Tracking management method and system for long-term medication of endocrine patient

Abstract

The invention relates to the technical field of medical information, in particular to an endocrine patient long-term medication tracking management method and system, and the method comprises the following steps: extracting multiple pieces of key information in a prescription based on the electronic prescription information of a patient, recognizing the taking time and dosage information of multiple medicines, and sending medication reminding information to the patient, by monitoring the opening and closing state of the medicine box, the medicine taking time and quantity are recorded, and reminding and medicine taking monitoring information is generated. According to the method, the opening and closing state of the medicine box is monitored in real time, the taking time and quantity of medicine are recorded, the transparency of medicine treatment and the compliance of a patient are improved, physiological parameters of the patient are collected regularly, time sequence analysis and doctor feedback are matched, the change trend and periodic fluctuation of the illness state of the patient are accurately recognized, and the patient compliance is improved. By analyzing drug use logs of patients and doctors, effects of various drugs are identified, side effects are detected, drug doses and types are helped to be adjusted in time, the risk of adverse drug reactions is effectively reduced, and the treatment effect is improved.

Description

Technical Field

[0001] The present invention relates to the field of medical information technology, and particularly to a method and system for long-term medication tracking management of endocrine patients. Background Art

[0002] The field of medical information technology focuses on improving the quality and efficiency of healthcare through various information and communication technologies, including electronic health records, patient management systems, medical decision support systems, and telemedicine services. By accurately collecting, securely storing, and intelligently analyzing various patient physiological data, it aims to provide real-time medical information, improve the accuracy and accessibility of information, help doctors and patients make medical decisions, optimize treatment outcomes, and enhance patient satisfaction. Combining patient education and the public dissemination of health information promotes patient self-management and raises public health awareness.

[0003] Among them, the long-term medication tracking management method for endocrine patients aims to ensure that patients continuously and correctly use medications according to medical orders, monitor the efficacy and potential side effects of medications, and help doctors and patients track the treatment progress in real time, adjust and optimize the medication treatment plan, ensure the coherence and effectiveness of medication treatment, reduce the risk of adverse drug reactions, improve the transparency of treatment and patient compliance, and through continuous health monitoring, identify and handle health problems early, improve treatment effects and the quality of life of patients, by integrating electronic health records, automatic medication reminders, regular health assessments, and various functions.

[0004] Traditional medication tracking management methods lack real-time and personalized processing capabilities, cannot accurately track the actual use of medications in medication management and monitoring, limit the accuracy of medication efficacy assessment, increase the risk of adverse drug reactions, lack detection data on the opening and closing status of medicine boxes, cannot accurately grasp the medication situation of patients, affect the coherence and effectiveness of the medication treatment plan, are difficult to cope with complex and changing medical needs, lead to medical decisions made by patients and doctors without sufficient information support, and result in poor treatment effects. Summary of the Invention

[0005] To solve the technical problems of medication management and medication monitoring existing in the prior art, embodiments of the present invention provide a method and system for long-term medication tracking management of endocrine patients. The technical solutions are as follows: On the one hand, a method for long-term medication tracking management of endocrine patients is provided, and the method includes: S1: Based on the patient's electronic prescription information, extract multiple key information in the prescription, identify the taking time and dosage information of various medications, and send medication reminder information to the patient. By monitoring the opening and closing status of the medicine box, record the time and quantity of medication taken, and generate reminder and medication monitoring information; S2: Based on the reminder and medication monitoring information, regularly collect multiple physiological parameter data of the patient, combine the patient's personal information and timestamp, perform data preprocessing, and create a patient physiological data set; S3: Based on the patient's physiological data set, identify the change trend and periodic fluctuation of the patient's physiological data through time series analysis, predict the patient's condition evolution trend in combination with physician feedback, and output the change trend analysis results; S4: Based on the change trend analysis results, analyzing the medication logs of patients and doctors, identifying multiple keywords associated with drug effects and side effects in the logs, evaluating drug efficacy and detecting drug side effects, and generating drug tracking information; S5: Based on the drug tracking information and in combination with the patient's disease development trend, the effects of the existing drug dosage and type on the patient are evaluated, and the drug dosage and type are adjusted according to the evaluation results to generate medication dosage adjustment data.

[0006] As a further solution of the present invention, the reminder and medication monitoring information includes medication time information, dosage information of multiple drugs, and medication monitoring records; the patient physiological data set includes physiological parameter collection data, patient personal information, and timestamp information; the change trend analysis results include a prediction curve of disease progression, a trend chart of key physiological indicators, and periodic fluctuation analysis results; the drug tracking information includes drug effect feedback information, side effect detection results, and medication risk assessment information; the medication dosage adjustment data includes drug dosage adjustment records, drug type update records, and taking frequency information.

[0007] As a further solution of the present invention, based on the patient's electronic prescription information, multiple key information in the prescription is extracted, the taking time and dosage information of multiple drugs are identified, and medication reminder information is sent to the patient. By monitoring the opening and closing status of the medicine box, the time and amount of drug removal are recorded, and the steps of generating reminder and medication monitoring information are specifically as follows: S101: Based on the patient's electronic prescription information, analyze the prescription text, extract the drug name, dosage, frequency of use and precautions information, and generate a prescription information dataset; S102: Building a medication schedule based on the prescription information data set by identifying dosages and frequencies of multiple drugs; S103: Using the medication schedule, using sensors to monitor the opening and closing status of the medicine box, recording the time and amount of medication taken, monitoring the patient's medication taking status, and generating reminders and medication monitoring information.

[0008] As a further solution of the present invention, based on the reminder and medication monitoring information, multiple physiological parameter data of the patient are regularly collected, combined with the patient's personal information and timestamp, and data preprocessing is performed to create a patient physiological data set. Specifically, the steps are as follows: S201: Regularly collect multiple physiological parameter data of endocrine patients according to the reminder and medication monitoring information, record the collection time information, and generate a physiological parameter record; S202: Based on the physiological parameter record, collect the patient's personal information, including the patient's age, gender, medical history, and allergic drugs, and generate a patient information collection record; S203: Use the patient information collection record to clean the data, including removing outliers and filling in missing values, optimizing the data quality, and creating a patient physiological data set.

[0009] As a further solution of the present invention, based on the patient physiological data set, through time series analysis, identify the change trend and periodic fluctuation of the patient's physiological data, and combine with the doctor's feedback to predict the evolution trend of the patient's condition. The steps of outputting the change trend analysis result are specifically as follows: S301: Based on the patient physiological data set, sort multiple physiological parameters of endocrine patients according to the time information to generate a time series data set; S302: Based on the time series data set, identify the change trend and periodic fluctuation of multiple physiological data, and generate data trend and fluctuation information; S303: Based on the data trend and fluctuation information, combine with the doctor's feedback, analyze and predict the development direction of the patient's condition, and generate a change trend analysis result.

[0010] As a further solution of the present invention, the specific formula for analyzing and predicting the development direction of the patient's condition is: Wherein, represents the calculation result of the trend value at the current time point, refers to the current time point, refers to the first time period before the current time point, refers to the second time period before the current time point, refers to the third time period before the current time point, refers to the fourth time period before the current time point, represents the most recent patient physiological data point, represents the previous patient physiological data point, represents the patient physiological data point of the period before last, represents the patient physiological data point of an earlier period, is the weight of the data point, reflecting its importance to the prediction result, is the weight of the data point, is the weight of the data point, is the weight of The weight of the data point.

[0011] As a further aspect of the present invention, based on the change trend analysis result, analyze the medication logs of patients and doctors, identify multiple keywords associated with drug effects and side effects in the logs, evaluate the drug efficacy and detect drug side effects. The steps of generating drug tracking information are specifically as follows: S401: Based on the change trend analysis result, analyze the medication logs of patients and doctors, identify and extract multiple keywords associated with drug effects and side effects, and generate a keyword extraction record; S402: Based on the keyword extraction record, through semantic analysis of the extracted multiple keywords, identify the effects of multiple drugs on the target patient, detect the side effects of the drugs, and generate a keyword analysis result; S403: Based on the keyword analysis result, by analyzing the severity of multiple side effect types, evaluate the medication risk of the patient, and generate drug tracking information.

[0012] As a further aspect of the present invention, based on the drug tracking information, combined with the development trend of the patient's condition, evaluate the effects of the existing drug dosage and type on the patient, and adjust the drug dosage and type according to the evaluation result. The steps of generating medication dosage adjustment data are specifically as follows: S501: Based on the drug tracking information, combined with the development trend of the condition of endocrine patients, evaluate the drug adjustment needs of the target patient, and generate a demand analysis result; S502: Based on the demand analysis result, analyze and identify drugs with poor efficacy and side effect risks, calculate the adjustment priorities of multiple drugs, evaluate the drug types to be adjusted, and generate an adjustment type identification result; S503: According to the adjustment type identification result, considering the factors of the patient's weight, age, and gender, combined with the actual disease stage of the patient, calculate the dosage adjustment values of multiple drugs, and generate medication dosage adjustment data.

[0013] As a further aspect of the present invention, the specific formula for calculating the adjustment priorities of multiple drugs is: Wherein, represents the drug adjustment priority, represents the drug efficacy reduction rate, represents the severity of side effects, represents the patient weight impact factor, represents the patient age adjustment coefficient, is the weight of the efficacy reduction rate, is the weight of the severity of side effects, is the weight of the weight impact factor, is the weight of the age adjustment coefficient, is a factor for standardizing calculation results.

[0014] On the other hand, a long-term medication tracking management system for endocrine patients is provided. This system is applied to the long-term medication tracking management method for endocrine patients, and the system includes: The prescription text analysis module analyzes the prescription text based on the patient's electronic prescription information, extracts information such as drug name, dosage, taking frequency, and precautions, and generates prescription extraction information; The patient medication monitoring module calculates the taking time and sends reminder information based on the prescription extraction information, according to the taking dosage and frequency of multiple drugs, monitors the opening and closing state of the medicine box in combination with a sensor, evaluates the patient's medication compliance, and generates reminder and medication monitoring information; The physiological data acquisition module regularly acquires multiple physiological parameters of the patient based on the reminder and medication monitoring information, combines the patient's personal information and time stamp for data preprocessing, and generates a patient physiological data set; The patient condition analysis module uses time series analysis based on the patient physiological data set to identify the change trend and periodic fluctuations of the data, combines the physician's feedback to predict the condition change, and generates a change trend analysis result; The drug efficacy and side effect identification module analyzes the medication log based on the change trend analysis result, identifies keywords related to drug effects and side effects, evaluates the effect of the drug on the target patient, and detects the side effects of the drug, generating drug tracking information; The dosage adjustment analysis module adjusts the patient's medication dosage and type based on the drug tracking information, considering the patient's weight, age, gender, and combining the real-time condition information, generating medication dosage adjustment data.

[0015] The beneficial effects brought by the technical solutions provided in the embodiments of the present invention at least include: By real-time monitoring the opening and closing state of the medicine box and recording the taking time and quantity of drugs, the transparency of drug treatment and the patient's compliance are improved. Regularly acquiring the patient's physiological parameters, combined with time series analysis and physician feedback, accurately identify the change trend and periodic fluctuations of the patient's condition. By analyzing the medication logs of patients and doctors, identify the effects of multiple drugs and detect side effects, help adjust the drug dosage and type in a timely manner, effectively reduce the risk of drug adverse reactions, and improve the treatment effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0017] Figure 1 It is a schematic diagram of the working process of the present invention; Figure 2 It is a detailed flowchart of S1 of the present invention; Figure 3 It is a detailed flowchart of S2 of the present invention; Figure 4 It is a detailed flowchart of S3 of the present invention; Figure 5 It is a detailed flowchart of S4 of the present invention; Figure 6 It is a detailed flowchart of S5 of the present invention; Figure 7 It is a system flowchart of the present invention. Specific embodiments

[0018] The following will describe the technical solutions in the present invention with reference to the accompanying drawings.

[0019] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as an "example" in the present invention should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of the word "example" is intended to present concepts in a specific manner. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one of the two can be selected.

[0020] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, the meanings they express are the same. "(of)", "corresponding", and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, the meanings they express are the same.

[0021] In the embodiments of the present invention, sometimes subscripts such as W 1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meanings they express are the same.

[0022] To make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments.

[0023] The embodiments of the present invention provide a method for long-term medication tracking and management of endocrine patients, such as Figure 1 shown in the flowchart of the method for long-term medication tracking and management of endocrine patients. The processing flow of this method can include the following steps: S1: Based on the patient's electronic prescription information, extract multiple key information in the prescription, identify the taking time and dosage information of various drugs, and send medication reminder information to the patient. By monitoring the opening and closing status of the medicine box, record the time and quantity of medicine taken, and generate reminder and medication monitoring information; S2: Based on the reminder and medication monitoring information, regularly collect multiple physiological parameter data of the patient, combine the patient's personal information and time stamp, perform data preprocessing, and create a patient physiological data set; S3: Based on the patient physiological data set, through time series analysis, identify the change trend and periodic fluctuation of the patient's physiological data, combine with the doctor's feedback, predict the evolution trend of the patient's condition, and output the change trend analysis result; S4: Based on the change trend analysis result, analyze the medication logs of the patient and the doctor, identify multiple keywords associated with drug effects and side effects in the logs, evaluate the drug efficacy and detect drug side effects, and generate drug tracking information; S5: Based on the drug tracking information, combine with the development trend of the patient's condition, evaluate the effect of the existing drug dosage and type on the patient, and adjust the drug dosage and type according to the evaluation result, and generate medication dosage adjustment data.

[0024] The reminder and medication monitoring information includes medication time information, dosage information of various drugs, and medication situation monitoring records. The patient physiological data set includes physiological parameter acquisition data, patient personal information, and time stamp information. The change trend analysis result includes the prediction curve of the disease progression, the trend chart of key physiological indicators, and the periodic fluctuation analysis result. The drug tracking information includes drug effect feedback information, side effect detection results, and medication risk assessment information. The medication dosage adjustment data includes drug dosage adjustment records, drug type update records, and taking frequency information.

[0025] Please refer to Figure 2 , based on the patient's electronic prescription information, the steps of extracting multiple key information in the prescription, identifying the taking time and dosage information of various drugs, and sending medication reminder information to the patient. By monitoring the opening and closing status of the medicine box, record the time and quantity of medicine taken, and generate reminder and medication monitoring information are specifically as follows: S101: Based on the patient's electronic prescription information, analyze the prescription text, extract drug name, dosage, taking frequency, and precautions information, and generate a prescription information data set; In sub-step S101, through natural language processing techniques, including text mining techniques, the text content in the prescription is systematically analyzed. The process involves the extraction of information such as drug names, dosages, administration frequencies, and precautions. Text analysis tools are applied for part-of-speech tagging and entity recognition. By using text processing libraries such as SpaCy or NLTK, key information in the text is identified. For example, drug names are identified as nouns, and dosages and frequencies are located for numbers and units through pattern recognition. Based on the extracted information, a preliminary prescription information dataset is constructed. Each record contains the specific drug name, dosage, administration frequency, and corresponding precautions. The dataset will serve as the basis for subsequent processing steps to ensure the accuracy and availability of the data, forming a structured prescription information dataset for further analysis.

[0026] S102: Based on the prescription information dataset, construct a medication schedule by identifying the dosages and frequencies of multiple drugs. In sub-step S102, using association rule learning in data mining techniques, identify the patient's medication patterns and construct a personalized medication schedule. Apply clustering algorithms to classify drug types and administration times, identify common administration time and dosage patterns, use decision tree algorithms to determine the medication rules, input the data into the model, predict the medication time based on the patient's actual medication records, and automatically generate a medication schedule for each patient. The schedule records the specific administration time points of each drug to ensure that patients take their medications on time. The schedule is very crucial in practical applications and can be dynamically adjusted according to the patient's actual situation to improve the compliance rate of the treatment plan.

[0027] S103: Utilize the medication schedule, use sensors to monitor the opening and closing status of the medicine box, record the time and quantity of drug retrieval, monitor the patient's medication status, and generate reminder and medication monitoring information. In the above content, use sensors to monitor the opening and closing status of the medicine box, and calculate the average value of the medication time deviation according to the formula . In the formula, represents the average medication time deviation, represents the th actual time of opening the medicine box, represents the th scheduled medication time, represents the total number of times the medicine box is opened and closed during the monitoring period; Detailed explanation of the formula and the derivation process of the formula calculation: Assume that the preset medication times for the target patient are 8:00, 12:00, 16:00, 20:00, 22:00, and the actual times are 8:05, 11:50, 16:15, 20:03, 22:10 respectively. Convert them to minutes: , , , , , , , , , , Calculate : ; ; ; ; The result of 8.6 minutes indicates that the deviation between the average time of each medication and the scheduled time is 8.6 minutes. The calculation process is used to evaluate the time accuracy of the patient's medication intake, helping medical providers adjust the medication reminder system and improve the patient's medication compliance.

[0028] Please refer to Figure 3 , based on the reminder and medication monitoring information, regularly collect multiple physiological parameter data of the patient, combine the patient's personal information and timestamp, and perform data preprocessing. The steps to create the patient physiological dataset are as follows: S201: According to the reminder and medication monitoring information, regularly collect multiple physiological parameter data of the endocrine patient, record the collection time information, and generate a physiological parameter record; In the sub-step of S201, regularly collect the heart rate, blood pressure, and blood sugar of the endocrine patient, and use a biosensor to perform real-time monitoring of the data. For each data collection, the system automatically records the collection timestamp to ensure the accuracy of data tracking. During the collection process, the data is transmitted to the central database through a wireless network, and the AES encryption algorithm is used to ensure the security of data transmission. After the data reaches the database, it undergoes preliminary formatting and classification storage through a preset data processing process. The device time and server time are automatically calibrated for each data collection to ensure the consistency and accuracy of the time information. The generated physiological parameter record includes specific measurement values, the specific date and time of each measurement, providing a basis for subsequent data analysis and patient condition monitoring.

[0029] S202: Based on the physiological parameter record, collect the patient's personal information, including the patient's age, gender, medical history, and allergic medications, and generate a patient information collection record; In sub-step S202, the age, gender, medical history, and information on allergic drugs of the patient are collected. The collection process is carried out by medical staff using an electronic health record system. The system has a preset data input template to ensure the comprehensive collection of all necessary information. During the input process, data validation techniques such as regular expression matching are used to ensure the correctness and integrity of the information format. For example, the age field only accepts numerical input, and the gender field is limited to options such as male / female. In this way, a patient information collection record is generated, and each patient's record has a unique identifier for subsequent data tracking and access.

[0030] S203: Using the patient information collection record, clean the data, including removing outliers and filling in missing values, optimizing the data quality, and creating a patient physiological data set; In sub-step S203, box plot analysis and multiple imputation techniques are used to identify and process outliers in the data. Specifically, through box plot analysis, data points outside the normal physiological range are quickly identified and removed. For missing data values, they are reasonably filled according to the statistical characteristics of the existing data using multiple imputation techniques. The process is carried out using the mice package in the R language to ensure the scientificity and rationality of data filling. The cleaned data set will be further evaluated for quality, including checking data integrity and verifying data accuracy. The process ensures that the generated patient physiological data set has high availability and reliability in subsequent medical research and clinical applications. The entire data cleaning and optimization process is automatically completed on the data analysis platform, improving the processing efficiency and data quality.

[0031] Please refer to Figure 4 , based on the patient physiological data set, through time series analysis, identify the changing trends and periodic fluctuations of the patient's physiological data, and combined with the feedback from physicians, predict the evolution trend of the patient's condition. The specific steps for outputting the analysis results of the changing trends are as follows: S301: Based on the patient physiological data set, sort multiple physiological parameters of endocrine patients according to time information to generate a time series data set; In sub-step S301, use time information to sort the data. The Pandas library in the Python programming language is used to process the data. The time series functions provided by the Pandas library can conveniently handle indexing, sorting, and storing time data. Set the timestamp field in the data set as the index, sort all records in ascending order of time, and observe the changing trends of each physiological parameter over time to ensure that each record is arranged in chronological order, which is beneficial for subsequent time series analysis. The generated time series data set includes multiple parameters such as heart rate, blood pressure, and blood sugar at each time point. The target data is accurately sorted according to the actual collection time, enabling subsequent analysis to accurately reflect the time dependence and dynamic changes of the patient's state.

[0032] S302: Based on the time series dataset, identify the changing trends and periodic fluctuations of various physiological data, and generate data trend and fluctuation information; In sub-step S302, based on the constructed time series dataset, use statistical analysis methods to identify the changing trends and periodic fluctuations of various physiological data. Analyze the time series characteristics in the data using the autoregressive moving average model, which is implemented through the forecast package in R language. Conduct stationarity detection on the time series data to ensure that the data is suitable for the autoregressive model. According to the autocorrelation and partial autocorrelation of the data, select appropriate model parameters for trend and periodic analysis. The results reveal the main changing trends and potential periodic fluctuations of each physiological parameter over time, such as the daily fluctuations of heart rate and blood pressure and the impact period of drug taking on blood sugar. The target trend and fluctuation information provides valuable data support for doctors.

[0033] S303: Based on the data trend and fluctuation information, combined with the feedback from physicians, analyze and predict the development direction of the patient's condition, and generate the change trend analysis result; The specific formula for analyzing and predicting the development direction of the patient's condition is: Among them, represents the calculation result of the trend value at the current time point, refers to the current time point, refers to the first time period before the current time point, refers to the second time period before the current time point, refers to the third time period before the current time point, refers to the fourth time period before the current time point, represents the most recent physiological data point of the patient, represents the physiological data point of the patient in the previous period, represents the physiological data point of the patient in the period before the previous period, represents the physiological data point of the patient in an earlier period, is for the weight of the data point, reflecting its importance to the prediction result, is for the weight of the data point, is for the weight of the data point, is for the weight of the data point.

[0034] Formula: ; Detailed explanation of the formula and the derivation process of formula calculation: The formula is used to calculate the weighted trend value of the disease development and predict the future development state of the disease; Meaning and setting values of parameters: : The disease assessment score of the most recent period, assumed to be 75 points; : The disease assessment score of the previous period, assumed to be 70 points; : The disease assessment score of the period before the previous period, assumed to be 72 points; : The disease assessment score of an earlier period, assumed to be 68 points; : The weight of the most recent data point, assumed to be 0.4; : The weight of the data point in the previous period, assumed to be 0.3; : The weight of the data point in the period before the previous period, assumed to be 0.2; : The weight of the earliest data point, assumed to be 0.1; Substitute the parameters into the formula for calculation: ; ; ; ; Calculation result It shows that the weighted average disease assessment score of the four time points currently considered is 72.2. The value is used to help doctors understand the trend of the patient's disease control, adjust the treatment plan and drug dosage.

[0035] Please refer to Figure 5 , based on the results of the trend analysis, analyze the medication logs of the patient and the doctor, identify multiple keywords associated with drug effects and side effects in the logs, evaluate the drug efficacy and detect drug side effects. The specific steps for generating drug tracking information are as follows: S401: Based on the results of the trend analysis, analyze the medication logs of the patient and the doctor, identify and extract multiple keywords associated with drug effects and side effects, and generate keyword extraction records; In sub-step S401, use the keyword extraction method in text mining technology, such as the term frequency-inverse document frequency algorithm, supplemented by the natural language processing library NLTK for part-of-speech tagging and stop word filtering, convert the text data in the medication logs into an analyzable format, apply the TFIDF algorithm to identify high-frequency and discriminative keywords in the text, the target keywords are mainly related to drug effects and potential side effects, extract information points directly related to drug effects from a large amount of text data, and the generated keyword extraction records list the names of each drug and related effect and side effect keywords, providing basic data for further drug effect analysis and safety assessment.

[0036] S402: Based on the keyword extraction records, through semantic analysis of multiple extracted keywords, identify the effects of various drugs on the target patient, detect the side effects of the drugs, and generate keyword analysis results; In sub-step S402, semantic analysis techniques such as latent semantic analysis are adopted. By constructing a matrix of terms and documents, applying singular value decomposition to extract the implicit structure of the text data, identifying the relationships between word meanings, systematically detecting the key effects and common side effects of drugs, the generated keyword analysis results summarize the main therapeutic effects and side effects of each drug, provide decision-making support information for medical professionals, ensure the safety of drug use, help patients understand possible health risks, and promote effective communication between patients and doctors.

[0037] S403: Based on the keyword analysis results, by analyzing the severity of multiple side effect types, evaluate the drug use risk of the patient and generate drug tracking information; In sub-step S403, risk assessment models such as logistic regression analysis are used to quantify the drug use risk of the patient according to the frequency and severity of side effects, classify the side effect types by severity, calculate the probability of each side effect and the resulting health consequences. The generated drug tracking information describes the potential risks of various side effects and the overall safety of drug use, provides a scientific basis for doctors to adjust prescriptions or take preventive measures, ensures the safety and effectiveness of patient drug use, and the target information is integrated into the patient's health record to guide future treatment and drug use supervision.

[0038] Please refer to Figure 6 , based on the drug tracking information, combined with the development trend of the patient's condition, evaluate the effects of the existing drug dosage and type on the patient, and adjust the drug dosage and type according to the evaluation results. The specific steps for generating drug dosage adjustment data are as follows: S501: Based on the drug tracking information, combined with the development trend of the condition of endocrine patients, evaluate the drug adjustment needs of the target patient and generate a needs analysis result; In sub-step S501, a decision support system is used to analyze the association between the patient's condition and drug response, and the association rule analysis method in data mining technology is adopted. By deeply analyzing the historical data set, identify the patterns between the changes in the condition and the drug effects. The analysis process takes into account the historical trend data of the patient's condition, drug use records, and relevant health indicators. The generated needs analysis result describes the drug adjustment needs of patients at different disease stages, including the situations of needing to increase the dosage or change the drug, and the urgency of drug adjustment. The result provides a scientific basis for doctors to formulate or adjust treatment plans, ensuring that the drug treatment plan is closely linked to the actual condition of the patient.

[0039] S502: Based on the results of the requirements analysis, analyze and identify drugs with poor efficacy and the risk of side effects, calculate the adjustment priorities of multiple drugs, evaluate the types of drugs that need to be adjusted, and generate the adjustment type identification results; The specific formula for calculating the adjustment priorities of multiple drugs is: Among them, represents the drug adjustment priority, represents the drug efficacy reduction rate, represents the severity of side effects, represents the patient weight impact factor, represents the patient age adjustment coefficient, is the weight of the efficacy reduction rate, is the weight of the severity of side effects, is the weight of the weight impact factor, is the weight of the age adjustment coefficient, is the factor used to standardize the calculation results.

[0040] Formula: ; Detailed explanation of the formula and the derivation process of formula calculation: The formula is used to evaluate the priority of drug adjustment, and the result is used to determine the drug adjustment strategy; Parameter meaning and setting values: is the drug efficacy reduction rate, assuming ; is the severity of side effects, assuming ; is the patient weight impact factor, assuming ; is the patient age adjustment coefficient, assuming ; , , , are the weight coefficients of the corresponding factors, which are adjusted according to the severity of the patient's condition and treatment needs. Assuming , , , ; is the normalization factor, assuming it is 1; Substitute the parameters into the formula for calculation: ; ; Result It indicates that the priority of drug adjustment is relatively low, meaning that under the current parameter settings, the efficacy of the drug decreases and the risk of side effects is relatively controllable, and further monitoring or minor drug adjustments are required.

[0041] S503: According to the adjustment type recognition result, considering the patient's weight, age, and gender factors, combined with the patient's actual disease stage, calculate the dose adjustment values of multiple drugs to generate medication dose adjustment data; In sub-step S503, a pharmacological calculation model is used, including a pharmacokinetic model. The model considers the patient's physiological parameters to adjust the drug dose, predicts the response of different patient groups to the drug through the absorption, distribution, metabolism, and excretion characteristics of the drug. The generated medication dose adjustment data provides specific dose recommendations, including the specific adjustment values and dosing frequencies of each drug. The target data helps doctors customize personalized drug treatment plans for each patient, improve treatment effects, reduce the risk of side effects, and optimize the overall treatment effect and quality of life of the patient.

[0042] Please refer to Figure 7 , a long-term medication tracking management system for endocrine patients. The long-term medication tracking management system for endocrine patients is used to execute the above-mentioned long-term medication tracking management method for endocrine patients. The system includes: The prescription text analysis module analyzes the prescription text based on the patient's electronic prescription information, extracts information such as drug names, doses, dosing frequencies, and precautions, and generates prescription extraction information; The patient medication monitoring module calculates the medication time and sends reminder messages based on the prescription extraction information, according to the dosing amounts and frequencies of multiple drugs, and monitors the opening and closing status of the medicine box in combination with sensors to evaluate the patient's medication compliance, and generates reminder and medication monitoring information; The physiological data collection module regularly collects multiple physiological parameters of the patient based on the reminder and medication monitoring information, combines the patient's personal information and time stamps, and performs data preprocessing to generate a patient physiological data set; The patient condition analysis module uses time series analysis based on the patient physiological data set to identify the change trends and periodic fluctuations of the data, combines the feedback from physicians, predicts the condition changes, and generates change trend analysis results; The drug efficacy and side effect identification module analyzes the medication log based on the change trend analysis result, identifies keywords related to drug effects and side effects, evaluates the effect of the drug on the target patient, and detects the side effects of the drug to generate drug tracking information; The dose adjustment analysis module adjusts the patient's medication dose and type based on the drug tracking information, considering the patient's weight, age, and gender, combined with the real-time condition information, to generate medication dose adjustment data.

[0043] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that contains one or more collections of available media. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, or a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0044] It should be understood that the term “and / or” in this document is merely a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. In addition, the character “ / ” in this document generally represents an “or” relationship between the associated objects before and after, but it may also represent an “and / or” relationship, which can be specifically understood by referring to the context.

[0045] In the present invention, “at least one” means one or more, and “a plurality” means two or more. “At least one of the following” or its similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0046] It should be understood that in various embodiments of the present invention, the order numbers of the above processes do not imply the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0047] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0048] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the devices, apparatuses, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0049] In several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0050] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0051] In addition, the functional units in each embodiment of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0052] When the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0053] As described above, the above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A method for tracking and managing long-term medication for endocrine patients, characterized in that: The method comprises: Based on the patient's electronic prescription information, it extracts multiple key information from the prescription, identifies the time and dosage information of multiple drugs, and sends medication reminder information to the patient. By monitoring the opening and closing status of the medicine box, it records the time and quantity of drug removal, and generates reminder and medication monitoring information; Based on the reminder and medication monitoring information, multiple physiological parameter data of the patient are regularly collected, combined with the patient's personal information and timestamp, data preprocessing is performed to create a patient physiological data set; Based on the patient's physiological data set, identify the change trend and periodic fluctuation of the patient's physiological data through time series analysis, predict the patient's condition evolution trend in combination with physician feedback, and output the change trend analysis results; Based on the change trend analysis results, analyzing the medication logs of patients and doctors, identifying multiple keywords associated with drug effects and side effects in the logs, evaluating drug efficacy and detecting drug side effects, and generating drug tracking information; Based on the drug tracking information and in combination with the patient's disease development trend, the effects of existing drug dosages and types on patients are evaluated, and the drug dosages and types are adjusted according to the evaluation results to generate medication dosage adjustment data.

2. The method for tracking and managing long-term medication for endocrine patients according to claim 1, characterized in that: The reminder and medication monitoring information includes medication time information, dosage information of multiple drugs, and medication monitoring records. The patient physiological data set includes physiological parameter collection data, patient personal information, and timestamp information. The change trend analysis results include a prediction curve of disease progression, a trend chart of key physiological indicators, and periodic fluctuation analysis results. The drug tracking information includes drug effect feedback information, side effect detection results, and medication risk assessment information. The medication dosage adjustment data includes drug dosage adjustment records, drug type update records, and frequency of administration information.

3. The method for tracking and managing long-term medication for endocrine patients according to claim 1, characterized in that: Based on the patient's electronic prescription information, extract multiple key information from the prescription, identify the time and dosage information of multiple drugs, and send medication reminder information to the patient. By monitoring the opening and closing status of the medicine box, record the time and quantity of drug removal, and generate reminders and medication monitoring information, the specific steps are as follows: Based on the patient's electronic prescription information, the prescription text is analyzed to extract the drug name, dosage, frequency of use and precautions information to generate a prescription information dataset; Based on the prescription information data set, construct a medication schedule by identifying dosages and frequencies of multiple drugs; The medication schedule is used to monitor the opening and closing status of the medicine box using sensors, record the time and amount of medication taken, monitor the patient's medication taking status, and generate reminders and medication monitoring information.

4. The method for tracking and managing long-term medication for endocrine patients according to claim 1, characterized in that: Based on the reminder and medication monitoring information, multiple physiological parameter data of the patient are regularly collected, combined with the patient's personal information and timestamp, and data preprocessing is performed to create the patient's physiological data set. The specific steps are: According to the reminder and medication monitoring information, multiple physiological parameter data of endocrine patients are regularly collected, and the collection time information is recorded to generate physiological parameter records; Based on the physiological parameter records, collect the patient's personal information, including the patient's age, gender, medical condition, and allergic drugs, and generate a patient information collection record; The patient information collection records are used to clean the data, including removing outliers, filling missing values, optimizing data quality, and creating a patient physiological data set.

5. The method for tracking and managing long-term medication for endocrine patients according to claim 1, characterized in that: Based on the patient's physiological data set, the change trend and periodic fluctuation of the patient's physiological data are identified through time series analysis, and the patient's condition evolution trend is predicted in combination with the physician's feedback. The steps of outputting the change trend analysis result are specifically as follows: Based on the patient physiological data set, multiple physiological parameters of the endocrine patient are sorted according to time information to generate a time series data set; Based on the time series data set, identifying the change trends and periodic fluctuations of various physiological data, and generating data trend and fluctuation information; Based on the data trends and fluctuation information, combined with physician feedback, the direction of the patient's disease progression is analyzed and predicted, and change trend analysis results are generated.

6. The method for tracking and managing long-term medication for endocrine patients according to claim 5, characterized in that: The specific formula for analyzing and predicting the direction of the patient's disease progression is: in, Represents the trend value calculation result at the current time point, Refers to the current time point, Refers to the first time period before the current time point. Refers to the second time period before the current time point. Refers to the third time period before the current time point, Refers to the fourth time period before the current time point. Represents the most recent patient physiological data point, Represents the patient's physiological data points in the previous period, Represents the patient's physiological data points from the previous period, Represents earlier patient physiological data points, Yes The weight of a data point reflects its importance to the prediction result. Yes The weight of the data point, Yes The weight of the data point, Yes The weight of the data point.

7. The method for tracking and managing long-term medication for endocrine patients according to claim 1, characterized in that: Based on the change trend analysis results, the steps of analyzing the medication logs of patients and doctors, identifying multiple keywords related to drug effects and side effects in the logs, evaluating drug effects and detecting drug side effects, and generating drug tracking information are as follows: Based on the change trend analysis results, analyzing the medication logs of patients and doctors, identifying and extracting a plurality of keywords associated with drug effects and side effects, and generating keyword extraction records; Based on the keyword extraction record, by performing semantic analysis on the extracted multiple keywords, the effects of multiple drugs on target patients are identified, the side effects of the drugs are detected, and keyword analysis results are generated; Based on the keyword analysis results, the severity of various side effect types is analyzed to evaluate the patient's medication risk and generate drug tracking information.

8. The method for tracking and managing long-term medication for endocrine patients according to claim 1, characterized in that: Based on the drug tracking information, combined with the patient's disease development trend, the effect of the existing drug dosage and type on the patient is evaluated, and the drug dosage and type are adjusted according to the evaluation results. The steps of generating the drug dosage adjustment data are as follows: Based on the drug tracking information and combined with the disease development trend of the endocrine patient, the drug adjustment needs of the target patient are evaluated to generate a demand analysis result; Based on the demand analysis results, analyze and identify drugs with poor efficacy and risks of side effects, calculate adjustment priorities for multiple drugs, evaluate the types of drugs that need to be adjusted, and generate adjustment type identification results; According to the adjustment type identification result, taking into account the patient's weight, age, and gender factors, combined with the patient's actual disease stage, the dosage adjustment values ​​of multiple drugs are calculated to generate medication dosage adjustment data.

9. The method for tracking and managing long-term medication for endocrine patients according to claim 8, characterized in that: The specific formula for calculating the adjustment priority of multiple drugs is: in, Represents the priority of drug adjustment, Indicates the rate of reduction in drug efficacy. Indicates the severity of the side effects, represents the patient weight influencing factor, represents the patient age adjustment factor, is the weight of the efficacy reduction rate, is the weight of the severity of the side effect, is the weight of the weight influencing factor, is the weight of the age adjustment coefficient, is the factor used to normalize the calculation results.

10. A long-term medication tracking and management system for endocrine patients, characterized in that: According to any one of claims 1 to 9, the method for tracking and managing long-term medication for endocrine patients comprises: The prescription text analysis module analyzes the prescription text based on the patient's electronic prescription information, extracts the drug name, dosage, frequency of use and precautions, and generates prescription extraction information; The patient medication monitoring module extracts information based on the prescription, calculates the medication time and sends reminder information according to the dosage and frequency of multiple drugs, combines sensors to monitor the opening and closing status of the medicine box, evaluates the patient's medication compliance, and generates reminders and medication monitoring information; The physiological data collection module regularly collects multiple physiological parameters of the patient based on the reminder and medication monitoring information, performs data preprocessing in combination with the patient's personal information and timestamp, and generates a patient physiological data set; The patient condition analysis module uses time series analysis based on the patient's physiological data set to identify the change trend and periodic fluctuation of the data, and combines physician feedback to predict the change of the condition and generate a change trend analysis result; The drug efficacy and side effect identification module analyzes the medication log based on the change trend analysis results, identifies keywords related to drug efficacy and side effects, evaluates the effect of the drug on the target patient, detects the side effects of the drug, and generates drug tracking information; The dosage adjustment analysis module adjusts the patient's medication dosage and type based on the medication tracking information, taking into account the patient's weight, age, and gender, and combining real-time condition information to generate medication dosage adjustment data.

Images