A system for collecting, analyzing, supervising and managing medical behaviors in emergency and outpatient departments

Abstract

This invention relates to the field of smart healthcare technology, specifically to a medical behavior collection, analysis, and monitoring system that integrates multi-source data from outpatient and emergency departments. The key technical features of this system include: intelligent triage and condition assessment modules; intelligent interaction and communication assistance modules; personalized treatment pathway modules; intelligent quality control and compliance early warning modules; intelligent medical order recommendation and management modules; patient empowerment and self-management modules; and end-to-end collaborative and closed-loop management modules. This system collects and integrates multi-source data from patients, including text, voice, images, and video, to achieve quantitative assessment and grading of their condition. It also performs intelligent triage and dynamic scheduling based on the status of medical resources. Simultaneously, it provides functions such as medical record generation, pathway optimization, behavior monitoring, and risk warning during the treatment process, and assists in decision-making through drug compatibility analysis and treatment plan recommendations.

Description

Technical Field

[0001] This invention relates to the field of smart healthcare technology, and more specifically, to a system for collecting, analyzing, monitoring, and managing outpatient and emergency medical behavior. Background Technology

[0002] With the continuous advancement of medical informatization and the construction of smart hospitals, outpatient and emergency departments, as crucial entry points for hospital medical services, directly impact the efficiency and accuracy of medical resource allocation and patient experience. In the traditional medical model, outpatient and emergency department triage primarily relies on manual consultation and experience-based judgment, typically with triage nurses making initial decisions based on patient complaints, physical signs, and simple examination results. However, this method is highly subjective and easily influenced by factors such as differences in the experience of medical staff, workload, and patients' expressive abilities, leading to inaccurate triage and biased priority judgments.

[0003] While some medical institutions have introduced information-based triage systems to achieve basic registration, patient flow management, and queue control, most systems remain at the stage of single-information input and rule matching, lacking the ability to comprehensively analyze patients' multimodal symptom information. For example, existing systems typically rely solely on text or simple structured data, making it difficult to effectively utilize multi-source information such as voice, images, and video, resulting in an incomplete portrayal of the patient's condition. Furthermore, existing triage systems often employ fixed rules or simple scoring mechanisms in the disease assessment process, lacking in-depth analysis of individual patient differences, making it difficult to achieve accurate triage and dynamic adjustments.

[0004] Furthermore, existing outpatient and emergency systems generally suffer from lag in resource scheduling and triage decisions, failing to dynamically optimize based on departmental load, doctor availability, and queuing status in real time. This can easily lead to congestion in some departments while other resources remain idle. In terms of inter-departmental or inter-institutional referrals, current technology also lacks a unified coordination mechanism, often requiring patients to repeatedly register and wait, increasing the time and cost of medical care.

[0005] During the diagnosis and treatment process, existing technologies have weak monitoring and supervision capabilities for medical practices, lacking real-time analysis and early warning mechanisms for the rationality of treatment pathways, medication safety, and compliance of behaviors. Furthermore, individualized treatment plan recommendations, health management guidance, and participatory decision support for each patient are also insufficient, making it difficult to meet the current needs for precision medicine and patient-centered services.

[0006] In addition, existing systems generally lack the ability to manage the entire process in a closed loop. Data from before, during and after diagnosis are often fragmented and cannot form an effective feedback and optimization mechanism, making it difficult for the system to continuously learn and improve the triage and treatment effects.

[0007] Therefore, there is an urgent need to design a medical behavior collection, analysis, and monitoring system that integrates multi-source data from outpatient and emergency departments to solve these problems. Summary of the Invention

[0008] The purpose of this invention is to solve the technical problems mentioned in the background section and to provide a medical behavior collection, analysis and monitoring system that integrates multi-source data from outpatient and emergency departments.

[0009] The objective of this invention is achieved through the following technical solution: A medical behavior collection, analysis, and monitoring system that integrates multi-source data from outpatient and emergency departments, comprising: The system includes modules for intelligent triage and disease assessment, intelligent interaction and communication assistance, personalized treatment pathways, intelligent quality control and compliance early warning, intelligent medical order recommendation and management, patient empowerment and self-management, and full-process collaboration and closed-loop management. The intelligent triage and disease assessment module is used to collect patients' multimodal symptom information, calculate the severity of their condition, generate triage levels, and output triage results. The intelligent interaction and communication assistance module is used to guide patients to supplement symptom information, analyze emotional state, and generate structured medical record data. The personalized treatment pathway module is used to generate treatment pathways based on the patient's condition and disease knowledge, and to provide waiting guidance and follow-up visit management. The intelligent quality control and compliance early warning module is used to monitor medical treatment behavior and perform compliance detection and early warning based on rules; The intelligent recommendation and management module for medical orders is used to intelligently recommend and optimize medication and treatment plans; The patient empowerment and self-management module is used to realize patient health data management, symptom self-assessment, and participatory diagnosis and treatment decision-making. The full-process collaboration and closed-loop management module is used to realize cross-departmental collaboration, efficacy tracking, and closed-loop optimization of diagnosis and treatment feedback.

[0010] Furthermore, the intelligent triage and disease assessment module includes: a multimodal symptom acquisition unit, a disease severity index calculation unit, an intelligent triage and appointment optimization unit, and an intelligent hierarchical referral channel; wherein the multimodal symptom acquisition unit is used to collect the patient's text, voice, image, and video information; The severity index calculation unit is used to calculate the severity of the illness based on the symptom information and the patient's basic information; the intelligent triage and appointment optimization unit is used to match the department to be treated according to the severity of the illness and optimize the queuing order; the intelligent hierarchical referral channel is used to realize intra-hospital referral and inter-hospital referral.

[0011] Furthermore, the intelligent interaction and communication assistance module includes: The unit includes a doctor-patient intelligent dialogue engine, a voice emotion analysis unit, and an intelligent medical record writing and error correction unit. The doctor-patient intelligent dialogue engine unit is used to guide patients to supplement symptom information; The voice emotion analysis unit is used to identify the patient's emotional state; The intelligent medical record writing and error correction unit is used to generate structured medical records and perform information verification.

[0012] Furthermore, the personalized treatment pathway module includes: Disease atlas guidance unit, intelligent waiting room guidance unit, and treatment cycle and follow-up visit reminder unit; The disease atlas guidance unit is used to generate treatment pathways based on disease knowledge. The intelligent waiting guidance unit is used to optimize the waiting order based on the status of medical resources; The treatment cycle and follow-up reminder unit is used to generate follow-up plans and reminders.

[0013] Furthermore, the intelligent quality control and compliance early warning module includes: Medical behavior monitoring unit and medical insurance rule engine unit; The medical behavior monitoring unit is used to identify abnormal medical behaviors; The medical insurance rule engine unit is used to detect whether the treatment plan complies with medical insurance rules and output early warning information.

[0014] Furthermore, the intelligent recommendation and management module for medical orders includes: The unit includes a drug suitability analysis unit, a treatment plan cost-benefit analysis unit, and a science popularization content delivery unit. The drug suitability analysis unit is used to match appropriate drugs based on patient characteristics; The cost-benefit analysis unit for treatment plans is used to compare the effectiveness and cost of different treatment plans. The science popularization content push unit is used to push relevant health information to patients.

[0015] Furthermore, the patient empowerment and self-management module includes: The system includes a personal health record visualization unit, a symptom self-assessment and health scoring unit, a doctor-patient shared decision support unit, and a treatment effect feedback and learning unit. The personal health record visualization unit is used to display changes in the patient's health data; The symptom self-assessment and health scoring unit is used to support patients in assessing their symptoms. The shared decision support unit for doctors and patients is used to support patients' participation in diagnosis and treatment decisions; The treatment effect feedback learning unit is used to optimize the model based on the treatment results.

[0016] Furthermore, the full-process collaboration and closed-loop management module includes: a cross-departmental collaboration unit, a treatment effect tracking unit, and an inpatient unit; The interdisciplinary collaboration unit is used to achieve multi-disciplinary collaborative diagnosis and treatment; The treatment effect tracking unit is used to continuously monitor the patient's treatment effect; The inpatient unit is used to connect outpatient and inpatient processes.

[0017] Furthermore, the system performs dynamic triage and pathway optimization based on patient symptom data, basic patient information, and the status of medical resources.

[0018] Furthermore, the system continuously optimizes the triage model, treatment path, and recommendation strategy based on the feedback of diagnosis and treatment results, thereby forming a closed-loop self-learning mechanism.

[0019] Compared with the prior art, the present invention has the following beneficial effects: 1. The outpatient and emergency multi-source data fusion medical behavior collection, analysis and monitoring system proposed in this invention achieves comprehensive acquisition and accurate expression of patient symptom information by constructing a multimodal data collection and fusion processing mechanism. The system can not only process multi-source data such as text, voice, image and video at the same time, but also perform feature extraction and standardized expression through a unified data structure, thereby significantly improving the completeness and accuracy of patient condition information, avoiding triage errors caused by missing information or expression deviations, and improving the quality of basic triage data.

[0020] 2. This invention introduces a comprehensive assessment mechanism for the severity of a patient's condition, combining basic patient information and past medical history to achieve a more objective and quantitative grading process. Compared to traditional methods relying on experience, this system can dynamically assess a patient's condition based on multidimensional characteristics. Furthermore, it integrates this assessment with real-time medical resource status for intelligent triage and pathway optimization, effectively alleviating departmental congestion and uneven resource allocation. This improves overall medical resource utilization efficiency, shortens patient waiting times, and enhances the operational efficiency of outpatient and emergency departments.

[0021] 3. This invention achieves intelligent assistance and standardized management throughout the entire diagnosis and treatment process by setting up functional modules such as intelligent interaction, personalized treatment path generation, medical behavior monitoring and early warning, and intelligent recommendation. During the diagnosis and treatment process, the system can automatically complete medical record information, optimize the diagnosis and treatment process, and monitor the rationality of medical behaviors in real time, providing early warnings for abnormal situations, thereby reducing medical risks. Simultaneously, through drug compatibility analysis and treatment plan comparison, it provides decision support for doctors and patients. Furthermore, through patient self-management and a closed-loop feedback mechanism throughout the entire process, it achieves data integration and continuous optimization before, during, and after diagnosis, further improving the quality of medical services and patient satisfaction. Attached Figure Description

[0022] Fig. 1 This is a system block diagram of the present invention; Fig. 2 This is a data flow diagram of the module unit of the present invention. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of this invention clearer, the following description is provided in conjunction with embodiments and appendices. Figs. 1-2 The present invention will be further described in detail below. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0024] Example 1: This example uses the integrated intelligent triage system for outpatient and emergency departments of a tertiary general hospital as an application scenario to specifically illustrate the medical behavior collection, analysis, and monitoring system for multi-source data fusion in outpatient and emergency departments described in this invention. The system is deployed on hospital self-service terminals, mobile applications, and doctor workstations, and achieves data interoperability through the hospital's internal information system.

[0025] In actual operation, upon arrival at the hospital, patients first input information through the multimodal symptom collection unit in the intelligent triage and condition assessment module. Patients can input their chief complaint text via a self-service terminal or describe their symptoms via voice. The system also supports uploading photos of the affected area or images of relevant examination reports. In some cases, it can also record the patient's dynamic performance, such as breathing or limb movement, via video. The system uniformly accesses all these various forms of data and, through built-in semantic parsing and recognition technology, transforms unstructured information into standardized symptom feature data, thereby forming structured input data.

[0026] After symptom collection is completed, the system automatically invokes the severity index calculation unit in the intelligent triage and condition assessment module to comprehensively evaluate the patient's current status. This unit not only analyzes symptom characteristics but also combines basic patient information, such as age, gender, past medical history, and chronic disease status, to make a comprehensive judgment. Based on built-in grading rules, the system classifies patients into different condition levels, including acute and critical illness, general emergency, and general outpatient categories, providing a basis for subsequent triage.

[0027] After obtaining the severity level of the illness, the system uses the intelligent triage and appointment optimization unit within the intelligent triage and illness assessment module to perform department matching and resource scheduling. This unit matches the corresponding department based on the illness category; for example, it prioritizes assigning chest pain patients to cardiology and trauma patients to emergency surgery. Simultaneously, the system obtains real-time data on queuing status, doctor availability, and clinic load for each department, dynamically assessing medical resources and allocating the optimal treatment path for patients based on this assessment, including the target department, doctor level, and estimated waiting time.

[0028] When the system detects that departmental resources are strained or that a patient's condition requires higher-level medical services, the intelligent triage and condition assessment module's intelligent tiered referral channel is triggered, enabling referrals between different departments within the hospital, or transferring patients to higher-level or specialized hospitals, and automatically completing appointment registration and information transmission, thereby reducing patients' repeated registration and waiting time.

[0029] During the patient's waiting and consultation process, the intelligent interaction and communication assistance module continues to function. Through its intelligent doctor-patient dialogue engine unit, it guides patients to supplement incomplete symptom information, such as onset time, duration, and accompanying symptoms; the voice emotion analysis unit identifies the patient's emotional state and provides relevant information to the doctor for reference; simultaneously, the intelligent medical record writing and error correction unit automatically generates a draft of a structured electronic medical record and verifies key information, thereby improving the efficiency and accuracy of medical record writing.

[0030] During the diagnosis and treatment process, the personalized treatment pathway module generates a standardized and dynamically adjustable treatment pathway for the patient based on the patient's condition and triage results. The disease atlas guidance unit generates examination and treatment procedures, such as automatically scheduling blood tests and imaging examinations for patients with infectious diseases; the intelligent waiting guidance unit optimizes the waiting order based on real-time queuing conditions; and the treatment cycle and follow-up reminder unit generates follow-up plans and rehabilitation tasks, thereby achieving continuous management of the diagnosis and treatment process.

[0031] During the diagnosis and treatment process, the intelligent quality control and compliance early warning module monitors medical behavior in real time. Specifically, the medical behavior monitoring unit constructs behavioral profiles of doctors or departments, analyzes and compares treatment behaviors, and triggers early warnings when deviations from standard procedures, duplicate examinations, or abnormal medication use occur. The medical insurance rule engine unit performs rule verification on the treatment plan, providing alerts when operations that do not comply with medical insurance policies are detected, thereby improving the standardization of diagnosis and treatment and reducing the risk of violations.

[0032] In the intelligent medical order recommendation and management module, the system provides doctors with auxiliary decision support based on individual patient characteristics and medical data. The drug suitability analysis unit analyzes drug safety based on the patient's age, liver and kidney function, and allergy history; the treatment plan cost-benefit analysis unit compares the efficacy, risks, and costs of different treatment plans; and the science popularization content push unit pushes relevant disease knowledge and health guidance to patients, thereby improving the scientific nature of medical decisions and patients' awareness.

[0033] In the patient empowerment and self-management module, the system establishes health records for patients and displays the trend of health data changes through a personal health record visualization unit; it supports patients to conduct self-assessment through a symptom self-check and health scoring unit; it supports patients to participate in the selection of treatment plans through a doctor-patient shared decision support unit; and it records treatment results through a treatment effect feedback learning unit and uses them for subsequent optimization, thereby improving patient participation and treatment compliance.

[0034] After diagnosis and treatment are completed, the end-to-end collaboration and closed-loop management module integrates and optimizes the entire process. It enables multidisciplinary collaborative diagnosis and treatment through cross-departmental collaboration units; continuously monitors patient treatment outcomes through treatment effect tracking units; and achieves seamless integration of outpatient and inpatient processes through inpatient units. Simultaneously, the system uses follow-up and data feedback mechanisms to feed treatment results back to the front-end model, optimizing subsequent triage strategies and treatment pathways, thus forming a continuously improving closed-loop system.

[0035] Through the above implementation methods, the present invention realizes integrated management of the entire process from patient data collection, disease assessment, intelligent triage, treatment execution to behavior monitoring and feedback optimization. It not only improves the efficiency of medical resource utilization, but also significantly enhances the accuracy of triage and the patient's medical experience, and has good practical application value.

[0036] Example 2: This embodiment proposes a medical behavior collection, analysis and monitoring system that integrates multi-source data from outpatient and emergency departments. The system adopts a modular and chain-like data flow design. The modules are connected through a unified data structure and interface to realize a continuous processing process from patient input to closed-loop feedback of diagnosis and treatment.

[0037] The system first receives patient input information at a medical terminal (such as a self-service machine, mobile device, or doctor's workstation) and performs unified modeling through a multimodal symptom acquisition module. During the data acquisition phase, patient input is uniformly represented as a multimodal data set: ; in, This represents the set of original input data from the patient. This represents text data, used to record patient complaints, medical history, and other textual information. This represents voice data, corresponding to the symptoms described by the patient's voice. This represents image data, such as photos of the affected area or images from examination reports; This refers to video data, such as dynamic symptom logs or surveillance videos.

[0038] The system uses natural language processing, speech recognition, and image recognition algorithms to parse the above data and uniformly map it into structured symptom feature vectors: ; in, Represents the symptom feature vector; Indicates the first Characteristic values ​​of symptoms, such as fever level, pain level, etc.; Indicates the number of symptom feature dimensions; This represents a function for multimodal data fusion and feature extraction.

[0039] In practical engineering, It can be jointly constructed from a pre-trained medical language model and a visual model, performing unified encoding and feature alignment on data from different modalities. Then, basic patient information is introduced to construct a patient attribute vector. ; in, Represents a vector of basic patient information; Indicates the first Patient attributes, such as age, gender, and history of chronic diseases; Indicates the number of attributes.

[0040] To achieve accurate assessment, symptom information is integrated with patient attributes to obtain comprehensive characteristics: ; in, Represents the fused feature vector; Indicates the first One fusion feature; Indicates the dimension of the fused features; The feature fusion function can be represented by weighted concatenation or deep neural network fusion.

[0041] During the disease assessment phase, the system calculates a severity score using a weighted model: ; in, A score indicating the severity of the illness; Indicates the first The weight coefficients of each feature are used to reflect the importance of that feature; Indicates the first One fusion feature value; This represents the total number of fused features.

[0042] To avoid the influence of different units of measurement, the scores are normalized: ; in, This represents the normalized disease score; Indicates the original score; This represents the minimum historical score. This represents the highest historical score. The classification is based on the normalization results: ; in, Indicates the triage level; This represents a tiered mapping function that can classify patients into different emergency levels or outpatient priorities based on a threshold.

[0043] During the triage and scheduling phase, the system matches patients to relevant departments based on their condition level and characteristic information. ; in, Indicates the target department for the match; Indicates the triage level; Indicates fusion characteristics; This represents the department matching function.

[0044] Simultaneously considering the current state of medical resources, a resource load rate model is constructed: ; in, Indicates resource load rate; This indicates the current number of patients in the queue; This indicates the number of doctors or clinics currently available.

[0045] Triage decisions are made based on the patient's condition and available resources. ; in, Indicates the triage decision result (emergency, outpatient, or referral); This represents the splitting function.

[0046] Further calculation of referral priority: ; in, Indicates referral priority; Indicates the weight of the disease condition; Indicates resource weight; This represents the normalized disease score; This indicates the resource load rate.

[0047] In the intelligent interaction module, the quality of consultation is optimized through information completeness assessment: ; in, Indicates the completeness of information; Indicates the first Whether each information item is filled in (1 indicates filled in, 0 indicates not filled in); Indicates the total number of information items.

[0048] Generate structured electronic medical records: ; in, Represents electronic medical record data; This represents the function for generating medical records.

[0049] In the personalized treatment phase, treatment pathways are constructed: ; in, Represents a set of diagnostic and treatment pathways; Indicates the first One diagnostic and treatment step; This indicates the number of steps. The estimated waiting time is: ; in, Indicates the estimated waiting time; Indicates resource load rate; Indicates the triage level (the larger the value, the lower the priority).

[0050] The treatment cycle is calculated as follows: ; in, Indicates the total treatment cycle; Indicates the first Time required for each diagnostic and treatment step; Indicates the number of steps. In medical behavior monitoring, the behavioral deviation is calculated as follows: ; in, Indicates the degree of abnormality in behavior; Indicates the current eigenvalue; Represents the historical average characteristic value; Indicates the number of features. When: The system then triggers a risk warning; among which, This indicates the warning threshold.

[0051] In the intelligent recommendation module, the drug matching score is as follows: ,in, Indicates drug suitability; This represents the drug matching function.

[0052] Treatment plan evaluation: ,in, Indicates the effectiveness of the treatment plan; Indicators representing therapeutic efficacy; Indicates risk indicators; Indicates the degree of side effects; These are the weighting coefficients.

[0053] During the patient self-management phase, the health status index is: ; in, Indicates health index; Indicates weight; Indicates symptom characteristic values; This indicates the number of features. The updated health status is: ; in, This indicates the updated health index; This represents the self-evaluation correction function.

[0054] Finally, model optimization is performed within closed-loop management: ; in, Indicates the updated features; Indicates the original feature; This indicates a deviation in the diagnosis or treatment results; This represents the learning rate.

[0055] The optimization objective is: ; in, This represents the vector norm, used to measure the difference before and after optimization.

[0056] In summary, the outpatient and emergency multi-data fusion medical behavior collection, analysis, and monitoring system described in this embodiment acquires the patient's original data set through a multimodal symptom collection module. and via feature extraction function Transform into symptom feature vector Further combining patient basic information vectors Through the fusion function Forming a comprehensive feature vector Based on this, the system uses a weighted model to calculate the severity score of the illness. And obtained through normalization Then through hierarchical functions Determine the triage level This drives the department matching function. and the diversion decision function This enables intelligent triage and resource allocation for patients across outpatient, emergency, and referral pathways.

[0057] Subsequently, through information completeness indicators Complete the consultation information and generate a structured medical record. To further construct a set of diagnosis and treatment pathways And combined with resource load rate Calculate waiting time and treatment cycle This allows for dynamic optimization of the diagnosis and treatment process. During the execution of diagnosis and treatment, behavioral deviation is monitored. With threshold To achieve real-time monitoring and risk warning of medical practices, and based on drug compatibility and the effectiveness of treatment plans It provides intelligent decision support. Simultaneously, the system uses a health status index... and update value Enable patients to conduct self-assessment and participate in decision-making.

[0058] Ultimately, through a feedback optimization mechanism, deviations in treatment results are addressed. Feedback is fed back into the feature vector update process to obtain the optimized features. And by minimizing the objective function This system enables continuous learning and performance improvement of the system model, thus forming a complete system encompassing "data collection, intelligent assessment, triage scheduling, treatment execution, behavior monitoring, and feedback optimization." Through the above technical solutions, this system can improve triage accuracy, shorten patient waiting times, and enhance overall treatment efficiency and the quality of medical services while ensuring the rational allocation of medical resources.

[0059] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments, but the present invention is not limited to these embodiments. Equivalent modifications made by those skilled in the art without departing from the principles of the present invention should fall within the protection scope of the present invention.

[0060] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A medical behavior collection, analysis, and monitoring system that integrates multi-source data from outpatient and emergency departments, characterized in that, include: The system includes modules for intelligent triage and disease assessment, intelligent interaction and communication assistance, personalized treatment pathways, intelligent quality control and compliance early warning, intelligent medical order recommendation and management, patient empowerment and self-management, and full-process collaboration and closed-loop management. The intelligent triage and disease assessment module is used to collect patients' multimodal symptom information, calculate the severity of their condition, generate triage levels, and output triage results. The intelligent interaction and communication assistance module is used to guide patients to supplement symptom information, analyze emotional state, and generate structured medical record data. The personalized treatment pathway module is used to generate treatment pathways based on the patient's condition and disease knowledge, and to provide waiting guidance and follow-up visit management. The intelligent quality control and compliance early warning module is used to monitor medical treatment behavior and perform compliance detection and early warning based on rules; The intelligent recommendation and management module for medical orders is used to intelligently recommend and optimize medication and treatment plans; The patient empowerment and self-management module is used to realize patient health data management, symptom self-assessment, and participatory diagnosis and treatment decision-making. The full-process collaboration and closed-loop management module is used to realize cross-departmental collaboration, efficacy tracking, and closed-loop optimization of diagnosis and treatment feedback.

2. The medical behavior collection, analysis, and monitoring system based on multi-source data fusion in outpatient and emergency departments according to claim 1, characterized in that, The intelligent triage and disease assessment module includes: a multimodal symptom acquisition unit, a disease severity index calculation unit, an intelligent triage and appointment optimization unit, and an intelligent hierarchical referral unit; wherein the multimodal symptom acquisition unit is used to collect the patient's text, voice, image, and video information; The severity index calculation unit is used to calculate the severity of the illness based on the symptom information and the patient's basic information; the intelligent triage and appointment optimization unit is used to match the department to be treated according to the severity of the illness and optimize the queuing order; the intelligent hierarchical referral channel is used to realize intra-hospital referral and inter-hospital referral.

3. The medical behavior collection, analysis, and monitoring system based on multi-source data fusion in outpatient and emergency departments according to claim 1, characterized in that, The intelligent interaction and communication assistance module includes: The unit includes a doctor-patient intelligent dialogue engine, a voice emotion analysis unit, and an intelligent medical record writing and error correction unit. The doctor-patient intelligent dialogue engine unit is used to guide patients to supplement symptom information; The voice emotion analysis unit is used to identify the patient's emotional state; The intelligent medical record writing and error correction unit is used to generate structured medical records and perform information verification.

4. The medical behavior collection, analysis, and monitoring system based on multi-source data fusion in outpatient and emergency departments according to claim 1, characterized in that, The personalized treatment pathway module includes: Disease atlas guidance unit, intelligent waiting room guidance unit, and treatment cycle and follow-up visit reminder unit; The disease atlas guidance unit is used to generate treatment pathways based on disease knowledge. The intelligent waiting guidance unit is used to optimize the waiting order based on the status of medical resources; The treatment cycle and follow-up reminder unit is used to generate follow-up plans and reminders.

5. The medical behavior collection, analysis, and monitoring system based on multi-source data fusion in outpatient and emergency departments according to claim 1, characterized in that, The intelligent quality control and compliance early warning module includes: Medical behavior monitoring unit and medical insurance rule engine unit; The medical behavior monitoring unit is used to identify abnormal medical behaviors; The medical insurance rule engine unit is used to detect whether the treatment plan complies with medical insurance rules and output early warning information.

6. The medical behavior collection, analysis, and monitoring system based on multi-source data fusion in outpatient and emergency departments according to claim 1, characterized in that, The intelligent medical order recommendation and management module includes: The unit includes a drug suitability analysis unit, a treatment plan cost-benefit analysis unit, and a science popularization content delivery unit. The drug suitability analysis unit is used to match appropriate drugs based on patient characteristics; The cost-benefit analysis unit for treatment plans is used to compare the effectiveness and cost of different treatment plans. The science popularization content push unit is used to push relevant health information to patients.

7. The medical behavior collection, analysis, and monitoring system based on multi-source data fusion in outpatient and emergency departments according to claim 1, characterized in that, The patient empowerment and self-management module includes: The system includes a personal health record visualization unit, a symptom self-assessment and health scoring unit, a doctor-patient shared decision support unit, and a treatment effect feedback and learning unit. The personal health record visualization unit is used to display changes in the patient's health data; The symptom self-assessment and health scoring unit is used to support patients in assessing their symptoms. The shared decision support unit for doctors and patients is used to support patients' participation in diagnosis and treatment decisions; The treatment effect feedback learning unit is used to optimize the model based on the treatment results.

8. The medical behavior collection, analysis, and monitoring system based on multi-source data fusion in outpatient and emergency departments according to claim 1, characterized in that, The full-process collaboration and closed-loop management module includes: a cross-departmental collaboration unit, a treatment effect tracking unit, and an inpatient unit; The interdisciplinary collaboration unit is used to achieve multi-disciplinary collaborative diagnosis and treatment; The treatment effect tracking unit is used to continuously monitor the patient's treatment effect; The inpatient unit is used to connect outpatient and inpatient processes.

9. The medical behavior collection, analysis, and monitoring system based on multi-source data fusion in outpatient and emergency departments according to claim 1, characterized in that, The system performs dynamic triage and pathway optimization based on patient symptom data, basic patient information, and the status of medical resources.

10. The medical behavior collection, analysis, and monitoring system based on multi-source data fusion in outpatient and emergency departments according to claim 1, characterized in that, The system continuously optimizes the triage model, treatment pathways, and recommendation strategies based on feedback from diagnosis and treatment results, thereby forming a closed-loop self-learning mechanism.

Images