1.2.

[0106] After performing the same calculation on all first sub-information, the processor adds up all first products to obtain a first score for the candidate. Finally, the processor compares the first score with a pre-set score threshold (i.e., the inclusion / exclusion criteria are quantified as the score threshold) to determine whether the candidate is qualified.

[0107] Those skilled in the art will appreciate that, in addition to the first description information, the description information may also include demographic information, medical history information, and lifestyle information of the candidate, etc., and this information may be used together with the first description information for the first review.

[0108] For example, the target disease research project needs to screen candidates for chronic insomnia accompanied by deficiency of both heart and spleen, where the first description information defines the first sub-information of three dimensions:

[0109] Time to fall asleep (dimension A): The average time required to fall asleep as reported by the candidate;

[0110] Sleep duration (dimension B): The actual sleep duration per day reported by the candidate;

[0111] Number of nighttime awakenings (Dimension C): The number of times the candidate wakes up each night as reported by the candidate.

[0112] The processor pre-configures the dimension weights corresponding to each dimension: dimension A has a weight of 0.4, dimension B has a weight of 0.3, and dimension C has a weight of 0.3.

[0113] The first description of a candidate, Mr. Li, is:

[0114] Time taken to fall asleep: 1.5 hours on average (corresponding to an information score of 3 points);

[0115] Sleep duration: only 4 hours a day (corresponding to an information score of 2 points);

[0116] Number of nighttime awakenings: 3 times per night (corresponding to an information score of 4 points).

[0117] The processor calculates the first product of each first sub-information in turn: the first product of the time taken to fall asleep = 3 minutes × 0.4 = 1.2; the first product of the sleep duration = 2 minutes × 0.3 = 0.6; the first product of the number of awakenings at night = 4 minutes × 0.3 = 1.2.

[0118] Adding the three first products above yields Mr. Li's first score = 1.2 + 0.6 + 1.2 = 3.0. If the threshold score for inclusion in the first review of the research project is 2.5, and a score greater than the threshold meets the inclusion criteria, then Mr. Li's first score of 3.0 ≥ 2.5. The processor determines that Mr. Li has passed the first review and marks him as a candidate for the target disease research project.

[0119] Figure 3 yes Figure 1 The flow chart of step S400 is as follows: Figure 3 As shown, in some embodiments, the symptom information includes second sub-information of multiple dimensions. Based on the symptom information, a second review of the candidate research subject is performed (step S400), including:

[0120] Step S410: for each second sub-information, multiply the information score of the second sub-information by the dimension weight of the dimension to which the second sub-information belongs, to obtain a second product, wherein the information score and the dimension weight are pre-configured;

[0121] Step S420: determining a second score of the candidate research subject based on the multiple second products;

[0122] Step S430: Determine the disease type and disease severity level of the candidate research subject based on the second score;

[0123] Step S440: Conduct a second review of the candidate research subjects based on the disease type and disease severity level.

[0124] In this embodiment, symptom information is subdivided into multiple dimensions of secondary sub-information, each of which corresponds to the candidate's quantitative or qualitative performance on a specific clinical characteristic. The processor pre-configures each secondary sub-information with an information score and a dimension weight for the dimension to which it belongs. The information score quantifies the candidate's performance on that sub-information, while the dimension weight indicates the relative importance of that sub-information in the overall assessment.

[0125] During the second review, the processor reads the corresponding information score and dimension weight for each second sub-information, and calculates the second product of the sub-information (i.e., information score × dimension weight) to reflect the contribution value of the sub-information to the overall condition assessment of the candidate research subject. Subsequently, the processor adds up all the second products to obtain the second score of the candidate research subject. Based on the second score, the processor maps the disease type and disease severity level of the candidate research subject according to pre-set rules, for example, corresponding to different score intervals as mild insomnia with deficiency of both heart and spleen, moderate insomnia with insufficient qi and blood, or severe insomnia with excessive heart and liver fire, etc. Finally, the processor determines whether the alternative research subject has passed the second review and decides whether to include it as a research subject of the target disease research project based on whether the disease type corresponding to the alternative research subject meets the inclusion requirements of the target disease research project and whether the severity of the disease is within the allowable range (i.e., the inclusion criteria / exclusion criteria of the second review).

[0126] For example, the target disease research project is to study patients with chronic insomnia accompanied by deficiency of both heart and spleen. The processor defines four "second sub-information" dimensions:

[0127] Duration of insomnia (dimension A): measures the duration of insomnia in months;

[0128] The degree of impairment of daytime function (dimension B): the impact of insomnia on daily life was measured using a patient self-assessment scale (0–10 points);

[0129] Frequency of palpitations (dimension C): the frequency of palpitations in the past two weeks;

[0130] Tongue and pulse manifestations (Dimension D): Determine pale tongue, weak pulse, etc. through TCM syndrome differentiation.

[0131] The processor pre-sets the weights of each dimension as follows: Dimension A weight 0.35, Dimension B weight 0.25, Dimension C weight 0.20, Dimension D weight 0.20, and calibrates the information score ranges corresponding to different performances:

[0132] Duration of insomnia: 3 points for 3–6 months, 4 points for 6–12 months, and 5 points for more than 12 months;

[0133] Impaired daytime function: 0–2 points correspond to 1 point, 3–5 points correspond to 2 points, 6–8 points correspond to 3 points, and 9–10 points correspond to 4 points;

[0134] Frequency of palpitations: 1–2 times per week corresponds to 1 point, 3–5 times per week corresponds to 2 points, 6–10 times per week corresponds to 3 points, and more than 10 times per week corresponds to 4 points;

[0135] Tongue and pulse: Mild deficiency of both heart and spleen corresponds to 2 points, moderate deficiency corresponds to 3 points, and severe deficiency corresponds to 4 points.

[0136] The symptom information submitted by the candidate research subject, Ms. Wang, is as follows:

[0137] Duration of insomnia: has lasted for 10 months (corresponding to an information score of 4 points);

[0138] Impaired daytime function: self-assessment score 7 points (corresponding to information score 3 points);

[0139] Frequency of palpitations: 8 times in the past two weeks (corresponding to an information score of 3 points);

[0140] Tongue and pulse manifestations: moderate deficiency of both heart and spleen (corresponding information score 3 points).

[0141] The processor calculates the second products of each second sub-information in sequence: the second product of insomnia duration = 4 points × 0.35 = 1.40; the second product of daytime functional impairment = 3 points × 0.25 = 0.75; the second product of palpitations frequency = 3 points × 0.20 = 0.60; the second product of tongue and pulse manifestations = 3 points × 0.20 = 0.60;

[0142] The processor adds up all the above "second products" to obtain Ms. Wang's second score = 1.40 + 0.75 + 0.60 + 0.60 = 3.35.

[0143] If the "second score" is in the range of 3.0-3.9, it corresponds to "moderate insomnia with deficiency of both heart and spleen";

[0144] If the "second score" is ≥4.0, it corresponds to "severe insomnia with deficiency of both heart and spleen";

[0145] If the "second score" is <3.0, it is judged as "mild insomnia with deficiency of both heart and spleen" or ineligible for inclusion.

[0146] Therefore, Ms. Wang's second score of 3.35 fell within the 3.0–3.9 range, and the processor determined her condition to be moderate insomnia with heart and spleen deficiency, with a moderate severity level. The project study stipulated that only patients with moderate to severe insomnia with heart and spleen deficiency would be included, so Ms. Wang ultimately passed the second review and was selected as a research subject for the target disease research project.

[0147] In the above two embodiments, the processor achieves an objective and refined evaluation of candidate objects or alternative research objects through the "multi-dimensional quantitative scoring + weighted summary" method, improves the screening accuracy and consistency, and realizes the comprehensive consideration of multi-dimensional features.

[0148] In some embodiments, a second screening of candidate research subjects is performed based on the disease type and disease severity, including:

[0149] Obtain medical history and medication information of potential research subjects;

[0150] Determine whether the candidate research subjects meet the preset exclusion criteria based on medical history and drug use information;

[0151] If the candidate research subjects do not meet the preset exclusion criteria, a second review will be conducted on the candidate research subjects based on the type and severity of the disease.

[0152] In this embodiment, the processor can further obtain the medical history information and drug use information of individuals who have been marked as candidate research subjects (which can be obtained through input from the candidate research subjects or from the patient database), and use the two as one of the review bases for the second review.

[0153] Specifically, after the processor has used the symptom information to determine the disease type and corresponding disease severity level, or while determining the disease type and disease severity level, it compares the candidate research subject's medical history information and medication use information with the preset exclusion criteria to determine whether the candidate meets the project's preset exclusion criteria. For example, the research project may stipulate that if the candidate research subject has a history of severe heart disease, active hepatitis, or has recently used Chinese patent medicine or Western medicine that conflicts with the research protocol (such as sleep aids, vasodilators, etc.), he or she should be excluded.

[0154] The processor will first parse the medical history information (such as previous diagnosis, surgical records, allergy history) and drug use information (such as whether sleeping pills or antidepressants have been taken in the past three months, whether anticoagulant treatment is being taken, etc.) provided by the candidate research subject, and automatically compare the preset exclusion criteria list: If any one of the exclusion conditions is found, the processor will determine that the candidate research subject does not meet the preset exclusion criteria and directly remove it from the candidate pool of research subjects; only when it does not touch any exclusion items, the processor will continue to conduct a second review based on the previously determined disease type and disease severity level to determine whether it truly meets the requirements for formal inclusion in this target disease research project.

[0155] If it is determined that the candidate research subject meets the preset exclusion criteria, the processor can notify the candidate research subject by email to undergo disease diagnosis and treatment, or add him / her to the exclusion queue. Later, when reviewing subjects for other disease research projects, the subjects in the exclusion queue will be directly screened out.

[0156] In this way, the processor can further eliminate subjects with potential safety risks or drug conflicts by checking the medical history and medication status of the alternative research subjects before the second review, ensuring that the final included subjects meet the requirements of disease type and severity level as well as the safety standards in terms of medication and medical history.

[0157] For example, the target disease research project focuses on chronic insomnia with heart and spleen deficiency. The candidate research subject, Mr. Zhang, is labeled as: Disease Type - Moderate Insomnia with Heart and Spleen Deficiency, Disease Severity - Moderate. The processor simultaneously obtains Mr. Zhang's medical history and medication information (obtained from the questionnaire Mr. Zhang submitted and the patient database), and obtains the following information:

[0158] Medical history information: Mr. Zhang was previously diagnosed with premature heart beats, but had no history of liver or kidney damage;

[0159] Medication usage information: Currently taking 20mg of atorvastatin orally daily to control blood lipids; has not taken any sleeping pills, Chinese patent medicines or psychiatric drugs in the past two months.

[0160] The processor compares the above medical history information and drug use information with the project's preset exclusion criteria:

[0161] One of the pre-set exclusion criteria is a history of severe heart disease. Although Mr. Zhang has a history of premature heart beats, his condition is currently under stable control and does not constitute a severe heart disease (such as heart failure or myocardial infarction). Therefore, he is not excluded.

[0162] The second pre-set exclusion criterion was: recent use of hypnotics or antidepressants that conflicted with the study. Mr. Zhang had not taken any hypnotics or antidepressants in the past two months, so this did not constitute an exclusion.

[0163] Other exclusion criteria (such as active hepatitis, severe renal impairment, etc.) Mr. Zhang has no related diseases and is not subject to exclusion.

[0164] Since Mr. Zhang's medical history and medication usage information did not meet any pre-defined exclusion criteria, the processor continued with a second review based on its determined disease type—moderate insomnia with heart and spleen deficiency—and its determined disease severity—moderate. The target disease research project only includes patients with moderate to severe insomnia with heart and spleen deficiency, and Mr. Zhang met this inclusion criteria, so the processor ultimately confirmed and marked him as a research subject for this target disease research project.

[0165] In some embodiments, the method further comprises:

[0166] When the candidate research subjects meet the preset exclusion criteria, a third review of the symptom information of the candidate research subjects is conducted to determine whether the candidate research subjects are research subjects for other disease research projects.

[0167] In this embodiment, when the candidate research subject cannot continue to be included in the current target disease research project due to the aforementioned preset exclusion criteria, the processor can conduct a third review on the candidate research subject based on his or her existing symptom information to determine whether he or she happens to meet the inclusion requirements of another disease research project.

[0168] Specifically, if the processor finds that the alternative research subject meets the preset exclusion criteria (such as the presence of specific complications, recent use of conflicting drugs, etc.) after the second review or medical history / medication information comparison, a third review will be conducted: first, all other disease research projects that are currently recruiting and have matching symptom requirements are retrieved from the database, where each project also pre-defines the corresponding inclusion / exclusion criteria and required symptom characteristics; then, the processor automatically compares the symptom information previously submitted and structured stored by the alternative research subject (such as subjective self-reported clinical manifestations, various quantitative scores, Chinese medicine syndrome differentiation elements, etc.) with the inclusion / exclusion criteria corresponding to each other disease research project one by one.

[0169] If the candidate research subject meets the inclusion criteria of a certain project and has no conflicting exclusions, he / she will be judged to be suitable for participating in the other disease research project and will be marked as the research subject of that project; if he / she meets the criteria of multiple projects at the same time, he / she may be reallocated according to the project priority or the guidance of the research coordinator; if he / she does not meet the conditions of any other project, he / she will eventually be removed from the candidate list of all projects, and he / she may be advised to pay attention to new research in the future or directly feedback the non-compliance information.

[0170] In this way, when alternative research subjects are unable to continue to participate in the current project due to meeting the preset exclusion criteria, they will be matched to other eligible disease research projects through the third review, thereby achieving efficient use of population resources and improving the recruitment success rate.

[0171] In some implementations, obtaining description information of a candidate object includes:

[0172] Obtaining original description information of the candidate subject, including the candidate subject's identity information and condition description information;

[0173] Determine whether the candidate has been a research subject in a target disease research project based on identity information;

[0174] In the case that the candidate subject has never been a research subject of the target disease research project, term conversion is performed on the condition description information, and the condition description information is converted into common terms for symptom description to obtain description information.

[0175] In this embodiment, the processor first obtains original descriptive information from the candidate object, which includes the candidate object's identity information (such as name, ID number, contact information, previous participation records, etc.) on the one hand, and the candidate object's condition description information (that is, the candidate object's subjective statement of his or her physical discomfort or disease condition in natural language or unstructured form) on the other hand.

[0176] The processor first uses the candidate's identity information to determine whether the candidate has previously been a research subject for the target disease research project. If the identity information matches someone who has already participated in the project, the candidate will not be included again. Only after confirming that the candidate has not been a research subject for the target disease research project will the processor further perform terminology conversion on the candidate's condition description information, converting non-standardized expressions such as "difficulty falling asleep," "frequent night awakenings," and "tiredness" given by the candidate in oral, written, or other free-form ways into pre-defined general symptom description terms (e.g., "frequent night awakenings" - difficulty falling asleep, "sleep maintenance disorders," etc.). Ultimately, all converted general symptom description terms can be combined with necessary identity codes and deduplication identifiers to form formal description information for subsequent initial review.

[0177] In this way, the processor can avoid duplicate recruitment and ensure the accuracy and consistency of data in the subsequent first review by first excluding candidates who have participated in this project and then converting the unstructured disease descriptions into standardized common terms for symptom descriptions.

[0178] For example, Ms. Zhang's original description information is as follows:

[0179] Identity information: Name “Zhang XX”, contact number “138xxxx5678”.

[0180] Condition description information:

[0181] "I haven't been able to sleep well for the past year. I have to toss and turn in bed for hours before I can fall asleep.

[0182] “Even if I can fall asleep, I often wake up in the middle of the night and then have a hard time falling asleep again;”

[0183] "I often feel dizzy during the day, my memory is not as good as before, and I get anxious and short of breath easily;"

[0184] "I've taken Anshen Buxin Pills and Shenqi Dihuang Pills before, and I haven't seen any significant improvement after taking them for about a month."

[0185] The processor first reads and verifies the identity information. It finds no record of "Zhang XX" as a research subject in the target research project in the internal database, confirming that she has never been a research subject in the target disease research project. Therefore, it enters the next step of term conversion. The processor converts the above-mentioned description of Ms. Zhang's condition into common symptom description terms one by one, as follows:

[0186] Convert "I have not been able to sleep well in the past year and have to toss and turn in bed for several hours before falling asleep" to "Insomnia - Difficulty falling asleep (on average, it takes more than 2 hours to fall asleep every night, which has lasted for 12 months)"

[0187] Convert "Even if I can fall asleep, I often wake up in the middle of the night and have difficulty falling asleep again after waking up" to "Sleep maintenance disorder (easy to wake up in the middle of the night, difficult to fall asleep again after waking up, frequency greater than 4 times / week)"

[0188] Change "often feeling dizzy during the day, memory is not as good as before, and easily palpitating and short of breath" to "impaired daytime function - fatigue, memory loss, palpitations and shortness of breath (affecting daily work and life)";

[0189] Convert "I have taken Anshen Buxin Pills and Shenqi Dihuang Pills before, and have been taking them for about a month, but there has been no significant improvement" to "Medication history - taking Chinese patent medicine (Anshen Buxin Pills, Shenqi Dihuang Pills) for 1 month, with no significant therapeutic effect."

[0190] After packaging all the common terms describing the above symptoms together with the desensitized identity information, the processor forms the final description information and saves it for subsequent first review or other screening processes based on scoring rules.

[0191] In some embodiments, after determining that the candidate research subject is a research subject for the target disease, the method further comprises:

[0192] Collect information on the physical condition of the research subjects;

[0193] Based on the physical condition information, modification suggestions are output for the research steps of the target disease.

[0194] In this embodiment, after the confirmation of the research subject of the target disease research project is completed, the research subject is continued to be tracked and intervention optimized. Specifically, the processor can first collect the physical status information of the research subject through wearable devices, remote monitoring terminals or regular outpatient follow-up, etc. The physical status information may include but is not limited to vital signs (such as heart rate, blood pressure, body temperature), sleep quality indicators (such as sleep latency, deep sleep duration), activity data (such as average daily steps, exercise intensity), physical sign quantitative data (such as weight, blood sugar, blood lipid levels) or traditional Chinese medicine signs (such as tongue, pulse, complexion changes).

[0195] After obtaining the above-mentioned physical status information, the processor compares and analyzes the current physical status of the research subject with the expected status in combination with the established processes and intervention plans of each link in the target disease research steps. When the processor finds that the physical status of the research subject deviates from expectations, it will output modification suggestions to the research team or the research subject himself based on the deviation. These suggestions may include adjusting the frequency of follow-up, optimizing the dosage of Chinese or Western medicine, changing the lifestyle intervention plan (such as exercise intensity, eating habits), supplementing necessary auxiliary examinations (such as nocturnal polysomnography), or adding specific evaluation indicators to the research process (such as retesting the anxiety and depression scale).

[0196] In this way, through this modification suggestion mechanism based on dynamic body status feedback, it is ensured that the research subjects can maintain high consistency with the research design requirements throughout the entire research cycle, thereby improving the validity and security of the research data.

[0197] In some embodiments, the processor collects physical status information of the research subjects. Physical status information can be manually input or collected by sensors to ensure timeliness and accuracy. At the same time, the processor provides real-time tracking of research progress, including research subject participation, treatment progress, and health feedback. This allows researchers to view the data and progress of all candidates through the client and adjust treatment or research plans as needed. In addition, the processor can regularly send requests to research subjects for feedback to understand their treatment effects and research participation experience. The processor can classify, organize, cleanse, and summarize trends of the received information through big data analysis, allowing researchers to query the status of research patients on demand, including treatment effects, symptom improvement, the effectiveness of traditional Chinese medicine prescriptions, and overall treatment effect trends for patient groups.

[0198] In this way, the processor realizes full-process management, from information collection of research subjects to treatment tracking and data analysis, realizing the digitization and automation of the scientific research process, greatly improving the work efficiency of scientific researchers and reducing potential errors in human operations.

[0199] Please attend Figure 4 , is a structural diagram of a research object determination device provided in an embodiment of the present application. In a second aspect of an embodiment of the present application, a research object determination device 10 is provided. The device 10 includes:

[0200] An acquisition module 11 is used to obtain description information of a candidate object;

[0201] A first review module 12 is configured to perform a first review on the candidate subject based on the description information, and determine the candidate subject as a candidate research subject for the target disease research project if the review result of the first review indicates that the candidate subject is qualified;

[0202] A sending module 13 is used to send interaction information to the candidate research subject, where the interaction information is used to obtain symptom information input by the candidate research subject, where the symptom information is used to characterize the physical symptoms of the candidate subject;

[0203] The second review module 14 is used to perform a second review on the candidate research subject based on the symptom information, and determine the candidate research subject as a research subject for the target disease research project if the review result of the second review indicates that the candidate research subject is qualified.

[0204] The research object determination device 10 provided in the second aspect of the embodiment of the present application can implement each process implemented in the above-mentioned method embodiment and achieve the same beneficial effects. To avoid repetition, it will not be repeated here.

[0205] See Figure 5 , is a structural diagram of an electronic device provided in an embodiment of the present application. The third aspect of the embodiment of the present application provides an electronic device 500, including a processor 510 and a memory 520. The memory 520 stores machine-executable instructions that can be executed by the processor 510. The processor 510 can execute the machine-executable instructions to implement the above-mentioned research object determination method.

[0206] A fourth aspect of an embodiment of the present application provides a machine-readable storage medium, on which instructions are stored. When the instructions are executed by a processor, the processor implements the above-mentioned research object determination method.

[0207] In one embodiment of the present application, a computer program product is further provided, including a computer program, which implements the research object determination method according to the above embodiment when executed by a processor.

[0208] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0209] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including the instruction device, which implements the function specified in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0210] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0211] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0212] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0213] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0214] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

[0215] In addition, the various embodiments of the present invention may be arbitrarily combined, and as long as they do not violate the concept of the present invention, they should also be regarded as the contents disclosed by the present invention.

Claims

1. A method for determining a research object, characterized in that: The method comprises: Get the description information of the candidate object; performing a first review of the candidate subject based on the descriptive information, and determining the candidate subject as a candidate research subject for a target disease research project if a review result of the first review indicates that the candidate subject is qualified; Sending interaction information to the candidate research subject, wherein the interaction information is used to obtain symptom information input by the candidate research subject, wherein the symptom information is used to characterize the physical symptoms of the candidate subject; A second review is performed on the candidate research subject based on the symptom information. When the review result of the second review indicates that the candidate research subject is qualified, the candidate research subject is determined as the research subject of the target disease research project.

2. The method according to claim 1, characterized in that The description information includes first description information of the candidate subject's physical symptoms, the first description information includes first sub-information of multiple dimensions, and the first review of the candidate subject based on the description information includes: For each piece of first sub-information, multiply the information score of the first sub-information by the dimension weight of the dimension to which the first sub-information belongs, to obtain a first product, wherein the information score and the dimension weight are pre-configured; determining a first score of the candidate object based on a plurality of the first products; A first review is performed on the candidate object according to the first score.

3. The method according to claim 1, characterized in that The symptom information includes second sub-information of multiple dimensions, and the second review of the candidate research subject based on the symptom information includes: For each second sub-information, multiply the information score of the second sub-information by the dimension weight of the dimension to which the second sub-information belongs, to obtain a second product, wherein the information score and the dimension weight are pre-configured; determining a second score for the candidate research subject based on the plurality of second products; Determining the disease type and disease severity level of the candidate research subject based on the second score; A second review is conducted on the candidate research subjects based on the disease type and the severity of the disease.

4. The method according to claim 3, characterized in that The second review of the candidate research subjects based on the disease type and disease severity level includes: Obtaining medical history information and drug use information of the candidate research subjects; Determining whether the candidate research subject meets the preset exclusion criteria based on the medical history information and the drug use information; In the case that the candidate research subject does not meet the preset exclusion criteria, a second review is conducted on the candidate research subject based on the disease type and the severity level of the disease.

5. The method according to claim 4, characterized in that The method further comprises: In the case that the candidate research subject meets the preset exclusion criteria, a third review is performed on the symptom information of the candidate research subject to determine whether the candidate research subject is a research subject for other disease research projects.

6. The method according to claim 1, characterized in that The obtaining of description information of the candidate object includes: Obtaining original description information of the candidate subject, wherein the original description information includes the identity information and condition description information of the candidate subject; Determining, based on the identity information, whether the candidate subject has served as a research subject for the target disease research project; In the case that the candidate subject has never been a research subject of the target disease research project, term conversion is performed on the condition description information to convert the condition description information into common terms for symptom description to obtain the description information.

7. The method according to claim 1, characterized in that After determining that the candidate research subject is a research subject of the target disease, the method further includes: Collecting physical condition information of the research subject; Based on the physical condition information, a modification suggestion is output for a research step on the target disease.

8. A device for determining a research object, characterized in that: The device comprises: An acquisition module is used to obtain description information of candidate objects; a first review module, configured to perform a first review on the candidate subject according to the description information, and determine the candidate subject as a candidate research subject for a target disease research project if a review result of the first review indicates that the candidate subject is qualified; a sending module, configured to send interaction information to the candidate research subject, wherein the interaction information is used to obtain symptom information input by the candidate research subject, wherein the symptom information is used to characterize the physical symptoms of the candidate subject; The second review module is used to perform a second review on the candidate research subject based on the symptom information, and determine the candidate research subject as the research subject of the target disease research project when the review result of the second review indicates that the candidate research subject is qualified.

9. An electronic device, characterized in that: The device includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory for storing computer programs; The processor is configured to implement the steps of the research object determination method according to any one of claims 1 to 7 when executing the program stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the research object determination method according to any one of claims 1 to 7 are implemented.

Images