A pediatric constipation traditional chinese medicine comprehensive treatment curative effect evaluation and follow-up management system
Patent Information
- Application Number
- CN202611041927.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-07-14
- Publication Date
- 2026-11-03
AI Technical Summary
In existing technologies, the records of parents performing assisted treatment for pediatric constipation outside the hospital rely on manual filling, which is prone to memory bias and perfunctory behavior, resulting in high data noise, a disconnect between assessment results and actual situation, and difficulty for doctors to distinguish between inadequate implementation and ineffective treatment.
By acquiring the start and submission times of nursing behaviors, analyzing submission delays and page interaction data, calculating the weights of data timeliness and interaction effectiveness, generating a comprehensive confidence coefficient, and combining the frequency of medical orders and bowel movements, an execution intensity scoring model is constructed to judge the treatment effect.
It improved the accuracy of efficacy assessment, avoided misjudgment and blind adjustment of treatment plans, and enhanced the efficiency and scientific nature of follow-up consultation decisions.
Smart Images
Figure CN123033655A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of medical data processing technology, specifically to a comprehensive TCM treatment efficacy evaluation and follow-up management system for pediatric constipation. Background Technology
[0002] When children experience constipation, doctors often advise parents to perform regular supplementary procedures outside the hospital, such as abdominal massage and acupressure, to consolidate the therapeutic effect. The effectiveness of this home intervention model highly depends on the parents' adherence and consistency.
[0003] However, current follow-up management systems largely rely on parents manually filling out operation records. Due to memory lapses or a perfunctory attitude, parents often engage in bulk entry the following day or quickly click to complete the process. Existing data collection technologies typically only record the submission time, failing to distinguish between real-time records and subsequent entries, or identify invalid records with abnormal operation durations. This results in a large amount of noise in the system's collected data, failing to reflect the true intensity of implementation. Furthermore, when a child's follow-up visit shows no improvement in symptoms, doctors struggle to distinguish whether the improvement is due to parents' failure to follow the instructions correctly or the current treatment plan being ineffective for the child. Existing counting and statistical methods only count the number of check-ins, ignoring the loss of effect caused by deviations in timing and interruptions in implementation, leading to a disconnect between assessment results and actual conditions, and failing to provide effective data support for doctors to adjust treatment plans. Summary of the Invention
[0004] To address the technical problem of only counting the number of check-ins while ignoring the loss of effects due to deviations in timing and interruptions in execution, leading to a disconnect between evaluation results and actual conditions, the present invention aims to provide a comprehensive TCM treatment efficacy evaluation and follow-up management system for pediatric constipation. The specific technical solution adopted is as follows: In a first aspect, embodiments of the present invention provide a comprehensive TCM treatment efficacy evaluation and follow-up management system for pediatric constipation, the system comprising: The nursing data acquisition module is used to obtain the start time of nursing actions and the submission time of nursing logs in the nursing record log. The operation behavior analysis module is used to analyze the submission delay based on the start time of the nursing behavior and the submission time of the nursing log, and determine the data timeliness weight; determine the interaction validity weight based on the page dwell time and the number of effective page touches in the log; and obtain a comprehensive confidence coefficient by combining the data timeliness weight and the interaction validity weight. The behavioral intervention analysis module is used to generate a standard reference time set based on the frequency of medical orders, determine the loss coefficient based on the time deviation between the start time of the nursing behavior and the standard reference time, and analyze the contribution of each operation based on the comprehensive confidence coefficient and the loss coefficient to determine the effective intervention value per day. The execution effect judgment module is used to construct an execution intensity integral iterative model based on the single-day effective intervention value, simulate the natural decay ratio through an exponential decay factor, and obtain an execution intensity score; generate a defecation score based on defecation frequency and defecation characteristics; and perform correlation analysis between the execution intensity score and the defecation score to judge the current execution effect.
[0005] Secondly, a method for evaluating and managing the efficacy of traditional Chinese medicine comprehensive treatment for childhood constipation is provided, the method comprising: Retrieve the start time of nursing actions and the submission time of nursing logs; Based on the start time of the nursing behavior and the submission time of the nursing log, the submission delay is analyzed to determine the data timeliness weight; based on the page dwell time and the number of effective page touches in the log, the interaction validity weight is determined; and by combining the data timeliness weight and the interaction validity weight, a comprehensive confidence coefficient is obtained. A standard reference time set is generated based on the frequency of medical orders. The loss coefficient is determined based on the time deviation between the start time of the nursing behavior and the standard reference time. The contribution of each operation is analyzed based on the comprehensive confidence coefficient and the loss coefficient to determine the effective intervention value per day. Based on the effective daily intervention value, an execution intensity integral iterative model is constructed by simulating the natural decay ratio through an exponential decay factor to obtain an execution intensity score; a defecation score is generated based on defecation frequency and defecation characteristics; and a correlation analysis is performed between the execution intensity score and the defecation score to determine the current execution effect.
[0006] Thirdly, embodiments of the present invention provide an electronic device, including a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, it implements the various possible implementations of the first aspect.
[0007] Fourthly, embodiments of the present invention provide a computer program product comprising: computer program code, which, when executed on a computer, causes the computer to perform the method described in the first aspect or any possible implementation thereof.
[0008] Fifthly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to perform the various possible implementations of the first aspect.
[0009] The embodiments of the present invention have at least the following beneficial effects: This invention first analyzes submission delays by analyzing the start time of nursing actions and the submission time of nursing logs, thus determining a data timeliness weight. The larger the time difference between the start time of nursing actions and the submission time of nursing logs, the lower the credibility of the nursing record. This data timeliness weight is used to reduce the overall confidence coefficient of the nursing record. By monitoring the user's dwell time on the form entry page and the number of effective page touches, a two-way constraint logic is used to determine the interaction validity weight. By combining the data timeliness weight and the interaction validity weight, a comprehensive confidence coefficient is obtained. This comprehensive confidence coefficient is constructed by integrating factors such as supplementary recording errors due to memory lapses and invalid records due to perfunctory work. It represents the credibility of the nursing record, improving the authenticity and usability of the basic data. When there is a deviation between the start time of nursing actions and the standard reference time, the treatment effect is likely to be compromised. Therefore, a reduction coefficient is determined based on the time deviation between the start time of nursing actions and the standard reference time. Then, based on the comprehensive confidence coefficient and the reduction coefficient, the contribution of each operation is analyzed to determine the effective intervention value per day. Furthermore, based on the daily effective intervention value, an exponential decay factor was introduced to simulate the natural loss of intervention effects over time, constructing a model to obtain an execution intensity score. This score reflects the impact of the timing and continuity of the intervention on the final intervention effect, characterizing the extent to which the patient received effective intervention. Then, a defecation score was determined based on the patient's current bowel movements. The patient's bowel movements can reflect the extent to which the intervention was received; a higher defecation score indicates a higher degree of effective intervention. Finally, a correlation analysis was performed between the execution intensity score and the defecation score to determine the current execution effect. This execution effect provides doctors with decision-making assistance based on objective data, avoiding misjudging the treatment as ineffective and frequently changing prescriptions when parents fail to execute the treatment correctly, and also avoiding blindly requiring parents to increase the frequency of operations when the treatment is indeed ineffective. This invention improves the accuracy of efficacy evaluation and enhances the efficiency and scientific rigor of follow-up consultation decisions. Attached Figure Description
[0010] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0011] Figure 1 This is a system block diagram of a comprehensive TCM treatment efficacy evaluation and follow-up management system for pediatric constipation provided in one embodiment of the present invention; Figure 2This is a flowchart illustrating the method for evaluating and managing the efficacy of traditional Chinese medicine comprehensive treatment for pediatric constipation, as provided in one embodiment of the present invention. Detailed Implementation
[0012] To further illustrate the technical means and effects of this invention in achieving its intended purpose, the following detailed description, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a comprehensive TCM treatment efficacy evaluation and follow-up management system for pediatric constipation proposed according to this invention.
[0013] In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments may be combined in any suitable form.
[0014] In the description of the embodiments of the present invention, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in the text is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. In addition, in the description of the embodiments of the present invention, "multiple" refers to two or more.
[0015] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.
[0016] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.
[0017] The embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art will recognize that, with technological advancements and the emergence of new scenarios, the technical solutions provided by the embodiments of the present invention are also applicable to similar technical problems.
[0018] The following description, in conjunction with the accompanying drawings, details the specific scheme of the comprehensive TCM treatment efficacy evaluation and follow-up management system for pediatric constipation provided by this invention.
[0019] Please see Figure 1 The diagram illustrates a system block diagram of a comprehensive TCM treatment efficacy evaluation and follow-up management system for pediatric constipation according to an embodiment of the present invention. The system includes the following modules: The nursing data acquisition module 10 is used to acquire the start time of nursing behavior and the submission time of nursing log in the nursing record log.
[0020] The system collects user operation logs in real time during nursing care activities through the client application's data interface. Each submission of a nursing record is encapsulated into a separate user operation log, which is then recorded as the nursing record log. This nursing record log contains two key time attributes: the start time of the nursing activity and the submission time of the nursing log.
[0021] Time of onset of nursing behavior For: The timestamp of the start of the nursing action actively selected by the user in the interface calendar control, representing the user's claimed operation time. Nursing log submission time. For: the time of onset of nursing behavior The timestamp received by the system server and written to the database represents the actual time when the data was generated. Taking the i-th nursing record as an example, the start time of the nursing action is the timestamp of the start time of the nursing action recorded in the i-th nursing record, and the nursing log submission time is the timestamp of the i-th nursing record being uploaded and submitted to the client application.
[0022] The start time of the nursing action corresponding to a nursing record and the submission time of the nursing log are collectively referred to as nursing log time data.
[0023] The operation behavior analysis module 20 is used to analyze the submission delay based on the start time of the nursing behavior and the submission time of the nursing log, and determine the data timeliness weight; determine the interaction validity weight based on the page dwell time and the number of effective page touches in the log; and obtain a comprehensive confidence coefficient by combining the data timeliness weight and the interaction validity weight.
[0024] This invention uses the difference between the start time of nursing behavior and the submission time of nursing logs to weight the credibility of nursing records. By monitoring the user's dwell time and effective touch count on the form submission page, and using two-way constraint logic to eliminate abnormal operations, excessively fast dwell time is considered perfunctory, and excessively slow dwell time is considered idle. This achieves the verification of offline entity behavior quality using two types of interaction behavior data: non-contact dwell time and effective touch count, resulting in an interaction validity weight. The interaction validity weight, to a certain extent, identifies perfunctory or cheating behavior during the form submission process, such as mechanically clicking rapidly to fill in orders, or idling for a long time after opening the page. Finally, by combining the data timeliness weight and the interaction validity weight, a comprehensive confidence coefficient is obtained.
[0025] Time verification is performed by checking the start time of the nursing action and the submission time of the nursing log. If the start time of the nursing action is greater than the submission time of the nursing log, it indicates that the user has selected a future time point. This behavior is unreasonable. Therefore, the nursing record corresponding to the start time of the nursing action and the submission time of the nursing log is forcibly judged as an invalid record, marked as abnormal data and discarded to prevent dirty data from entering the subsequent process.
[0026] As a specific embodiment of the present invention, after obtaining the nursing behavior start time and nursing log submission time, the submission delay time is determined based on the difference between the nursing behavior start time and nursing log submission time. Specifically, the difference between the nursing behavior start time and nursing log submission time is calculated as the submission delay time.
[0027] As a specific example of the present invention, for the i-th nursing record, the submission delay time is... The calculation formula is: ;in, The start time of the nursing action in the i-th nursing record; The submission time of the nursing log for the i-th nursing record.
[0028] When the submission delay time is less than 0, it means that the nursing action start time is greater than the nursing log submission time.
[0029] It should be noted that if the submission delay exceeds the preset historical tracing threshold, the reliability of the corresponding nursing behavior start time and nursing log submission time is extremely low. Although not directly discarded, the corresponding data timeliness weight is set to zero in subsequent calculations. In this embodiment of the invention, the preset historical tracing threshold is 7 days, which is 604,800 seconds. In other embodiments, the implementer can adjust this value according to the actual situation.
[0030] To quantify the impact of post-entry supplementation on data credibility, this invention introduces a data timeliness weight. Since the accuracy of user recall usually shows a non-linear decreasing trend over time, in this embodiment of the invention, a negative correlation is made between the submission delay duration and the data timeliness weight through an exponential decay function.
[0031] In a specific embodiment of the present invention, a data timeliness weight is obtained by negatively mapping the submission delay duration through an exponential decay function. Specifically, the data timeliness weight is calculated by using a piecewise function combined with an exponential decay model.
[0032] As an example of the present invention, the timeliness weight of the data in the i-th nursing record. The calculation formula is: Where exp is an exponential function with the natural constant e as the base; The submission delay time for the i-th nursing record; To remember the effective window size; This represents the memory decay rate.
[0033] In this embodiment of the invention, the size of the effective memory window indicates that when the submission delay time is within this range, the submitted nursing record is a reliable real-time record. The size of the effective memory window is determined based on user behavior statistical analysis. As an example, the size of the effective memory window is set to 86,400 seconds, which is equivalent to 24 hours. This means that as long as the difference between the start time of the nursing behavior and the submission time of the nursing log is within 24 hours, the data timeliness weight assigned to that nursing record is considered reliable. All are 1.0. The memory decay rate characterizes how quickly data reliability decreases after the effective window is exceeded. In this embodiment of the invention, it is set... This value ensures that the longer the delay, the smaller the output value of the exponential function, thus achieving a smooth reduction in weight for outdated data. The formula for calculating the data timeliness weight maps the simple time difference to a normalized weight between 0 and 1, objectively reflecting the quality of the data in the time dimension.
[0034] To identify perfunctory user behavior during the data entry process, such as mechanically clicking rapidly to complete tasks or leaving the page idle for extended periods, the system introduces an interaction validity weight. The interaction validity weight approaches 1 only when the average duration of a single touch falls within a reasonable operation range; too fast or too slow will result in a decrease in weight. In other words, only when the user's operation pace is within a normal range of moderate speed is the corresponding nursing record considered valid data. The interaction validity weight is determined based on the page dwell time and the number of effective page touches in the logs, specifically: Based on the page dwell time and effective page touch count in the logs, the average time for a single touch is determined; the average time for a single touch is compared with preset upper and lower limit thresholds to obtain the interaction effectiveness weight.
[0035] In one embodiment of the present invention, the ratio of page dwell time to the number of effective page touches in the log is used as the average time for a single touch. It should be noted that when the average time for a single touch is 0, it is treated as 0.
[0036] In one embodiment of the present invention, the interaction validity weight is obtained by comparing the average time of a single touch with preset upper and lower operation thresholds. The preset upper and lower operation thresholds include: a preset upper operation threshold and a preset lower operation threshold; an upper limit validity weight is determined based on the difference between the average time of a single touch and the preset upper operation threshold; a lower limit validity weight is determined based on the difference between the average time of a single touch and the preset lower operation threshold; and the upper limit validity weight and the lower limit validity weight are weighted and summed to obtain the interaction validity weight.
[0037] As an example of the present invention, the interaction validity weight of the i-th nursing record. The calculation formula is: ; Where exp is an exponential function with the natural constant as the base; and Sensitivity coefficient; Let be the average time taken for a single touch in the i-th nursing record; This is a preset lower limit threshold for operation; This is a preset operation upper limit threshold. In this embodiment of the invention, the sensitivity coefficient... The value is 0.02, and the sensitivity coefficient is... The value is 0.01. In other embodiments, the implementer may adjust the value according to the actual situation. The sensitivity coefficient ranges from [0.01, 0.05].
[0038] In this embodiment of the invention, a preset lower limit threshold is defined. The timeout is set to 500 milliseconds. This is the lower limit based on the typical response time of human-computer interaction. This is the average time taken for a single touch. When the value is significantly lower than this, the output of the first part of the function approaches 0, indicating that it is determined to be a case of rapid order manipulation. Preset operation upper limit threshold. The timeout is set to 300,000 milliseconds, which is equivalent to 5 minutes. This is the average time for a single touch. When the value is significantly higher than the preset operation limit threshold, the output of the second half approaches 0, indicating that it is determined to be an inactive AFK (away from keyboard) operation.
[0039] Then, by combining the data timeliness weight and the interaction validity weight, a comprehensive confidence coefficient is obtained; thus, the weights of the two dimensions, data timeliness weight and interaction validity weight, are combined to obtain the comprehensive confidence coefficient of a single nursing record.
[0040] In one embodiment of the present invention, the data timeliness weight and the interaction validity weight are weighted and summed to obtain a comprehensive confidence coefficient. The weights assigned to the data timeliness weight and the interaction validity weight are both 0.5; that is, the average of the data timeliness weight and the interaction validity weight is used as the comprehensive confidence coefficient.
[0041] In one embodiment of the present invention, the product of the data timeliness weight and the interaction validity weight is used as the comprehensive confidence coefficient.
[0042] The composite confidence coefficient ranges from 0 to 1. When the composite confidence coefficient is 0.1, the nursing record will hardly contribute to the subsequent calculation, while when the composite confidence coefficient is 0.9, the nursing record will be considered an effective intervention.
[0043] The behavioral intervention analysis module 30 is used to generate a standard reference time set based on the frequency of medical orders, determine the loss coefficient based on the time deviation between the start time of the nursing behavior and the standard reference time, and analyze the contribution of each operation based on the comprehensive confidence coefficient and the loss coefficient to determine the effective intervention value per day.
[0044] To address the issues of actual operation time deviating from medical orders and duplicate submission of nursing records within the same time period, the behavioral intervention analysis module first constructs a standard time, generates a standard reference time set based on the frequency of medical orders, and determines the loss coefficient by performing time difference mapping. Based on this loss coefficient and the comprehensive confidence coefficient, the contribution of each operation is analyzed, and the validity of the data is further quantified to obtain the effective intervention value for a single day.
[0045] First, it's necessary to clarify the specific times each day for nursing procedures to be performed on each patient. Therefore, a standard reference time set is generated based on the frequency of medical orders. This involves extracting the frequency requirements or suggested time periods from the electronic prescription, for example, a prescription of twice daily.
[0046] The abstract frequency is transformed into calculable, specific time points. Specifically, if the electronic prescription provides suggested time periods, such as 8:00 AM and 8:00 PM, these time points are directly parsed to generate the corresponding set of standard reference times; for example, the set of standard reference times... ;in, This is the standard reference time for the first operation; This serves as the standard reference time for the second operation. This is the standard reference time for the Mth operation.
[0047] If the electronic prescription only specifies the suggested frequency without specifying the exact time, the auto-completion rule is triggered: a specific suggested time is generated based on the principle of even distribution during the day. For example, if the frequency is 2 times, the default standard reference times are set as follows: and For example, if the frequency is 3 times, the default standard reference time is set as follows: and The time range of a natural day is limited to between 8:00 AM and 8:00 PM. The principle of uniform distribution of daylight in a natural day can be understood as dividing the time period evenly based on frequency within the twelve hours from 8:00 AM to 8:00 PM to obtain the corresponding standard timestamp.
[0048] After determining the standard reference time, assess the time when the user's care behavior begins. The degree of agreement with the standard reference time. The loss factor characterizing timing deviation. The effective value of a single operation is obtained by combining the comprehensive confidence coefficient, and is recorded as the effective intervention value for a single day.
[0049] Traverse the standard reference time set Each standard reference time in the standard reference time For example, in the daily nursing record sequence, search for all records falling under the heading "..." Nursing records within the effective tolerance time window centered on the effective tolerance time window, and the window width of that effective tolerance time window. The timeframe is 14,400 seconds, which is the number of nursing records within four hours before and after the search. For example, if the doctor's order is given at 8:00 AM, nursing records performed by the user between 4:00 AM and 12:00 PM are considered valid attempts for this task. Operations outside this range will not be matched with the task.
[0050] After matching the start time of nursing actions in the nursing records with the standard reference time, a loss factor is determined based on the time deviation between the start time of the nursing action and the standard reference time. In other words, within the effective tolerance time window, the difference between the start time of the nursing action in the nursing records and the matched standard reference time is analyzed to determine the loss factor.
[0051] As an example of the present invention, the depreciation coefficient corresponding to the i-th nursing record. The calculation formula is: Where max is the function for finding the maximum value; The standard reference time to match the i-th nursing record; The start time of the nursing action in the i-th nursing record; The window width is set to effectively tolerate the time window. The numerator is 0 when the start time of the nursing action recorded in the nursing record equals the matching standard reference time. This indicates that the operation was completely effective and without any loss.
[0052] As the difference between the onset time of the nursing action in the nursing record and the matching standard reference time increases, the numerator increases, and the ratio increases. , Gradually decrease. When the deviation reaches or exceeds... When the nursing intervention begins outside the effective tolerance window of the matching standard reference time, the reduction factor is applied. The value is set to zero. The impact of the timing of nursing operations on task quality is quantified by the formula for calculating the loss coefficient; the greater the deviation, the lower the score.
[0053] To address the issue of users submitting multiple times or repeatedly clocking in within the same valid tolerance time window, a deduplication and optimization process is implemented. Specifically: for those matching the standard reference time... The product of the overall confidence coefficient and the loss coefficient of all nursing records is used as the confidence level of a single nursing record.
[0054] When there are at least two nursing records within the effective tolerance time window, the maximum confidence level is used as the actual operational contribution to the standard reference time corresponding to the effective tolerance time window; when there is only one nursing record within the effective tolerance time window, the confidence level of the nursing record is used as the actual operational contribution to the standard reference time corresponding to the effective tolerance time window.
[0055] As a specific example of the present invention, the actual operational contribution of the standard reference time corresponding to the effective tolerance time window of the i-th nursing record. The calculation formula is: ;in, The nominal score for a single standard operation is set to 1.0 in this embodiment. is the overall confidence coefficient for the i-th nursing record. Let be the depreciation factor for the i-th nursing record; Within the effective tolerance time window corresponding to the i-th nursing record, by taking the maximum value, the best operation performed by the user within that time period is recognized, and other redundant submissions are automatically ignored. This prevents inflated scores while tolerating the user's trial-and-error behavior.
[0056] After obtaining the actual operational contribution corresponding to each standard reference time, the actual operational contributions corresponding to all standard reference times within a single day are summed to obtain the effective intervention value for that day.
[0057] As an example of the present invention, taking day d as an example, the effective intervention value for that day is... The calculation formula is: Where M represents the number of standard reference times on day d; based on this, to further enhance the robustness of the system and prevent extreme abnormal data from impacting subsequent models, such as logic vulnerabilities caused by attacks, a physiological saturation threshold truncation logic is introduced during aggregation. A preset upper limit threshold for daily input is set. In this embodiment of the invention, the preset upper limit threshold is set to If the calculated daily effective intervention value If this value is exceeded, the daily effective intervention value will be forcibly set to the preset upper limit threshold. It acts as a circuit breaker, ensuring that the data input into the subsequent integral model is always within a reasonable numerical range.
[0058] The execution effect judgment module 40 is used to construct an execution intensity integral iterative model based on the single-day effective intervention value, simulate the natural decay ratio through an exponential decay factor, and obtain an execution intensity score; generate a defecation score based on defecation frequency and defecation characteristics; and perform correlation analysis between the execution intensity score and the defecation score to judge the current execution effect.
[0059] Obtain discrete daily effective intervention values Next, it is necessary to further address the impact of operational interruptions on the overall execution performance. In practical management scenarios, user actions are sequentially correlated, and repeated poor execution results can lead to the loss of previously accumulated execution momentum or effects. To address this, the execution performance evaluation module introduces an exponential decay model to calculate a continuously integral sequence that dynamically changes over time.
[0060] The core of this module is to construct an execution intensity integral iterative model. This model treats the daily input as the filling of an intensity pool, while introducing a natural evaporation mechanism to simulate the loss of effects over time.
[0061] Index by treatment day Perform the following iterative calculations sequentially to generate the execution intensity score for day d of the execution intensity integral. : ;in, The performance intensity score for day d; The preset exponential decay factor; The performance intensity score for day d-1; This refers to the standard intervention value at the hospital level; This is a preset effectiveness conversion factor; This represents the effective intervention value for day d.
[0062] Preset exponential decay factor This characterizes the natural decay rate of the performance effect without new input to sustain it. A larger value indicates faster effect loss, requiring users to maintain a higher frequency of operations to sustain their score. The preset exponential decay factor is based on empirical data from behavioral management regarding habit formation and effect decay. As an example of this invention, the preset exponential decay factor... The value is set to 0.35. This means that if a user stops all activity today, i.e., enters 0, their accumulated points from yesterday will be automatically reduced by 35% by the end of today.
[0063] This is the total input for the day, which consists of two parts: effective intervention values from the family and standard treatment values from the hospital. First, the standard intervention values from the hospital: [The text abruptly ends here, likely due to an incomplete sentence or missing information.] This value is obtained by querying the hospital information system (HIS); if the child received in-hospital professional treatment on that day, then this standard intervention value... A preset standard high value is taken as an example of this invention; the preset standard high value is 2.0; otherwise, it is 0. Second, a preset effectiveness conversion factor: [Preset effectiveness conversion factor] This is a normalization coefficient used to balance the differences between professional and non-professional procedures. Since parents' procedures are generally less standardized than those of medical staff, a discounting process is needed to prevent excessive weighting of family-based data in the model. As an example of this invention, the preset efficacy discount coefficient is set to... .
[0064] To initiate recursive calculations, a day prior to the start of the treatment cycle is predefined. The integral state of ) is .
[0065] This iterative process outputs a continuous sequence of execution intensity scores. Each value in this sequence is an execution intensity score, which objectively includes the cumulative effect of historical execution and the incremental contribution of current execution. It is the ultimate quantitative indicator for assessing the degree of execution effectiveness.
[0066] Because the child's bowel log usually includes two dimensions: bowel movement frequency. Bristol Stool Characteristics Grading The Bristol Stool Characteristics Grading System, also known as the Stool Characteristics Grading System, is user-defined based on the Bristol Stool Characteristics Grading System. To facilitate numerical trend analysis, the system merges these two dimensions into a single scalar score. Specifically, a stool score is generated based on stool frequency and characteristics. This involves: generating a frequency severity item based on stool frequency; generating a characteristic severity item based on stool characteristics; and then weighted summing the frequency severity item and the characteristic severity item to obtain the final stool score.
[0067] As an example of the present invention, the first Daily bowel score The calculation formula is: ;in, For the severity of the trait item, according to the Bristol Scale, level 4 is the ideal stool. This item calculates the absolute difference between the actual trait and the ideal value of 4. Whether the stool is dry (levels 1-3) or loose (levels 5-7), the greater the deviation, the higher the value of this trait severity item, indicating more severe symptoms. As the first weight, it is set to 1 in one embodiment of the present invention. This is a frequency severity term, primarily targeting functional constipation, where the core issue is infrequent bowel movements. A penalty function is defined. :like That is, when there is no bowel movement on that day: This triggers a penalty. If... That is, when there is a bowel movement on that day: No penalty. A bowel score will be given if there is no bowel movement. Significantly elevated; if defecation is present, the defecation score depends primarily on the severity of the trait. As the second weight, it is set to 2 in one embodiment of the invention. Maintain... Greater than Second weight Greater than the first weight This is because defecation frequency is more important in constipation assessment.
[0068] It should be noted that if a user does not submit a bowel movement log on a given day, the system will, in order to maintain the continuity of the sequence, use the score of the most recent valid record by default, or mark it as missing and remove that day from the subsequent analysis window.
[0069] This resulted in a bowel score sequence aligned with the treatment day. A higher defecation score indicates more severe constipation symptoms; a lower defecation score indicates symptom relief.
[0070] After obtaining the execution intensity score sequence representing the input through the preceding module, and the defecation score sequence representing output Subsequently, an intervention-feedback correlation analysis was performed. Through a two-layer threshold judgment logic, the root causes of poor treatment efficacy were automatically identified, and corresponding classification labels were generated for reference.
[0071] The correlation analysis between the execution intensity score and the defecation score sequence was used to determine the current execution effect. First, set an evaluation time window, such as the past 7 days, and calculate the average performance intensity score within the evaluation time window. ; The average performance intensity score within the evaluation time window Less than the preset execution strength threshold At that time, the label corresponding to the execution effect is "insufficient execution capability"; When this occurs, it indicates that the parents' effective interventions failed to meet the minimum standards required to maintain an effective level within the assessment period. This could be due to insufficient frequency of interventions or significant deviations in the timing of interventions leading to excessive point deductions. In this case, a label indicating insufficient execution ability is generated as output. This triggers the following actions on the user side: automatically pushes a standard operation demonstration video and sends a reminder to parents that more frequent care is needed. It also triggers the following actions on the doctor's side: marks low compliance in the patient list, indicating to the doctor that there is no need to adjust the prescription at this time, but rather to focus on urging adherence.
[0072] The average performance intensity score within the evaluation time window Greater than or equal to the preset execution strength threshold The system determines whether the defecation score meets preset improvement conditions; in this embodiment of the invention, a preset execution intensity threshold is used. The value is 3. The preset execution intensity threshold is based on historical data statistics. Only when the accumulated execution intensity score exceeds the preset execution intensity threshold can an observable intervention effect be produced, and then the next step of judgment can be made.
[0073] When the defecation score does not meet the preset improvement conditions, the label corresponding to the execution effect is "no response to the solution". When the defecation score meets the preset improvement conditions, the label corresponding to the effect is "effective maintenance".
[0074] As an example of the present invention, the variation in defecation score within the same assessment time window is calculated. : ;in and These are the start and end dates of the evaluation time window, respectively. To assess bowel score on the first day of the time window; To assess bowel movement scores on the last day of the time window. When This indicates a decrease in symptom scores and some improvement in symptoms. This indicates that the symptoms have not improved or have worsened.
[0075] When the defecation score does not meet the preset improvement conditions, that is, when the change in the defecation score is less than or equal to the preset symptom improvement threshold, it indicates that the current situation is a typical high-input, low-output abnormal pattern. This indicates that the parents have followed the medical orders with high quality and frequency, and the execution intensity score is sufficient to resist natural decay, but the child's symptoms have not improved. This shows that the current intervention plan has an extremely low response rate to the patient. At this time, the output label is "No response to the plan," that is, the label corresponding to the execution effect is "No response to the plan." As a preferred embodiment of the present invention, triggering an action on the doctor's end, the label is highlighted on the doctor's workbench, and a prompt box pops up: "No improvement in symptoms detected under high-intensity execution, indicating no response to the plan. Please assess whether the intervention plan needs to be adjusted."
[0076] In this embodiment of the invention, the preset symptom improvement threshold is set to 0.5. In other embodiments, the implementer may adjust this value according to the time situation.
[0077] Conversely, when the defecation score meets the preset improvement condition, that is, when the change in the defecation score is greater than the preset symptom improvement threshold... When the output effect is effectively maintained, the label corresponding to the execution effect is "effectively maintained", indicating that the current treatment plan and execution intensity are well matched, and it is recommended to maintain the status quo.
[0078] This invention transforms the complex clinical attribution problem into a standardized data classification task, outputting objective and clear labels for doctors' decision-making reference, thus solving the technical problems of blind attribution and the disconnect between assessment results and actual situation.
[0079] Please see Figure 2 , Figure 2 This invention provides a flowchart of a method for evaluating and managing the efficacy of traditional Chinese medicine comprehensive treatment for pediatric constipation, comprising the following steps: Retrieve the start time of nursing actions and the submission time of nursing logs; Based on the start time of the nursing behavior and the submission time of the nursing log, the submission delay is analyzed to determine the data timeliness weight; based on the page dwell time and the number of effective page touches in the log, the interaction validity weight is determined; and by combining the data timeliness weight and the interaction validity weight, a comprehensive confidence coefficient is obtained. A standard reference time set is generated based on the frequency of medical orders. The loss coefficient is determined based on the time deviation between the start time of the nursing behavior and the standard reference time. The contribution of each operation is analyzed based on the comprehensive confidence coefficient and the loss coefficient to determine the effective intervention value per day. Based on the effective daily intervention value, an execution intensity integral iterative model is constructed by simulating the natural decay ratio through an exponential decay factor to obtain an execution intensity score; a defecation score is generated based on defecation frequency and defecation characteristics; and a correlation analysis is performed between the execution intensity score and the defecation score to determine the current execution effect.
[0080] Alternatively, the transmission medium may be a wired link, such as, but not limited to, coaxial cable, fiber optic cable and digital subscriber line, or a wireless link, such as, but not limited to, wireless Fidelity (WIFI), Bluetooth and mobile device networks.
[0081] It should be noted that the device provided in the above embodiments is only an example of the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above.
[0082] This invention provides a computer device. Exemplarily, the computer device includes: a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, the computer device can execute any of the aforementioned methods for evaluating and following up on the efficacy of traditional Chinese medicine-based comprehensive treatment for pediatric constipation.
[0083] Furthermore, embodiments of the present invention also protect an apparatus that may include a memory and a processor, wherein the memory stores executable program code, and the processor is used to call and execute the executable program code to execute the efficacy evaluation and follow-up management system for comprehensive TCM treatment of pediatric constipation provided in embodiments of the present invention.
[0084] In this embodiment of the invention, the device can be divided into functional modules according to the above method example. For example, each module can correspond to a separate function, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and is only a logical functional division. In actual implementation, there may be other division methods.
[0085] When each module is divided according to its function, the device may also include a signal uploading module, a determination module, and an adjustment module. It should be noted that all relevant content regarding the steps involved in the above method embodiments can be referenced from the functional descriptions of the corresponding modules, and will not be repeated here.
[0086] It should be understood that the device provided in this embodiment of the invention is used to perform the above-mentioned comprehensive TCM treatment efficacy evaluation and follow-up management system for pediatric constipation, and thus can achieve the same effect as the above-mentioned implementation method.
[0087] When using integrated units, the device may include a processing module and a storage module. When applied to a device, the processing module can be used to control and manage the device's operations. The storage module can be used to support the device in executing relevant program code, etc. The processing module may be a processor or a controller, which can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this invention. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a digital signal processor (DSP) and a microprocessor, etc., and the storage module may be a memory.
[0088] In addition, the device provided in the embodiments of the present invention may specifically be a chip, component or module. The chip may include a connected processor and a memory. The memory is used to store instructions. When the processor calls and executes the instructions, the chip can execute the efficacy evaluation and follow-up management system for comprehensive TCM treatment of pediatric constipation provided in the above embodiments.
[0089] This invention also provides a computer-readable storage medium storing computer program code. When the computer program code is run on a computer, the computer executes the aforementioned method steps to implement the pediatric constipation comprehensive TCM treatment efficacy evaluation and follow-up management system provided in the above embodiments.
[0090] This invention also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned steps to implement the pediatric constipation comprehensive TCM treatment efficacy evaluation and follow-up management system provided in the above embodiments.
[0091] In this invention, the apparatus, computer-readable storage medium, computer program product, or chip provided in the embodiments are all used to execute the corresponding methods described above. Therefore, the beneficial effects they achieve can be referred to the beneficial effects in the corresponding methods described above, and will not be repeated here. Through the above description of the embodiments, those skilled in the art will understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In the embodiments provided by this invention, it should be understood that the disclosed apparatus and method can be implemented in other ways.
[0092] The device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical functional division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.
[0093] It should also be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.
[0094] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0095] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.
[0096] The above content is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the protection scope of the present invention.
Claims
1. A comprehensive TCM treatment efficacy evaluation and follow-up management system for pediatric constipation, characterized in that, The system includes the following modules: The nursing data acquisition module is used to obtain the start time of nursing actions and the submission time of nursing logs in the nursing record log. The operational behavior analysis module is used to analyze submission delays and determine data timeliness weights based on the start time of the nursing behavior and the submission time of the nursing log. Based on the page dwell time and effective page touch count in the logs, the interaction validity weight is determined; combined with the data timeliness weight and the interaction validity weight, a comprehensive confidence coefficient is obtained. The behavioral intervention analysis module is used to generate a standard reference time set based on the frequency of medical orders, determine the loss coefficient based on the time deviation between the start time of the nursing behavior and the standard reference time, and analyze the contribution of each operation based on the comprehensive confidence coefficient and the loss coefficient to determine the effective intervention value per day. The execution effect judgment module is used to construct an execution intensity integral iterative model based on the single-day effective intervention value, simulate the natural decay ratio through an exponential decay factor, and obtain an execution intensity score; and generate a defecation score based on defecation frequency and defecation characteristics. The correlation analysis between the performance intensity score and the defecation score was performed to determine the current performance effect.
2. The pediatric constipation comprehensive TCM treatment efficacy evaluation and follow-up management system according to claim 1, characterized in that, The process of analyzing submission delays and determining data timeliness weights based on the start time of the nursing action and the submission time of the nursing log includes: The submission delay duration is determined based on the difference between the start time of the nursing action and the submission time of the nursing log. The data timeliness weight is obtained by negatively mapping the submission delay duration using an exponential decay function.
3. The pediatric constipation comprehensive TCM treatment efficacy evaluation and follow-up management system according to claim 1, characterized in that, The determination of interaction validity weights based on page dwell time and effective page touch counts in the logs includes: Based on the page dwell time and the number of effective page touches in the logs, the average time for a single touch is determined; The average time for a single touch is compared with preset upper and lower operation thresholds to obtain the interaction effectiveness weight.
4. The pediatric constipation comprehensive TCM treatment efficacy evaluation and follow-up management system according to claim 3, characterized in that, The step of comparing the average time of a single touch with preset upper and lower operation thresholds to obtain the interaction effectiveness weight includes: The preset operation upper and lower limit thresholds include: the preset operation upper limit threshold and the preset operation lower limit threshold; The effectiveness weight of the upper limit is determined based on the difference between the average time of a single touch and the preset operation upper limit threshold. The effectiveness weight of the lower limit is determined based on the difference between the average time of a single touch and the preset lower limit threshold. The interaction validity weight is obtained by weighted summing of the upper limit validity weight and the lower limit validity weight.
5. The pediatric constipation comprehensive TCM treatment efficacy evaluation and follow-up management system according to claim 1, characterized in that, The comprehensive confidence coefficient is obtained by combining the data timeliness weight and the interaction validity weight, including: The weighted sum of the data timeliness weight and the interaction validity weight is used to obtain the comprehensive confidence coefficient.
6. The pediatric constipation comprehensive TCM treatment efficacy evaluation and follow-up management system according to claim 1, characterized in that, The determination of the loss coefficient based on the time deviation between the start time of the nursing action and the standard reference time includes: For any standard reference time in the set of standard reference times, construct an effective tolerance time window; Within the effective tolerance time window, the difference between the start time of nursing behaviors in the nursing records and the matching standard reference time is analyzed to determine the loss factor.
7. The pediatric constipation comprehensive TCM treatment efficacy evaluation and follow-up management system according to claim 6, characterized in that, The step of analyzing the contribution of each operation based on the comprehensive confidence coefficient and the loss coefficient to determine the effective intervention value for a single day includes: For a single nursing record, the product of the overall confidence coefficient and the loss coefficient is calculated as the confidence level of the single nursing record; When there are at least two nursing records within the effective tolerance time window, the maximum confidence level is used as the actual operational contribution to the standard reference time corresponding to the effective tolerance time window; when there is only one nursing record within the effective tolerance time window, the confidence level of the nursing record is used as the actual operational contribution to the standard reference time corresponding to the effective tolerance time window. The effective intervention value for a single day is obtained by summing the actual operational contributions corresponding to all standard reference times within a single day.
8. The pediatric constipation comprehensive TCM treatment efficacy evaluation and follow-up management system according to claim 1, characterized in that, The constructed execution intensity integral iterative model is as follows: ； in, The performance intensity score for day d; The preset exponential decay factor; The performance intensity score for day d-1; This is the standard intervention value for hospitals; This is a preset effectiveness conversion factor; This represents the effective intervention value for day d.
9. The pediatric constipation comprehensive TCM treatment efficacy evaluation and follow-up management system according to claim 1, characterized in that, The defecation score is generated based on defecation frequency and defecation characteristics, including: Based on defecation frequency, generate a frequency severity item; based on defecation characteristics, generate a characteristics severity item. The defecation score is obtained by weighted summation of the frequency severity item and the trait severity item.
10. The pediatric constipation comprehensive TCM treatment efficacy evaluation and follow-up management system according to claim 1, characterized in that, The step of performing correlation analysis between the execution intensity score and the defecation score sequence to determine the current execution effect includes: When the average execution intensity score within the evaluation time window is less than the preset execution intensity threshold, the label corresponding to the execution effect is insufficient execution capability. If the average execution intensity score within the evaluation time window is greater than or equal to the preset execution intensity threshold, it is determined whether the defecation score meets the preset improvement conditions. When the defecation score does not meet the preset improvement conditions, the label corresponding to the execution effect is "no response to the solution". When the defecation score meets the preset improvement conditions, the label corresponding to the effect is "effective maintenance".