Follow-up management methods, systems and storage media

Abstract

This invention provides a follow-up management method, system, and storage medium, belonging to the field of follow-up management technology. Specifically, it includes: based on the new data of patients to be followed up and the re-examination plan, identifying patients for whom follow-up questionnaires are constructed using all follow-up question items and designated as target patients; determining matching follow-up question items in the follow-up questionnaire based on the matching results of the target patients' follow-up questionnaires and the re-examination data; and determining the management method for the distribution of matching follow-up question items based on the distribution data of different matching follow-up question items, thereby reducing the data processing difficulty of follow-up questionnaires.

Description

Technical Field

[0001] This invention belongs to the field of follow-up management technology, and in particular relates to a follow-up management method, system and storage medium. Background Technology

[0002] To facilitate follow-up management of postoperative patients at home, for example, the invention patent application CN202410757371.8, "Intelligent Follow-up Management System and Method for Chronic Diseases in the Elderly," describes anonymous and backup-processed follow-up record tables that can be restored anonymously and from backups to obtain the corresponding follow-up record tables. This improves the security of follow-up data during transmission and the confidentiality and integrity during storage. However, the following technical problems exist:

[0003] As the number of patients requiring follow-up increases, using fixed follow-up questions to build follow-up questionnaires inevitably leads to higher processing difficulty and time for medical staff. Therefore, how to identify matching follow-up questions associated with patients' examination data and to construct personalized follow-up questionnaires for follow-up patients has become an urgent technical problem to be solved.

[0004] Therefore, there is an urgent need for a follow-up management method, system, and storage medium. Summary of the Invention

[0005] To achieve the objectives of this invention, the following technical solution is adopted:

[0006] Specifically, this application provides a follow-up management method, which includes:

[0007] S1 determines the follow-up question item data of the follow-up questionnaire. Based on the follow-up question item data of the follow-up questionnaire and the data of the patient to be followed up, if it is determined that personalized generation of the follow-up questionnaire is required, proceed to the next step.

[0008] Based on the new data of patients awaiting follow-up and the re-examination plan, S2 identifies patients for whom follow-up questionnaires are constructed using all follow-up question items and assigns them as target patients for such assignment.

[0009] S3 determines the matching follow-up question items in the follow-up questionnaire based on the matching results of the follow-up questionnaire of the target patients and the re-examination data. Based on the data of different matching follow-up question items, the management method for the distribution of the matching follow-up question items is determined.

[0010] The beneficial effects of this invention are as follows:

[0011] Based on the new data of patients awaiting follow-up and the re-examination plan, patients were identified for whom follow-up questionnaires were constructed using all follow-up question items and then assigned to lower-level management. This enabled the determination of matching follow-up question item identification and processing needs based on changes in the number of patients awaiting follow-up, and the determination of patients assigned to lower-level management based on the re-examination plan using the matching follow-up question item identification and processing needs. This allowed for dynamic adjustment of the re-examination result issuance time threshold from the perspective of identification and processing needs, thereby enabling dynamic adjustment of patients assigned to lower-level management. This not only reduced the difficulty of data processing but also further improved the efficiency of matching follow-up question item identification and processing.

[0012] By using different data sets of matching follow-up question items, a management method for distributing matching follow-up question items was determined. This avoids the technical problem of excessive data processing difficulty caused by continuing to distribute the items to target patients when there are many matching follow-up question items. By adjusting the distributing question items in the target patients, the reliability of the matching follow-up question item identification and processing results is further improved due to the reduction in the number of follow-up question items in the target patients, without reducing the identification and processing results of the matching follow-up question items.

[0013] Furthermore, the follow-up question item data is determined based on the number of follow-up question items in the patient's follow-up questionnaire.

[0014] Furthermore, the data of the patients to be followed up are determined based on the patient data that needs to be followed up in the follow-up management system.

[0015] Furthermore, it was determined that personalized generation processing of the access volume was required, specifically including:

[0016] Based on the follow-up question item data of the follow-up access volume, determine the number of follow-up question items of the follow-up access volume;

[0017] Based on the data of the patients to be followed up, the number of patients to be followed up is determined;

[0018] Based on the number of follow-up question items in the follow-up questionnaire and the number of patients to be followed up, it is determined whether personalized generation of the follow-up questionnaire is required.

[0019] Optionally, the method for determining the decentralization management method for matching follow-up issue items is as follows:

[0020] Based on the data from different matching follow-up question items, patients whose follow-up questionnaires contain the matching follow-up question items are identified and used as the matching follow-up patients for the matching follow-up question items.

[0021] Based on the matched follow-up question item data, determine the number of matched follow-up question items, and determine the matching factor based on the proportion of the matched follow-up question items in all follow-up question items;

[0022] The method for decentralizing the management of the matching follow-up issues is determined based on the number of matching follow-up issues and the matching factor of the matching follow-up issues.

[0023] In a second aspect, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the aforementioned follow-up management method when running the computer program.

[0024] Thirdly, the present invention provides a computer storage medium storing a computer program thereon, which, when executed in a computer, causes the computer to perform the aforementioned follow-up management method.

[0025] Other features and advantages will be set forth in the following description, and the objects and other advantages of the invention are realized and obtained through the structures particularly pointed out in the description and the drawings.

[0026] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0027] The above and other features and advantages of the present invention will become more apparent from a detailed description of exemplary embodiments thereof with reference to the accompanying drawings.

[0028] Figure 1 This is a flowchart of a follow-up management method;

[0029] Figure 2 This is a diagram illustrating the method for determining the need for personalized generation of random access volumes;

[0030] Figure 3 This is a flowchart illustrating the method for identifying target patients.

[0031] Figure 4 A flowchart illustrating the method for determining the decentralization management approach for matching follow-up issue items. Detailed Implementation

[0032] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this specification.

[0033] Example 1

[0034] like Figure 1 As shown, this application provides a follow-up management method, specifically including:

[0035] S1 determines the follow-up question item data of the follow-up questionnaire. Based on the follow-up question item data of the follow-up questionnaire and the data of the patient to be followed up, if it is determined that personalized generation of the follow-up questionnaire is required, proceed to the next step.

[0036] Based on the new data of patients awaiting follow-up and the re-examination plan, S2 identifies patients for whom follow-up questionnaires are constructed using all follow-up question items and assigns them as target patients for such assignment.

[0037] S3 determines the matching follow-up question items in the follow-up questionnaire based on the matching results of the follow-up questionnaire of the target patients and the re-examination data. Based on the data of different matching follow-up question items, the management method for the distribution of the matching follow-up question items is determined.

[0038] Furthermore, the follow-up question item data is determined based on the number of follow-up question items in the patient's follow-up questionnaire.

[0039] Furthermore, the data of the patients to be followed up are determined based on the patient data that needs to be followed up in the follow-up management system.

[0040] Specifically, such as Figure 2 As shown, it has been determined that personalized generation processing of the access volume is required, specifically including:

[0041] Based on the follow-up question item data of the follow-up access volume, determine the number of follow-up question items of the follow-up access volume;

[0042] Based on the data of the patients to be followed up, the number of patients to be followed up is determined;

[0043] Based on the number of follow-up question items in the follow-up questionnaire and the number of patients to be followed up, it is determined whether personalized generation of the follow-up questionnaire is required.

[0044] In the above steps, if the number of patients to be followed up is large, and if the number of follow-up questions on the follow-up questionnaire is also large, it will inevitably lead to greater difficulty for medical staff in analyzing and processing the follow-up questionnaire. Therefore, it is necessary to generate and process the follow-up questionnaire in a personalized manner, so as to generate and push the follow-up questionnaire in a targeted manner and reduce the difficulty of analysis and processing for medical staff.

[0045] Specifically, if the number of patients to be followed up is not within the preset range and the number of follow-up questions on the follow-up questionnaire is not within the preset range, then it is determined that personalized generation of the follow-up questionnaire is required.

[0046] Specifically, the following two possible implementation methods are included:

[0047] 1. This embodiment constructs a personalized questionnaire generation decision system based on dual threshold determination. The system first establishes a real-time monitoring mechanism to continuously track the number of patients to be followed up N and the number of questions Q in the currently used follow-up questionnaire. The system sets two key thresholds: a patient number threshold N_threshold and a question number threshold Q_threshold. N_threshold is dynamically adjusted according to the size of the medical institution and the configuration of medical staff; for example, it is set to 200 people for a medium-sized medical institution. Q_threshold is set to 30 questions based on questionnaire processing efficiency research.

[0048] The system automatically performs decision analysis, and the specific implementation process is as follows: First, the current workload index W = N × Q is calculated. When both N > N_threshold and Q > Q_threshold are satisfied, the system determines that personalized questionnaire generation is required. For example, when N=250 and Q=31 are detected, since both exceed the thresholds (200 and 30), the system outputs the decision result "Personalized generation is required".

[0049] 2. This embodiment considers not only the number of patients and the number of questions, but also incorporates multiple dimensions such as the workload of medical staff and the timeliness requirements for follow-up to make a comprehensive judgment. The system establishes a decision matrix, which includes the following key indicators: the number of patients to be followed up, the average number of questions in the questionnaire, the available working hours of medical staff, and the time limit for completing the follow-up.

[0050] The system calculates the personalization generation necessity index G using a weighted scoring model. The specific formula is: G = 0.4 × number of standardized patients + 0.3 × number of standardized questions + 0.2 × time pressure coefficient + 0.1 × resource strain. When G > 0.7, the system determines that personalized questionnaire generation is necessary. Wherein, number of standardized patients = min(1, N / N_max), where N_max is the institution's maximum processing capacity; number of standardized questions = min(1, Q / Q_max), where Q_max is the upper limit of questions that can be effectively processed; the time pressure coefficient is calculated based on the urgency of the follow-up completion deadline, i.e., the remaining time after normalization; resource strain reflects the current workload of medical staff, specifically obtained after normalization based on the number of patients followed up by medical staff.

[0051] The implementation of this system has resulted in significant quality improvement. Through precise workload assessment and timely personalized questionnaire generation interventions, the completeness and accuracy of follow-up data have been significantly improved, providing a more reliable data foundation for clinical research and medical quality improvement.

[0052] In summary, the personalized questionnaire generation decision system based on workload index not only improves the efficiency of follow-up management, but more importantly, it establishes an efficient, stable, and adaptive intelligent follow-up management system through scientific workload assessment and precise intervention, providing strong technical support for the digital transformation of medical institutions.

[0053] Specifically, the step of constructing a follow-up questionnaire using all follow-up question items involves building a follow-up questionnaire based on all existing follow-up question items in the department. This improves the efficiency of matching follow-up question items for identification and processing, laying the foundation for further personalized recommendation processing of follow-up question items.

[0054] Example 2

[0055] Specifically, such as Figure 3 As shown, the method for determining the target patients for distribution is as follows:

[0056] Based on the newly added data of the patients to be followed up, the date on which the new patients to be followed up were added was determined and used as the date of addition;

[0057] Based on the composition data of the newly added dates, determine the proportion of newly added dates within the most recent preset time period;

[0058] Based on the proportion of newly added dates within the most recent preset time period and the follow-up plan of the patients to be followed up, it is determined whether the patients to be followed up are the target patients for relocation.

[0059] It is understood that the newly added date refers to the date when the number of patients awaiting follow-up increases due to the presence of newly added patients awaiting follow-up.

[0060] It should be noted that the duration of the most recent preset time period is determined based on the number of patients to be followed up. The more patients to be followed up, the longer the preset time period will be.

[0061] It should be noted that, based on the proportion of newly added dates within the most recent preset time period and the follow-up plan of the patients to be followed up, determining whether the patients to be followed up are the target patients for relocation includes:

[0062] Based on the follow-up plan of the patient to be followed up, determine the interval between the most recent follow-up date and the current date;

[0063] Based on the newly added data of the patients to be followed up, the date on which the new patients to be followed up were added was determined and used as the date of addition;

[0064] The variation factor is determined based on the proportion of newly added dates within the most recent preset time period;

[0065] If the variable factor is greater than a preset variable factor threshold, then all patients to be followed up will be designated as target patients for reassignment.

[0066] Additionally, it can be understood that if the change factor is not greater than a preset change factor threshold, then the number of newly added patients to be followed up in the most recent preset time period is further determined. If the proportion of the number of newly added patients to be followed up in the most recent preset time period to all patients to be followed up is greater than a preset increase proportion threshold, then patients to be followed up with an interval duration less than a first interval duration threshold are determined as target patients for reassignment. If the proportion of the number of newly added patients to be followed up in the most recent preset time period to all patients to be followed up is not greater than a preset increase proportion threshold, then patients to be followed up with an interval duration less than a second interval duration threshold are determined as target patients for reassignment.

[0067] It should be noted that the first interval duration threshold is greater than the second interval duration threshold, and the specific value is determined based on the number of patients to be followed up. The more patients to be followed up, the larger the first interval duration threshold and the second interval duration threshold will be.

[0068] Specifically, the following specific embodiments are included:

[0069] 1. This embodiment constructs a patient decentralization decision-making system based on dynamic assessment. The system first obtains the follow-up plan data of all patients to be followed up through the medical institution's electronic medical record system, and calculates the interval T_i (in days) between the most recent follow-up date and the current date for each patient. At the same time, the system records the data of newly added patients to be followed up each day, marks the new dates, and counts the number of new dates in the last 30 days.

[0070] The system defines the formula for calculating the variation factor V as follows:

[0071] V = (N_add_date / 30) × (1 + σ_N / μ_N)

[0072] Where N_add_date is the number of new dates in the last 30 days, σ_N is the standard deviation of the number of new patients per day, and μ_N is the mean of the number of new patients per day. The system sets a preset threshold for the variation factor V_threshold = 0.6.

[0073] When the system detects that V > V_threshold, it determines that the patient population is in a high-volatility state. At this time, all patients to be followed up are marked as target patients for reassignment, ensuring comprehensive follow-up coverage during the period of volatility.

[0074] When V ≤ V_threshold, the system further calculates the proportion of new patients R:

[0075] R = N_recent / N_total

[0076] Where N_recent is the number of newly added patients in the last 30 days, and N_total is the total number of patients to be followed up. A preset threshold for the proportion of newly added patients is set to R_threshold = 0.3.

[0077] If R > R_threshold, the system will limit the target patients to those with an interval of T_i < 14 days (first interval threshold); if R ≤ R_threshold, the target patients will be those with an interval of T_i < 7 days (second interval threshold). The system automatically performs the above calculations to ensure that the deployment strategy matches the real-time changes in the patient population, thereby enabling faster identification of matching follow-up issues.

[0078] 2. This implementation presents a patient demobilization optimization system based on multi-period analysis. The system employs comprehensive analysis across multiple time periods to improve the accuracy of demobilization decisions. The system defines three observation periods: short-term (7 days), medium-term (30 days), and long-term (90 days), calculating the variation factors within each period: short-term variation factor V_s = N_add_date_7 / 7, medium-term variation factor V_m = N_add_date_30 / 30, and long-term variation factor V_l = N_add_date_90 / 90.

[0079] The comprehensive variation factor V_composite = 0.5×V_m + 0.3×V_s + 0.2×V_l, and the comprehensive variation factor threshold V_threshold = 0.5.

[0080] When V_composite > V_threshold, the system uses all patients awaiting follow-up as target patients for referral. Otherwise, the system calculates the recent increase rate R_30 = N_recent_30 / N_total and sets two increase rate thresholds: R_high = 0.4 and R_low = 0.2.

[0081] The decentralization strategy is as follows: If R_30 > R_high, patients with T_i < 10 days of follow-up will be the target patients for decentralization; if R_low < R_30 ≤ R_high, patients with T_i < 8 days of follow-up will be the target patients for decentralization; if R_30 ≤ R_low, patients with T_i < 5 days of follow-up will be the target patients for decentralization.

[0082] 3. This embodiment constructs a risk-adjusted patient demobilization decision-making system. In addition to basic time interval assessment, the system introduces patient risk assessment factors to achieve more accurate demobilization decisions. The system first calculates the baseline variation factor V and sets a threshold V_threshold = 0.55. When V > V_threshold, a full demobilization strategy is adopted.

[0083] When V ≤ V_threshold, the system not only considers the proportion of new patients, but also introduces a patient urgency factor E. The urgency factor is calculated based on factors such as the severity of the patient's disease and historical follow-up compliance, and is divided into three levels: high, medium, and low.

[0084] The system defines a priority score for patient transfer: S = α×(1 - T_i / T_max) + β×E + γ×R, where T_max is the maximum allowed interval, α, β, and γ are weighting coefficients, and R is the proportion of new patients. The transfer strategy is adjusted as follows: if R > 0.1, transfer patients whose S > the first threshold; if 0.05 < R ≤ 0.1, transfer patients whose S > the second threshold; if R ≤ 0.05, transfer patients whose S > the third threshold, where the first threshold is less than the second threshold, and the second threshold is less than the third threshold.

[0085] This system optimizes resource allocation while ensuring follow-up quality through multi-factor comprehensive evaluation, making it particularly suitable for large medical institutions with complex patient population structures. The system automatically generates a weekly decision-making report for administrators to review and optimize parameter settings.

[0086] Example 3

[0087] Specifically, such as Figure 4 As shown, the method for determining the matching follow-up question items is as follows:

[0088] Based on the matching results of the follow-up questionnaires of the target patients and the re-examination data, the follow-up issues that are consistent with the examination results of the re-examination items are determined;

[0089] Patients whose follow-up problem items are consistent with the survey results and the results of the re-examination items are considered as consistent patients for the follow-up problem items;

[0090] Based on the consistent patient, determine whether the follow-up question item is a matching follow-up question item in the follow-up questionnaire.

[0091] It is understandable that if the number of patients with consistent follow-up questions is within a preset range, it means that the probability of the follow-up questions being consistent with the examination results of the examination items is relatively high. Therefore, the follow-up questions are determined to be the matching follow-up questions in the follow-up questionnaire.

[0092] The following are several specific embodiments corresponding to this application:

[0093] 1. This embodiment uses thyroid disease patients as an example to construct a follow-up question item matching system based on the consistency of test results. The system first establishes a follow-up database for thyroid patients, which includes the patients' follow-up questionnaire results and corresponding thyroid function test results, with key indicators including TSH, FT3, FT4, etc.

[0094] The system defines the criteria for determining consistent patients: for each follow-up question, the survey results are compared with the corresponding thyroid function test results for consistency. For example, for the follow-up question "Have you felt fatigued or weak recently?", if the patient selects "yes" and the TSH test result is outside the normal range (>4.2 mIU / L), the patient is marked as a consistent patient for that question.

[0095] The system sets the preset patient number range to [15, 25]. For each follow-up question item, the system counts the cumulative number of consistent patients (N_consistent) over the most recent 90 days. When N_consistent ∈ [15, 25], the system determines that the follow-up question item is a matching follow-up question item.

[0096] The specific implementation process includes:

[0097] Data collection: Collect follow-up questionnaire data and laboratory test results of thyroid patients; Consistency comparison: Establish the mapping relationship between problem items and test indicators; Statistical analysis: Calculate the number of patients with consistent results for each problem item; Matching determination: Determine the matching problem items based on preset intervals.

[0098] For example, in the analysis of the "weight change" question item, the system found that when patients reported "weight gain" and abnormal TSH levels, the number of consistent patients for this question item was 18, which fell within the preset range, so it was marked as a matched follow-up question item.

[0099] 2. This embodiment develops a multi-indicator comprehensive assessment system for optimizing thyroid follow-up issues. The system considers not only the number of consistent patients, but also incorporates multiple dimensions such as consistency strength and clinical relevance for evaluation.

[0100] System-defined consistency strength index:

[0101] C_strength = (N_consistent / N_total) × (1 - p_value)

[0102] Here, p_value is the significance level of the correlation between the question item and the test result, calculated using the chi-square test.

[0103] For specific examination items for thyroid patients, the system establishes the following assessment framework: TSH-related symptoms: preset interval [12, 20]; thyroid antibody-related symptoms: preset interval [8, 15]; thyroid ultrasound-related symptoms: preset interval [10, 18].

[0104] The system employs a sliding time window statistical method, updating the number of consistent patients every 30 days. Simultaneously, the system requires that the following matching conditions be met: the number of consistent patients is within the corresponding preset interval; the consistency strength C_strength > 0.6; and the clinical expert score > 7 points (out of 10).

[0105] For example, when assessing the "neck discomfort" issue, the system found that 16 patients had results consistent with thyroid ultrasound examination, with a consistency strength of 0.72 and a clinical expert score of 8, thus classifying it as a matched follow-up issue.

[0106] Furthermore, the data for assigning matching follow-up questions includes the number of patients to whom the matching follow-up questions are assigned, specifically including the target patients and patients to whom medical staff assign matching follow-up questions based on their own judgment.

[0107] Example 4

[0108] Specifically, such as Figure 4 As shown, the method for determining the decentralization management method for matching follow-up issue items is as follows:

[0109] Based on the data from different matching follow-up question items, patients whose follow-up questionnaires contain the matching follow-up question items are identified and used as the matching follow-up patients for the matching follow-up question items.

[0110] Based on the matched follow-up question item data, determine the number of matched follow-up question items, and determine the matching factor based on the proportion of the matched follow-up question items in all follow-up question items;

[0111] The method for decentralizing the management of the matching follow-up issues is determined based on the number of matching follow-up issues and the matching factor of the matching follow-up issues.

[0112] Specifically, if the matching factor of the matching follow-up question item is greater than the preset matching factor threshold, it only needs to be assigned to the patient corresponding to the matching follow-up question item. For example, the "weight gain" in the follow-up question item can be assigned to the patient whose TSH level was abnormal in the previous test results.

[0113] Furthermore, if the matching factor of the matched follow-up question item is not greater than the preset matching factor threshold, and if the number of matched follow-up question items excluding those with matching factors greater than the preset matching factor threshold is within the preset range of matched question item numbers, then the matched follow-up question item will be distributed to all patients to be followed up. That is, the matched follow-up question item will be included in the follow-up questionnaires of all patients to be followed up, thereby enabling accurate verification of the matched follow-up question item.

[0114] Additionally, it is understood that if the number of matching follow-up issues excluding those with matching factors greater than a preset matching factor threshold is not within the preset range of matching issue numbers, then the matching follow-up issues will only be pushed to patients awaiting follow-up who are not included in the target processing.

[0115] Specific implementation methods include:

[0116] Example 1: Decentralized Management System Based on Matching Factor Hierarchy

[0117] This embodiment constructs a hierarchical management system based on matching factors. The system first analyzes follow-up data to identify all matching follow-up issues and determines the corresponding matching patient group for each issue. The system defines the formula for calculating the matching factor M as follows:

[0118] M = (N_match / N_total) × W_consistency

[0119] Where N_match is the number of matched follow-up issues, N_total is the total number of matched follow-up issues, and W_consistency is the consistency weight coefficient based on historical data, with a value range of [0.8, 1.2].

[0120] The system sets a preset matching factor threshold M_threshold = 0.6. When M > M_threshold, the number of matching follow-up question items is large. In this case, the system adopts a precise assignment strategy, assigning the matching follow-up question item only to the corresponding matching follow-up patient. For example, for the follow-up question item "weight gain," the system will precisely assign it to patients whose TSH levels were abnormal in their most recent examination.

[0121] When M ≤ M_threshold, the system further counts the number of remaining matching follow-up questions, N_remaining. The preset range for the number of matching questions is [0, 5]. If N_remaining ∈ [0, 5], then even if the data is distributed to all patients, the impact on the data processing difficulty of the target patients is minimal. The system will include these matching follow-up questions in the follow-up questionnaires of all patients awaiting follow-up for large-scale validation. If N_remaining ∉ [0, 5], the system adopts a supplementary distribution strategy, pushing these questions only to other patients awaiting follow-up besides the target patients, ensuring a reasonable allocation of follow-up resources.

[0122] 2. This embodiment specifically targets patients with thyroid diseases, constructing a decentralized management system based on precise matching of thyroid function test indicators. The system first establishes a full-cycle health database for thyroid patients, integrating follow-up questionnaire data and thyroid function laboratory test results, including key indicators such as TSH, FT3, FT4, thyroid peroxidase antibody (TPOAb), and thyroglobulin antibody (TgAb). The system uses data mining algorithms to analyze the correlation between different follow-up questions and these laboratory indicators, identifying clinically significant matching follow-up questions.

[0123] Taking typical thyroid symptoms as an example, the system defines the matching rules as follows:

[0124] For the question item "significant weight gain or loss", the matching criteria are: recent TSH levels exceeding the normal range (<0.27 or >4.2 mIU / L). For the question item "neck pressure or swelling", the matching criteria are: thyroid ultrasound showing nodules >1cm in diameter or diffuse lesions. For the question item "palpitations or bradycardia", the matching criteria are: abnormal FT3 levels or TSH <0.1 mIU / L. For the question item "cold intolerance or heat intolerance", the matching criteria are: abnormal TSH levels and abnormal FT4 levels. For the question item "dry or sweaty skin", the matching criteria are: thyroid dysfunction lasting for more than 3 months.

[0125] The system calculates the matching factor M for each matching follow-up question item using the following formula:

[0126] M = (N_match_patients / N_total_patients) × (1 + log(C_odds_ratio))× S_clinical

[0127] Here, N_match_patients represents the number of patients whose results match the examination results in the past 6 months; N_total_patients represents the total number of patients followed up; C_odds_ratio represents the odds ratio between the problem item and the examination results, calculated by logistic regression; and S_clinical represents the clinical expert's score (0-1) on the importance of the problem item.

[0128] The system has a preset matching factor threshold M_threshold = 0.65. When the M value for a matching follow-up question item is greater than 0.65, the system executes a precise referral strategy. For example, for the question item "significant weight change," if its matching factor is 0.72, the system will only refer it to patients whose TSH levels were abnormal in their most recent examination, which is expected to involve approximately 45% of follow-up patients.

[0129] For questions with a matching factor M ≤ 0.65, the system counts their number N_remaining. A preset range for the number of matching questions is set to [0, 5]. If N_remaining falls within this range, the system will include these questions in the questionnaires of all thyroid follow-up patients. For example, for the question "difficulty concentrating," if its matching factor is 0.58 and the current N_remaining = 3, the system will add this question to the follow-up questionnaires of all patients to collect broader data for validation. If N_remaining ∉ [0, 5], the system will execute a supplementary distribution strategy, pushing these questions only to patients other than the target patient. For example, when N_remaining = 12, the system will use a supplementary distribution strategy.

[0130] Example 5

[0131] In a second aspect, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the aforementioned follow-up management method when running the computer program.

[0132] Specifically, such as Figure 4 As shown, the method for determining the decentralization management method for matching follow-up issue items is as follows:

[0133] Based on the data from different matching follow-up question items, patients whose follow-up questionnaires contain the matching follow-up question items are identified and used as the matching follow-up patients for the matching follow-up question items.

[0134] Based on the matched follow-up question item data, determine the number of matched follow-up question items;

[0135] The method for decentralizing the management of the matching follow-up issues is determined based on the number of matching follow-up issues and the matching follow-up patient data for those issues.

[0136] It should be noted that if the number of matching follow-up questions is insufficient, the matching follow-up questions will be distributed to all patients to be followed up. In other words, the matching follow-up questions will be included in the follow-up questionnaires of all patients to be followed up, so that the verification of the matching follow-up questions can be performed accurately.

[0137] Furthermore, if the number of matched follow-up question items meets the requirements, and if the number of matched follow-up patients for the matched follow-up question item is within the preset range of matched patients, then since the number of matched follow-up patients is large, it is only necessary to assign it to the patient corresponding to the matched follow-up question item. For example, assign the follow-up question item "weight gain" to the patient whose TSH level was abnormal in the previous test results.

[0138] Additionally, it is understood that if the number of patients matched for the matching follow-up question item is not within the preset range of the number of matched patients, then if the number of matching follow-up question items is still insufficient after removing the matching question items assigned to the patients corresponding to the matching follow-up question item, then the matching follow-up question item will only be pushed to patients awaiting follow-up who are not included in the assignment processing target. However, if the number of patients matched for the matching follow-up question item is within the preset range of the number of matched patients, then the assignment processing of the matching follow-up question item will be performed on all patients awaiting follow-up, that is, the matching follow-up question item will be included in the follow-up questionnaires of all patients awaiting follow-up, thereby enabling accurate verification processing of the matching follow-up question item.

[0139] Example 6

[0140] Thirdly, the present invention provides a computer storage medium storing a computer program thereon, which, when executed in a computer, causes the computer to perform the aforementioned follow-up management method.

[0141] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0142] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0143] The above description is merely one or more embodiments of this specification and is not intended to limit this specification. Various modifications and variations can be made to the one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of this specification.

Claims

1. A follow-up management method characterized by, Specifically comprising: Determine follow-up question item data of a follow-up questionnaire, determine that personalized generation processing of the follow-up questionnaire needs to be performed when the follow-up question item data of the follow-up questionnaire and data of a patient to be followed up are determined, and proceed to the next step; Based on the new data of the patient to be followed up and the review plan, determine a patient whose follow-up questionnaire is constructed by using all follow-up question items for decentralization processing, and take the patient as a decentralization target patient; According to the matching situation of the survey results of the follow-up questionnaire of the decentralization target patient and the review data, determine the matching follow-up question items in the follow-up questionnaire, and determine the decentralization management method of the matching follow-up question items based on the decentralization data of different matching follow-up question items; Determine that personalized generation processing of the follow-up questionnaire needs to be performed, specifically comprising: Determine the number of follow-up question items of the follow-up questionnaire based on the follow-up question item data of the follow-up questionnaire; Determine the number of patients to be followed up according to the data of the patient to be followed up; Based on the number of follow-up question items of the follow-up questionnaire and the number of patients to be followed up, determine whether personalized generation processing of the follow-up questionnaire needs to be performed; If the number of patients to be followed up is not within a preset patient number interval and the number of follow-up question items of the follow-up questionnaire is not within a preset range, it is determined that personalized generation processing of the follow-up questionnaire needs to be performed; The method for determining the decentralization management method of the matching follow-up question items is: Determine the patients in the follow-up questionnaire who contain the matching follow-up question items based on the decentralization data of different matching follow-up question items, and take the patients as matching follow-up patients of the matching follow-up question items; Determine the number of matching follow-up question items according to the matching follow-up question item data, and determine a matching factor based on the proportion of the matching follow-up question items in all follow-up question items; Determine the decentralization management method of the matching follow-up question items based on the number of matching follow-up question items and the matching factor of the matching follow-up question items.

2. The follow-up management method according to claim 1, characterized in that, The follow-up question item data is determined according to the number of follow-up question items of the follow-up questionnaire of the patient.

3. The follow-up management method according to claim 1, characterized by, The data of the patient to be followed up is determined according to the patient data that needs to be followed up in the follow-up management system.

4. The follow-up management method according to claim 1, characterized by, The follow-up questionnaire constructed by using all follow-up question items is constructed based on all follow-up question items in the existing department.

5. The follow-up management method according to claim 1, characterized in that, The method for determining the decentralization target patient is: Determine the date of the newly added patient to be followed up based on the new data of the patient to be followed up, and take the date as a new date; Determine the proportion of the new date in the recent preset time period according to the constituent data of the new date; Based on the proportion of the new date in the recent preset time period and the review plan of the patient to be followed up, determine whether the patient to be followed up is a decentralization target patient.

6. The follow-up management method according to claim 5, characterized in that, The new date is a date when the number of patients to be followed up increases due to the existence of newly added patients to be followed up.

7. A computer system comprising: A memory and a processor connected by communication, and a computer program stored on the memory and capable of running on the processor, characterized in that the processor, when running the computer program, performs the follow-up management method of any one of claims 1-6.

8. A computer storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to perform the follow-up management method of any one of claims 1-6.

Images