Intelligent hospital guide and tracking return visit recording integrated system for medical examination

Abstract

The invention discloses an intelligent hospital guide and tracking return visit recording integrated system for medical examination, which relates to the technical field of intelligent medical treatment, and comprises the following steps: based on a comprehensive data set, using an A-star algorithm to identify a hospital guide path; in the process that the patient waits for the hospital according to the hospital guide path, the system collects behavior data of the patient in real time; based on historical data, training a waiting time difference prediction model, inputting the patient behavior data into the waiting time difference prediction model, and predicting a waiting time deviation value; dynamically adjusting a hospital guide path according to the waiting time deviation value; and after the patient finishes visiting according to the adjusted hospital guide path, the system automatically provides health propaganda and education contents, collects patient feedback data and stores the patient feedback data in the tracking return visit system. Through the A-star algorithm and the waiting time prediction model, the system can perceive waiting delay in advance and adjust a path in time, the waiting time of a patient is remarkably shortened, and the doctor-seeing experience is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent medical technology, and in particular to an integrated system of intelligent medical guidance and tracking return visit records for medical examinations. Background Art

[0002] With the continuous advancement of modern medical technology, hospital information management systems have been widely used, especially in nuclear medicine examinations and patient management. The introduction of intelligent technology has significantly improved the hospital's operational efficiency and patients' medical experience. The existing guidance system usually relies on the hospital's Internet of Things devices and information management system to plan the guidance path for patients by collecting basic information about patients, the use of radioactive drugs, and environmental data of the hospital. However, the limitation of the traditional guidance system is that it lacks the ability to make real-time dynamic adjustments and cannot optimize the path according to the patient's actual behavior data or the real-time status of the hospital. Especially in nuclear medicine examinations, patients, medical staff and the public may face the risk of radiation exposure, and path deviations or waiting delays will increase unnecessary radiation risks. In addition, after patients complete nuclear medicine examinations and treatments, they often rely on manual operations in health education, nursing measures, and follow-up management, which is inefficient and lacks personalized solutions, making it difficult to meet the diverse needs of patients.

[0003] However, the shortcomings of existing technologies in guiding and following up nuclear medicine examinations are mainly reflected in the following two aspects: First, most existing guidance systems are based on static path planning and cannot effectively respond to changes in the hospital environment, such as the metabolism time and decay of radioactive drugs, radiation doses in consulting rooms and wards, equipment utilization rates, and dynamic factors such as the number of waiting people. The actual safety and waiting experience of patients are difficult to guarantee. Secondly, after the patient completes the examination, the existing technology lacks automation and personalized processing in health management and follow-up mechanisms, and fails to make full use of patients' feedback data and examination results to optimize subsequent health management services. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an integrated intelligent medical guidance and tracking and return visit record system for medical examinations to solve the problems of lack of dynamic adjustment of the guidance path and insufficient automation of the tracking and return visit mechanism in the prior art.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In the first aspect, an embodiment of the present invention provides an integrated system of intelligent medical guidance and follow-up return visit records for medical examinations, which includes a data collection and preprocessing module: used to collect patient data and hospital environment data, preprocess the patient data and hospital environment data, and integrate them into a comprehensive data set; a guidance path identification module: used to identify the guidance path based on the comprehensive data set using the A-star algorithm; a patient behavior data collection module: used for the system to collect patient behavior data in real time while the patient is waiting for treatment according to the guidance path; a waiting time deviation value prediction module: used to train a waiting time difference prediction model based on historical data, input the patient behavior data into the waiting time difference prediction model, and predict the waiting time deviation value; a guidance path dynamic adjustment module: used to dynamically adjust the guidance path according to the waiting time deviation value; a health education and feedback collection module: used for the system to automatically provide health education content after the patient completes the treatment according to the adjusted guidance path, and collect patient feedback data and store it in the tracking return visit system.

[0008] As a preferred solution of the integrated system of intelligent medical guidance and follow-up visit records for medical examinations described in the present invention, the specific steps of collecting patient data and hospital environment data are as follows:

[0009] The hospital’s mobile app was used to collect the patient’s name, gender, age, medical history, scheduled examination items, appointment time, and radiopharmaceutical injection time and dose;

[0010] Collect hospital environment data in real time through the hospital's IoT devices and hospital information management system;

[0011] The environmental data include the location of the clinic, the number of patients waiting, the utilization rate of equipment, the number of patients received, and the radiation dose in the wards and rooms.

[0012] As a preferred solution of the integrated system of intelligent medical guidance and follow-up visit records for medical examinations described in the present invention, the patient data and hospital environment data are pre-processed and integrated into a comprehensive data set. The specific steps are as follows:

[0013] Fill missing data in patient and hospital environment data by filling in default values;

[0014] Identify and correct outliers in patient data and hospital environment data through rule detection;

[0015] Standardize patient data and hospital environment data through data type conversion;

[0016] Through data association, patient data and hospital environment data are integrated into a comprehensive data set.

[0017] As a preferred solution of the integrated system of intelligent medical guidance and follow-up visit records for medical examinations described in the present invention, the following specific steps are used to identify the guidance path based on the comprehensive data set using the A-star algorithm:

[0018] Through the graph model mapping function, the data in the comprehensive dataset is mapped to the node and path costs in the A-star algorithm;

[0019] The patient's current location is set as the starting node, and the target clinic is set as the target node. The A-star algorithm selects candidate nodes from the open list, calculates the cost function of the candidate nodes, and selects the node with the smallest cost as the next visited node to identify the optimal guidance path. The expression is:

[0020]

[0021] Among them, f9n) represents the total path cost from the starting node n to the target node, g(n c ) represents the path cost from the starting node to the current node, d(n c ,n e ) represents the current node n c Go to the next node n e The distance, v w represents the patient's walking speed, p w (n e ) represents the next node n e The number of patients waiting for treatment, p c (n e ) represents the next node n e The maximum number of patients received, p e (pt) indicates the urgency of the patient pt, t a (n e ) The next node’s available time for consultation, R r (n e ) represents node n e Radiation exposure risk, t m (n e ) represents node n e the associated radiopharmaceutical metabolism time;

[0022] By gradually calculating and comparing the total path cost f(n) of each candidate node, the node with the smallest total path cost is selected as the next visited node until the optimal path from the start node to the target node is found as the guide path;

[0023] The nodes represent the locations of consulting rooms and wards in the hospital;

[0024] The path cost represents the cost that a patient needs to pay to move from one node to another, including distance, time, and resource utilization.

[0025] As a preferred solution of the integrated system of intelligent medical guidance and follow-up visit records for medical examinations described in the present invention, the system collects patient behavior data in real time during the patient's waiting for consultation according to the guidance path. The specific steps are as follows:

[0026] While patients are waiting for their appointments according to the guidance path, the system collects patient behavior data in real time through IoT devices in the hospital and the patient's mobile devices;

[0027] The patient behavior data includes the patient's walking speed, moving distance, waiting time and path deviation.

[0028] As a preferred solution of the integrated system of intelligent medical guidance and follow-up visit records for medical examinations described in the present invention, wherein: based on historical data, a waiting time difference prediction model is trained, and the specific steps are as follows:

[0029] GNN is used as the basic model and trained based on historical data. The static and dynamic feature vectors of each node are extracted through the graph convolution layer. A high-dimensional feature representation is generated based on the connection relationship between nodes to capture the complex interaction relationship between nodes. Finally, GNN is trained into a waiting time difference prediction model that can predict the waiting time deviation value.

[0030] The static feature vector includes the type, location, historical average waiting time and historical radiation monitoring data of the clinic;

[0031] The dynamic feature vector includes the number of patients waiting in the clinic, the doctor's reception status, the equipment utilization rate, and the metabolism time and decay of the radioactive drug.

[0032] As a preferred solution of the integrated system of intelligent medical guidance and follow-up record for medical examinations described in the present invention, the steps of inputting patient behavior data into the waiting time difference prediction model to predict the waiting time deviation value are as follows:

[0033] The patient behavior data is input into the guidance path optimization model, and combined with the estimated waiting time of the patient in each clinic, the waiting time deviation value is predicted, and the expression is:

[0034]

[0035] Among them, ΔT represents the waiting time deviation value, D i,i+1 represents the walking distance of the patient from clinic i to clinic i+1, v w represents the patient's walking speed, W irepresents the waiting time of patients in clinic i, δ i,i+1 represents the path deviation of the patient from clinic i to clinic i+1, T i represents the estimated waiting time of clinic i, α is the path deviation δ i,i+1 , β is the nonlinear coefficient for controlling deviation, and N represents the total number of consulting rooms visited by the patient during the consultation process.

[0036] As a preferred solution of the integrated system of intelligent medical guidance and follow-up record for medical examinations described in the present invention, the specific steps of dynamically adjusting the guidance path according to the waiting time deviation value are as follows:

[0037] Based on the actual operation data and service standards of the hospital, a waiting tolerance threshold X is defined;

[0038] When ΔT≤X, the current guidance path is considered reasonable and the patient can continue to receive treatment according to the guidance path;

[0039] When ΔT>X, it is considered that the current guidance path is unreasonable and there is a large time deviation;

[0040] The system recalculates the total path cost based on the waiting time deviation value ΔT and the real-time status of each clinic, and dynamically adjusts the guidance path according to the recalculated total path cost;

[0041] The system sends the adjusted guidance route to the patient and guides the patient to wait for consultation according to the new route.

[0042] As a preferred solution of the integrated system of intelligent medical guidance and follow-up return visit records for medical examinations described in the present invention, after the patient completes the medical consultation according to the adjusted guidance path, the system automatically provides health education content and collects patient feedback data and stores it in the follow-up return visit system. The specific steps are as follows:

[0043] After the patient completes the consultation according to the adjusted consultation path, the system automatically records the patient's consultation results;

[0044] Based on the patient's medical results and hospitalization requirements, the system automatically generates personalized health education content and sends it to the patient via a mobile application;

[0045] After the patient finishes reading the monitoring education content, the system pushes a health check-in form every day to collect patient feedback data, and stores the patient feedback data in the tracking and return visit system;

[0046] The tracking and return visit system generates a personalized return visit plan based on the patient's feedback data and arranges subsequent follow-up, reexamination and health management services.

[0047] The beneficial effects of the present invention are: through intelligent data collection and preprocessing, A-star algorithm-based guidance path planning, real-time patient behavior data collection and waiting time deviation prediction, combined with dynamic adjustment of the guidance path, it is possible to provide patients with the best guidance path in a complex medical environment. Through the waiting time prediction model, the system can perceive waiting delays in advance and adjust the path in time, significantly shortening the patient's waiting time and improving the medical experience, while also reducing the impact of radiation on the environment in the supervision area and public places. In addition, the present invention automatically provides health education and collects patient feedback before and after the diagnosis, forming a complete follow-up and health management closed loop, which enhances the intelligence and personalization of medical services. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0049] Figure 1 This is a flow chart of the integrated system for intelligent medical guidance and follow-up record keeping for medical examinations in Example 1.

[0050] Figure 2 This is a flow chart of dynamically adjusting the guidance path according to the waiting time deviation value in Example 1. DETAILED DESCRIPTION

[0051] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0052] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0053] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0054] Example 1, reference Figure 1 and Figure 2, which is the first embodiment of the present invention, and provides an integrated system for intelligent medical guidance and follow-up visit records for medical examinations, including the following steps:

[0055] Data collection and preprocessing module: used to collect patient data and hospital environment data, preprocess the patient data and hospital environment data, and integrate them into a comprehensive data set.

[0056] Furthermore, the hospital’s mobile app collects the patient’s name, gender, age, medical history, scheduled examination items, appointment time, radiopharmaceutical injection time and dosage, patient needs, and follow-up of treatment effects;

[0057] It should be noted that the above information is obtained with the user's consent and is used for legitimate purposes.

[0058] Hospital environmental data is collected in real time through the hospital's Internet of Things devices and hospital information management system.

[0059] Environmental data included the location of the clinic, the number of patients waiting, the utilization rate of equipment, the number of patients admitted, and the radiation dose in the wards and rooms.

[0060] Fill missing data in patient and hospital environment data with default values.

[0061] For example, if the patient's age is missing, the system can default to 40 years old.

[0062] Identify and correct outliers in patient data and hospital environment data through rule detection.

[0063] For example, if a patient's age is recorded as 150 years old, the system will identify it as an anomaly and correct it to a reasonable value.

[0064] Patient data (such as age, gender, and medical history) and hospital environment data (such as waiting number and equipment utilization rate) were standardized through data type conversion.

[0065] For example, the system uniformly converts the equipment utilization rate of "70%" into a numerical format of 0.70.

[0066] Through data association, patient data and hospital environment data are integrated into a comprehensive data set.

[0067] It should also be noted that the data collection and preprocessing module ensures the accuracy and consistency of the data by cleaning, standardizing and integrating patient and hospital environment data, providing reliable data support for subsequent guidance route planning, and ultimately improving the decision-making efficiency and accuracy of the system.

[0068] Medical guidance path identification module: used to identify medical guidance paths based on comprehensive data sets using the A-star algorithm.

[0069] Furthermore, through the graph model mapping function, the data in the comprehensive dataset is mapped to the node and path costs in the A-star algorithm.

[0070] In nuclear medicine examinations, patients may be exposed to different degrees of radiation at different locations or nodes (such as consulting rooms, examination rooms, wards, etc.). Some patients are mobile radiation sources and there is mutual radiation; a small number of normal patients may also be at risk of radiation. In order to reduce the time that radiation patients stay in public areas and reduce the impact of nuclear radiation on the environment, we introduce R r (n e ) to represent node n e The radiation exposure risk is expressed as:

[0071]

[0072] Among them, D bg (n e ) represents node n e Background radiation dose, D med (n e ) indicates that the patient is at node n e Medical radiation dose caused by radioactive drugs (related to the type and dose of drugs), T p (n e ) indicates that the patient is at node n e The residence time, T d (n e ) represents the half-life of the radiopharmaceutical (the radioactivity of the drug decreases gradually over time);

[0073] The patient's current location is set as the starting node, and the target clinic is set as the target node. The A-star algorithm selects candidate nodes from the open list, calculates the cost function of the candidate nodes, and selects the node with the smallest cost as the next visited node to identify the optimal guidance path. The expression is:

[0074]

[0075] Among them, f(n) represents the total path cost from the starting node n to the target node, g(n c ) represents the path cost from the starting node to the current node, d(n c ,n e ) represents the current node n c Go to the next node n e The distance, v w represents the patient's walking speed, p w (n e ) represents the next node n e The number of patients waiting for treatment, pc (n e ) represents the next node n e The maximum number of patients received, p e (pt) indicates the urgency of the patient pt, t a (n e ) The next node’s available time for consultation, R r (n e ) represents node n e Radiation exposure risk, t m (n e ) represents node n e Related radiopharmaceutical metabolism time.

[0076] It should be noted that the open list is a collection of nodes to be processed in the A-star algorithm. These nodes are candidate nodes of paths that have been discovered but not yet fully processed. For example, when a patient goes from Clinic A to Clinic B, the open list may contain various intermediate nodes in multiple candidate paths from Clinic A to Clinic B, and the system will select the node with the lowest cost for the next visit.

[0077] By gradually calculating and comparing the total path cost f(n) of each candidate node, the node with the smallest total path cost is selected as the next visited node until the optimal path from the start node to the target node is found as the guidance path.

[0078] It should be noted that the A-star algorithm gradually calculates the total path cost function f(n) of each candidate node, which comprehensively considers the path cost from the starting node to the current node and the estimated cost from the current node to the target node. The algorithm selects the node with the lowest cost from the open list and uses it as the node to be visited next, then continues to expand the neighboring nodes of the node and repeats this process. In this way, by continuously comparing and updating the path cost, the algorithm eventually finds a path with the lowest total cost from the starting node to the target node as the guide path.

[0079] The nodes represent the locations of consulting rooms and wards in the hospital.

[0080] The path cost represents the cost that a patient needs to pay to move from one node to another, including distance, time, resource utilization, and the impact of nuclear radiation on the environment.

[0081] It should also be noted that the guidance path identification module maps the patient data and hospital environment data in the comprehensive data set to the nodes and path costs in the A-star algorithm. This module integrates multi-dimensional factors, including the patient's walking speed, the number of waiting patients, the reception capacity, the degree of urgency, and the radiation exposure risk unique to nuclear medicine examinations and the metabolism time and decay of radioactive drugs. The system can dynamically identify the optimal guidance path to ensure that patients can safely reach the target clinic in the shortest time and with the least resource consumption. Especially in nuclear medicine examinations, the planning of the guidance path not only considers conventional factors (such as distance, time, number of waiting patients, etc.), but also indirectly realizes radiation space and shielding protection by calculating the radiation exposure risk of each candidate node, combined with the metabolism and decay time of radioactive drugs, and minimizes the exposure of patients and staff to high radiation environments. This process not only improves the guidance efficiency and reduces the waiting time of patients, but also effectively optimizes the operation of the hospital through the reasonable allocation of resources and alleviates the congestion of departments. At the same time, the system's real-time dynamic adjustment capability can improve the patient's medical experience while ensuring their safety. Especially for nuclear medicine patients, it can significantly reduce unnecessary radiation exposure and waiting time, thereby effectively protecting the radiation safety of medical staff and patients.

[0082] Patient behavior data collection module: It is used to collect patient behavior data in real time while patients are waiting for consultation according to the guidance path.

[0083] Furthermore, while patients are waiting for their appointments according to the guidance route, the system collects patient behavior data in real time through IoT devices in the hospital (such as Bluetooth beacons, Wi-Fi devices, RFID readers, etc.) and the patients' mobile devices, ensuring that the system can dynamically track and monitor the patients' actual status, thereby providing accurate input for subsequent route optimization and waiting time prediction.

[0084] Patient behavior data include patients' walking speed, moving distance, waiting time, and path deviation.

[0085] It should also be noted that the patient behavior data collection module collects the patient's behavior data in real time. The system can make fast and intelligent path adjustments and responses based on the patient's actual situation, reduce the patient's waiting time, improve medical efficiency, and effectively prevent the patient from getting lost or deviating from the path in the hospital.

[0086] Waiting time deviation value prediction module: used to train a waiting time difference prediction model based on historical data, input patient behavior data into the waiting time difference prediction model, and predict the waiting time deviation value.

[0087] Furthermore, GNN is used as the basic model and trained based on historical data. The static feature vector and dynamic feature vector of each node are extracted through the graph convolution layer, and a high-dimensional feature representation is generated according to the connection relationship between the nodes to capture the complex interaction relationship between the nodes. Finally, GNN is trained into a waiting time difference prediction model that can predict the waiting time deviation value.

[0088] It should be noted that the reason for using graph neural network (GNN) as the basic model is that GNN can effectively process and model graph structure data, and information such as patient flow, clinic relationship, and equipment use involved in the hospital environment is naturally suitable for representation by graph structure. GNN can capture the dynamic interactions and associations between clinics by learning the complex relationships between nodes (such as clinics) and paths. It is particularly suitable for processing multi-dimensional dynamic information such as the number of waiting patients and the status of doctors’ reception, thereby providing more accurate waiting time prediction and path optimization. Therefore, GNN can make full use of the graph data in the hospital environment to improve the prediction accuracy of the model and the overall intelligence level of the system.

[0089] The static feature vector includes the type, location, historical average waiting time and historical radiation monitoring data of the clinic.

[0090] The dynamic feature vectors include the number of patients waiting in the clinic, the doctor's admission status, the equipment utilization rate, the metabolism time and decay of radioactive drugs, and the radiation dose of the wards and rooms.

[0091] The patient behavior data is input into the guidance path optimization model, and combined with the estimated waiting time of the patient in each clinic, the waiting time deviation value is predicted, and the expression is:

[0092]

[0093] Among them, ΔT represents the waiting time deviation value, D i,i+1 represents the walking distance of the patient from clinic i to clinic i+1, v w represents the patient's walking speed, W i represents the waiting time of patients in clinic i, δ i,i+1 represents the path deviation of the patient from clinic i to clinic i+1, T i represents the estimated waiting time of clinic i, α is the path deviation δ i,i+1 , β is the nonlinear coefficient for controlling deviation, and N represents the total number of consulting rooms visited by the patient during the consultation process.

[0094] It should be noted that the estimated waiting time T iIt is dynamically generated based on the clinic's historical waiting data and real-time status. The system combines historical average waiting time, current number of patients waiting, doctor's reception status, equipment availability and other information for calculation, and adjusts according to the patient's personalized factors (such as urgency, appointment time, etc.), so as to obtain a more accurate estimate of waiting time. This process ensures that the system can update the waiting time in real time in a dynamic environment, providing an accurate basis for subsequent route optimization and waiting time deviation prediction.

[0095] It should also be noted that the waiting time deviation value prediction module collects and analyzes patient behavior data in real time, and combines historical and dynamic environmental information. The system can more accurately predict the waiting time deviation, adjust the patient's guidance path in time, reduce unnecessary waiting and movement, and improve the efficiency of medical treatment. At the same time, the use of the waiting time difference prediction model can effectively capture the complex interactive relationship between consulting rooms in the hospital, further improve the accuracy of the prediction and the intelligence level of the system, and help optimize the utilization of hospital resources and improve the overall medical experience of patients.

[0096] Dynamic adjustment module of the guidance path: used to dynamically adjust the guidance path according to the waiting time deviation value.

[0097] Furthermore, based on the actual operation data and service standards of the hospital, a waiting tolerance threshold X is defined.

[0098] When ΔT≤X, the current guidance path is considered reasonable and the patient can continue to receive treatment according to the guidance path.

[0099] When ΔT>X, it is considered that the current guidance path is unreasonable and there is a large time deviation.

[0100] It should be noted that the waiting tolerance threshold X is a time limit defined based on the actual operating data of the hospital (such as historical waiting time, clinic load, etc.) and service standards (such as the maximum acceptable waiting time, patient satisfaction index, etc.), indicating the maximum waiting time range acceptable to patients under normal circumstances.

[0101] The system recalculates the total path cost based on the waiting time deviation value ΔT and the real-time status of the clinic, and dynamically adjusts the guidance path according to the recalculated total path cost.

[0102] It should be noted that the system recalculates the total path cost f(n) of each candidate path through the A-star algorithm, i.e., the total cost from the current node to the target clinic, based on the waiting time deviation value ΔT and the real-time status of each clinic (such as the number of patients waiting, the doctor's reception status, the equipment utilization rate, etc.). According to the latest path cost, the system dynamically adjusts the guidance path, giving priority to the path with the lowest cost and the greatest reduction in patient waiting time.

[0103] The system sends the adjusted guidance route to the patient and guides the patient to wait for consultation according to the new route.

[0104] It should also be noted that the guidance path dynamic adjustment module monitors the waiting time deviation and the status of the clinic in real time, and the system can dynamically adjust the guidance path to ensure that patients always wait along the optimal path when the hospital environment and patient status are constantly changing. This not only effectively reduces the patient's waiting time and unnecessary movement, improves the efficiency of medical treatment, but also avoids congestion caused by overloaded clinics or uneven resource allocation, ultimately improving the patient's overall medical experience and improving the hospital's operational efficiency and resource utilization.

[0105] Health education and feedback collection module: After the patient completes the medical consultation according to the adjusted guidance path, the system automatically provides health education content and collects patient feedback data and stores it in the tracking and follow-up system.

[0106] Furthermore, after the patient completes the consultation according to the adjusted guidance pathway, the system automatically records the patient's consultation results; the consultation results include radioactive drug treatment plans, radioactive drug usage information, prescription drugs, and follow-up imaging review arrangements.

[0107] Based on the patient's medical results and hospitalization requirements, the system automatically generates personalized health education content and sends it to the patient via a mobile application; for example, for patients undergoing nuclear medicine examinations and treatments, the system will send information about precautions and follow-up measures before and after the examination and treatment, content that requires timely adjustment, precautions for drug use, and the potential effects of radioactive drugs.

[0108] It should be noted that the content of health education includes whether radioactive drugs are used, whether radiation-related adverse reactions occur, how to deal with adverse reactions, the impact of radioactive drugs on diet and life before and after treatment, and related precautions.

[0109] After the patient finishes reading the monitoring education content, the system pushes a health check-in form every day to collect patient feedback data, and stores the patient feedback data in the tracking and follow-up system.

[0110] It should be noted that patient feedback data includes daily bowel movement frequency, body temperature, related symptoms that occur during the metabolism and decay of radioactive drugs (usually nervous system and digestive system reactions such as fatigue, dizziness, fatigue, nausea, bloating and other discomfort symptoms), medication status, diet records, and whether other abnormal symptoms occur. These data will help the system continuously monitor the patient's health status, especially the metabolism of radioactive drugs, and provide real-time tracking basis for doctors or medical teams to intervene or adjust treatment plans in a timely manner.

[0111] The tracking and return visit system generates a personalized return visit plan based on the patient's feedback data, and arranges subsequent follow-up, reexamination and health management services. For example, if the patient reports that the body temperature is still high and the symptoms have not been relieved after taking the medicine, the system will arrange a doctor to follow up in advance or recommend the patient to reexamine as soon as possible; if the patient reports that all indicators are normal and there are no discomfort symptoms, the system may arrange a regular health return visit or remind the patient to reexamine regularly, and provide personalized health management suggestions, such as continuing to maintain the current diet and exercise habits.

[0112] It should also be noted that the waiting time deviation value prediction module can more accurately predict the waiting time deviation value by collecting and analyzing patient behavior data in real time, and combining historical data with dynamic environmental information (such as the number of waiting patients in the clinic, the doctor's reception status, equipment utilization rate, radiation dose in wards and rooms, etc.). Based on the waiting time difference prediction model, the system uses graph neural network (GNN) to effectively capture the complex interaction relationship between clinics in the hospital, and generates high-dimensional feature representation by integrating static features with dynamic features to further improve the prediction accuracy. While predicting the waiting time deviation, it can timely adjust the guidance path according to the patient's real-time status and the dynamic situation of the clinic, reduce unnecessary waiting and movement of patients in the hospital, and optimize the medical process. In addition, the waiting time difference prediction model comprehensively considers the specific needs of nuclear medicine examinations by processing multi-dimensional factors such as walking distance, path deviation, waiting time and radiation exposure risk. This not only improves the efficiency of medical treatment, but also effectively optimizes the utilization of resources within the hospital, reduces department congestion, and improves the patient's overall medical experience, especially in complex nuclear medicine examination scenarios, helping patients complete the examination process more safely and efficiently.

[0113] In summary, the present invention provides patients with the best guidance path in a complex medical environment through: intelligent data collection and preprocessing, guidance path planning based on the A-star algorithm, real-time patient behavior data collection, and waiting time deviation prediction, combined with dynamic adjustment of the guidance path. Through the waiting time prediction model, the system can perceive waiting delays in advance and adjust the path in time, significantly shortening the patient's waiting time and improving the medical experience. In addition, the present invention automatically provides health education and collects patient feedback before and after diagnosis and treatment, forming a complete follow-up and health management closed loop, which enhances the intelligence and personalization of medical services.

[0114] Example 2, referring to Table 1, is the second example of the present invention. To further verify the technical solution of the present invention, experimental simulation data of an integrated system of intelligent guidance and follow-up visit records for medical examinations are provided.

[0115] The experiment simulated a medical scenario involving the diagnosis and treatment of multiple patients. The prior art used a traditional path planning algorithm, while the present invention used an innovative guidance path planning algorithm. The effect of the present invention was demonstrated by comparing the performance of the two technologies in optimizing patient waiting time and resource utilization.

[0116] First, the patient's basic information and hospital environment data are collected and preprocessed to generate a comprehensive data set as the basis for guidance route planning.

[0117] Secondly, the A-star algorithm is used to identify the optimal guidance path based on a comprehensive data set, taking into account factors such as patient location, walking speed, number of waiting people, and equipment utilization rate to ensure the efficiency and accuracy of path planning.

[0118] Next, while the patient is waiting for treatment according to the guidance path, the system collects the patient's behavioral data in real time and dynamically predicts the waiting time deviation value based on the waiting time difference prediction model trained with historical data to determine whether the current path needs to be adjusted.

[0119] Finally, based on the predicted waiting time deviation value, the system optimizes the guidance path in real time through the guidance path dynamic adjustment module, and after the patient completes the consultation, provides personalized health education content through the health education and feedback collection module, collects the patient's feedback data, and stores it in the tracking and return visit system.

[0120] The details are shown in Table 1 below:

[0121] Table 1 Comparison of functions of intelligent medical guidance system

[0122]

[0123]

[0124] Through the data analysis of the above table, it can be seen that the present invention has significant advantages in the guidance path planning, especially in reducing waiting time and improving resource utilization. For example, the waiting time of patient 1 was reduced from 45 minutes in the prior art to 30 minutes, a reduction of 33%; the waiting time of patient 2 was reduced from 30 minutes to 15 minutes, a reduction of 50%; and the waiting time of patient 3 was also reduced from 60 minutes to 45 minutes, a reduction of 25%. In addition, the present invention significantly improves resource utilization by dynamically adjusting the guidance path, further improving the overall operational efficiency of the hospital.

[0125] The integrated system of intelligent medical guidance and follow-up records for medical examinations of the present invention can not only significantly reduce the waiting time of patients, but also dynamically adjust the guidance path to improve the utilization efficiency of hospital resources, especially when there are a large number of waiting people or hospital resources are tight. This shows that the present invention optimizes the guidance process through the combination of intelligent algorithms and real-time data, improves the overall operational efficiency of the hospital and the patient's medical experience. It can also minimize the impact of ionizing radiation on the hospital environment, further ensuring the radiation safety of patients and staff.

[0126] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An integrated system for intelligent medical consultation and follow-up visit records, characterized by: include, Data collection and preprocessing module: used to collect patient data and hospital environment data, preprocess the patient data and hospital environment data, and integrate them into a comprehensive data set; Patient guidance path identification module: used to identify the patient guidance path based on the comprehensive data set using the A-star algorithm; Patient behavior data collection module: used for real-time collection of patient behavior data while patients are waiting for consultation according to the guidance path; Waiting time deviation value prediction module: used to train a waiting time difference prediction model based on historical data, input patient behavior data into the waiting time difference prediction model, and predict the waiting time deviation value; Dynamic adjustment module for the guidance path: used to dynamically adjust the guidance path according to the waiting time deviation value; Health education and feedback collection module: After the patient completes the medical consultation according to the adjusted guidance path, the system automatically provides health education content and collects patient feedback data and stores it in the tracking and follow-up system.

2. The integrated intelligent medical guidance and follow-up record system for medical examinations as claimed in claim 1, characterized in that: The specific steps of collecting patient data and hospital environment data are as follows: The hospital’s mobile app was used to collect the patient’s name, gender, age, medical history, scheduled examination items, appointment time, and radiopharmaceutical injection time and dose; Collect hospital environment data in real time through the hospital's IoT devices and hospital information management system; The environmental data include the location of the clinic, the number of patients waiting, the utilization rate of equipment, the number of patients received, and the radiation dose in the wards and rooms.

3. The integrated system for intelligent medical guidance and follow-up visit records for medical examinations as claimed in claim 2, characterized in that: The patient data and hospital environment data are preprocessed and integrated into a comprehensive data set. The specific steps are as follows: Fill missing data in patient and hospital environment data by filling in default values; Identify and correct outliers in patient data and hospital environment data through rule detection; Standardize patient data and hospital environment data through data type conversion; Through data association, patient data and hospital environment data are integrated into a comprehensive data set.

4. The integrated system for intelligent medical guidance and follow-up visit records for medical examinations as claimed in claim 3, characterized in that: Based on the comprehensive data set, the A-star algorithm is used to identify the guidance path. The specific steps are as follows: Through the graph model mapping function, the data in the comprehensive dataset is mapped to the node and path costs in the A-star algorithm; The patient's current location is set as the starting node, and the target clinic is set as the target node. The A-star algorithm selects candidate nodes from the open list, calculates the cost function of the candidate nodes, and selects the node with the smallest cost as the next visited node to identify the optimal guidance path. The expression is: Among them, f(n) represents the total path cost from the starting node n to the target node, g(n c ) represents the path cost from the starting node to the current node, d(n c , n e ) represents the current node n c Go to the next node n e The distance, v w represents the patient's walking speed, P w (n e ) represents the next node n e The number of patients waiting for treatment, pc(n e ) represents the next node n e The maximum number of patients admitted, p e (pt) indicates the urgency of the patient pt, t a (n e ) The next node’s available time for consultation, R r (n e ) represents node n e Radiation exposure risk, t m (n e ) represents node n e the associated radiopharmaceutical metabolism time; By gradually calculating and comparing the total path cost f(n) of each candidate node, the node with the smallest total path cost is selected as the next visited node until the optimal path from the starting node to the target node is found as the guidance path; The nodes represent the locations of consulting rooms and wards in the hospital; The path cost represents the cost that a patient needs to pay to move from one node to another, including distance, time, and resource utilization.

5. The integrated system for intelligent medical guidance and follow-up visit records for medical examination as claimed in claim 4, characterized in that: During the patient's waiting time according to the guidance path, the system collects patient behavior data in real time. The specific steps are as follows: While patients are waiting for their appointments according to the guidance path, the system collects patient behavior data in real time through IoT devices in the hospital and the patient's mobile devices; The patient behavior data includes the patient's walking speed, moving distance, waiting time and path deviation.

6. The integrated system for intelligent medical guidance and follow-up visit records for medical examinations as claimed in claim 5, characterized in that: Based on the historical data, a waiting time difference prediction model is trained, and the specific steps are as follows: GNN is used as the basic model and trained based on historical data. The static and dynamic feature vectors of each node are extracted through the graph convolution layer. A high-dimensional feature representation is generated based on the connection relationship between nodes to capture the complex interaction relationship between nodes. Finally, GNN is trained into a waiting time difference prediction model that can predict the waiting time deviation value. The static feature vector includes the type, location, historical average waiting time and historical radiation monitoring data of the clinic; The dynamic feature vector includes the number of patients waiting in the clinic, the doctor's reception status, the equipment utilization rate, and the metabolism time and decay of the radioactive drug.

7. The integrated system for intelligent medical guidance and follow-up visit records for medical examinations as claimed in claim 6, characterized in that: The patient behavior data is input into the waiting time difference prediction model to predict the waiting time deviation value. The specific steps are as follows: The patient behavior data is input into the guidance path optimization model, and combined with the estimated waiting time of the patient in each clinic, the waiting time deviation value is predicted, and the expression is: Among them, ΔT represents the waiting time deviation value, D i,i+1 represents the walking distance of the patient from clinic i to clinic i+1, v w represents the patient's walking speed, W i represents the waiting time of patients in clinic i, δ i,i+1 represents the path deviation of the patient from clinic i to clinic i+1, T i represents the estimated waiting time of clinic i, α is the path deviation δ i,i+1 , β is the nonlinear coefficient for controlling deviation, and N represents the total number of consulting rooms visited by the patient during the consultation process.

8. The integrated system for intelligent medical guidance and follow-up visit records for medical examinations as claimed in claim 7, characterized in that: The specific steps of dynamically adjusting the guidance path according to the waiting time deviation value are as follows: Based on the actual operation data and service standards of the hospital, a waiting tolerance threshold X is defined; When ΔT≤X, the current guidance path is considered reasonable and the patient can continue to receive treatment according to the guidance path; When ΔT>X, it is considered that the current guidance path is unreasonable and there is a large time deviation; The system recalculates the total path cost based on the waiting time deviation value ΔT and the real-time status of each clinic, and dynamically adjusts the guidance path according to the recalculated total path cost; The system sends the adjusted guidance route to the patient and guides the patient to wait for consultation according to the new route.

9. The integrated system for intelligent medical guidance and follow-up visit records for medical examinations as claimed in claim 8, characterized in that: After the patient completes the consultation according to the adjusted guidance path, the system automatically provides health education content and collects patient feedback data and stores it in the tracking and return visit system. The specific steps are as follows: After the patient completes the consultation according to the adjusted consultation path, the system automatically records the patient's consultation results; Based on the patient's medical results and hospitalization requirements, the system automatically generates personalized health education content and sends it to the patient via a mobile application; After the patient finishes reading the monitoring education content, the system pushes a health check-in form every day to collect patient feedback data, and stores the patient feedback data in the tracking and return visit system; The tracking and return visit system generates a personalized return visit plan based on the patient's feedback data and arranges subsequent follow-up, reexamination and health management services.

Images