Intelligent hospital management system based on clinical scientific research integration

Abstract

The invention relates to an intelligent hospital management system based on clinical scientific research integration, and the system comprises a clinical scientific research integration platform which is provided with a special disease database data service module which is used for integrating patient clinical data with a patient as a center; the special disease database data service module comprises a special disease scientific research data center which is used for storing high-quality multi-dimensional structured patient data processed by an artificial intelligence technology; the regional decision application module is used for collecting multi-hospital-area data and carrying out hospital diagnosis and treatment and multi-dimensional analysis of medication data; the regional collaborative application module is used for realizing medical resource sharing of multiple hospital areas; and the regional multi-center-line image integration module is used for acquiring image system data of a plurality of courtyards and realizing sharing and mutual recognition. According to the invention, multi-center medical data integration and scientific research collaboration are realized, and the collaborative work and collaborative diagnosis and treatment efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of medical information technology, and in particular to a smart hospital management system based on the integration of clinical and scientific research. Background Art

[0002] With the rapid development of medical informatization, hospitals have widely established various information systems, including electronic medical records (EMRs), hospital information systems (HISs), laboratory information systems (LISs), radiology information systems (RISs), and picture archiving and communication systems (PACSs). These systems have played a vital role in improving hospital management efficiency and the quality of medical services. In oncology hospitals in particular, a large amount of clinical data, such as patient information, medical records, test results, prescriptions, surgical records, and pathology reports, is collected and stored in diverse databases. At the same time, regional medical collaboration models are gradually gaining momentum, and multi-center medical cooperation networks are taking shape. Demand for services such as remote consultations, two-way referrals, and medical image sharing among medical institutions is growing. With the advancement of artificial intelligence, big data, and cloud computing technologies, intelligent analysis platforms integrating clinical and scientific research are emerging, aiming to integrate clinical data resources and support medical decision-making and scientific research.

[0003] Current medical information systems generally suffer from the separation of clinical data and scientific research activities. The massive amount of data generated by clinical medical activities is difficult to directly use in scientific research projects. The lack of disease-specific databases designed for specific diseases (such as tumors and other different types of cancer) makes it difficult for researchers to efficiently obtain structured and standardized disease-specific data sets. At the same time, the imperfect mechanism for sharing clinical and scientific research data among multiple centers has hindered the development of clinical research based on multi-center real-world data. Therefore, it is urgent to establish a new architectural model that, through the construction of disease-specific databases, can automatically convert the data generated during clinical diagnosis and treatment into high-quality data resources that can be used for scientific research, and realize the effective collaboration and sharing of medical resources and research data in a multi-center environment. Summary of the Invention

[0004] The present invention provides a smart hospital management system based on the integration of clinical and scientific research to solve the defects of the existing technology.

[0005] The present invention provides a smart hospital management system based on the integration of clinical and scientific research, including:

[0006] A regional decision-making application module, which is used to aggregate data from multiple hospital districts and conduct multi-dimensional analysis of hospital diagnosis, treatment, and medication data;

[0007] A regional collaborative application module, which is used to realize the sharing of medical resources among multiple hospital districts;

[0008] A regional multi-center online imaging integration module, which is used to collect multi-type imaging system data from multiple hospital districts and realize sharing and mutual recognition;

[0009] An integrated clinical and scientific research platform, wherein the integrated clinical and scientific research platform is respectively connected to the regional decision-making application module, the regional collaborative application module and the regional multi-center online imaging integration module to support data sharing. The integrated clinical and scientific research platform is provided with a special disease database data service module, and the special disease database data service module is used to integrate the multi-hospital data and the imaging system data into patient-centered patient clinical data, wherein the special disease database data service module includes a special disease scientific research data center, and the special disease scientific research data center is used to store high-quality multi-dimensional structured patient data processed by artificial intelligence technology.

[0010] According to the smart hospital management system based on the integration of clinical and scientific research provided by the present invention, the disease database data service module includes:

[0011] A data integration unit, configured to integrate patient clinical data in a patient-centric manner;

[0012] A disease-specific dataset management unit, which is used to customize disease-specific datasets that meet research needs by referring to clinical datasets, guidelines, and expert consensus from professional institutions;

[0013] A disease-specific database data overview unit, which is used to display an overview of the disease-specific database patients and medical records, variables of interest, data period distribution, and other information;

[0014] A medical record retrieval unit is used to perform full-text search and complex condition retrieval based on patient and medical record keywords.

[0015] According to the smart hospital management system based on the integration of clinical and scientific research provided by the present invention, the disease database data service module also includes:

[0016] A patient 360-degree view unit is used to enter the patient 360-degree view by clicking on the patient number, and to conduct a comprehensive view browsing of the patient information;

[0017] A patient label system unit, which is used to perform customized management of patient labels and perform rapid patient location query according to the labels;

[0018] The medical record exploration unit is used to conduct a data content survey based on the record writing situation and complete the preliminary feasibility analysis of the inclusion and exclusion conditions.

[0019] According to the present invention, a smart hospital management system based on the integration of clinical and scientific research is provided, wherein the integrated clinical and scientific research platform further comprises:

[0020] A scientific research data management module, comprising:

[0021] A project management unit, which is used to manage project progress, project members, project descriptions, and project attachments;

[0022] An admission and exclusion patient management unit is used to manage the admission and exclusion patients according to the subject, and to update the patients who meet the admission conditions in real time according to the admission and exclusion condition data;

[0023] A focus variable collection unit, which is used to automatically fill the variables after scientific research domain management into the data set;

[0024] A scientific research form design unit is used to design and edit the case report form required for the scientific research project and to fill in the follow-up stage and follow-up content according to the research design.

[0025] According to a smart hospital management system based on the integration of clinical and scientific research provided by the present invention, the scientific research data management module further includes:

[0026] A medical record display unit, which is used to display patient medical record data;

[0027] The data query and export unit is used to support various logical queries and export multi-modal data such as patient dimension, time dimension, and medical consultation dimension.

[0028] According to the present invention, a smart hospital management system based on the integration of clinical and scientific research is provided, wherein the integrated clinical and scientific research platform further comprises:

[0029] A scientific research authority system management module, which includes:

[0030] A user management unit, which is used to add new users and authorize them according to their identities;

[0031] A data permission unit, which is used to provide different roles with browsing and searching permissions for hospital-level data, department-level data, and medical group-level data;

[0032] A medical record anonymization unit, configured to anonymize medical records;

[0033] The minimum authority setting unit is used to comply with the medical industry's ethical standards and information security standards and provide the required minimum data sets for different roles.

[0034] According to the smart hospital management system based on the integration of clinical and scientific research provided by the present invention, the regional decision application module includes:

[0035] A hospital performance assessment submodule, which is used to analyze hospital district dimensions and time trend data on functional positioning indicators, quality and safety indicators, rational drug use indicators, resource efficiency indicators, revenue and expenditure structure indicators, and cost control indicators;

[0036] An anti-tumor drug clinical application management submodule, which is used to analyze hospital-area dimensions and time trend data on anti-tumor drug usage indicators, anti-tumor drug usage amount indicators, and anti-tumor drug prescription rationality indicators;

[0037] The tumor diagnosis and treatment analysis submodule is used to analyze hospital-area dimensions and time trend data on indicators such as outpatient visits, discharges, surgeries, anti-tumor drug treatments, and radiotherapy for patients with various types of cancer.

[0038] According to a smart hospital management system based on the integration of clinical and scientific research provided by the present invention, the regional collaborative application module includes:

[0039] Multidisciplinary MDT system submodule, which is used to support multi-hospital MDT integration and view and reference the patient's current visit information and previous medical records;

[0040] A two-way referral system submodule, which is used to support the integration of multi-hospital referral systems, including referral application, administrator review, department director review, referral acceptance, comprehensive referral query, and medical record sharing and retrieval;

[0041] The scheduling system submodule is used to support multi-campus scheduling management and scheduling data sharing.

[0042] According to the smart hospital management system based on the integration of clinical and scientific research provided by the present invention, the multidisciplinary MDT system submodule includes:

[0043] MDT application unit, which is used to support the viewing and reference of the patient's current medical information and previous medical records;

[0044] MDT medical record interconnection unit, which is used to support multi-dimensional query of case reports and panoramic view of patient diagnosis and treatment;

[0045] Remote MDT unit, which is used to support authorization of a single hospital, open remote consultation application permissions, and invite medical alliance hospitals and experts within the permission to conduct MDT remote consultations;

[0046] The consultation data integration unit is used to integrate document data and image data to form an independent MDT patient document library.

[0047] According to a smart hospital management system based on the integration of clinical and scientific research provided by the present invention, the regional multi-center online imaging integration module includes:

[0048] A multi-center imaging cloud platform data acquisition submodule, which is used to collect DICOM imaging data from multiple hospital areas;

[0049] A multi-center radiotherapy data acquisition submodule, which is used to acquire various types of radiotherapy DICOM and DICOMRT data;

[0050] The image data BI application submodule is used to perform statistical analysis on archived data, and supports graphic analysis, ratio analysis, trend analysis and comparative analysis.

[0051] The present invention provides a smart hospital management system based on the integration of clinical and scientific research. By establishing an integrated clinical and scientific research platform and introducing a disease-specific database data service module, it realizes the automatic conversion and deep integration of clinical data into scientific research data, significantly improving the efficiency and quality of scientific research data acquisition. The disease-specific database data service module integrates clinical data with patients as the center, processes the data through artificial intelligence technology, and generates high-quality multi-dimensional structured patient data, providing researchers with accurate and rich disease-specific research data sets, enabling researchers to quickly locate patient groups that meet the research conditions, and greatly shortening the data collection and processing cycle. Based on the disease-specific data set management unit, the system can refer to clinical data sets, guidelines and expert consensus of professional institutions to customize disease-specific data sets that meet specific research needs, meet the personalized data needs of different cancer studies, and improve the accuracy and reliability of the research. In addition, the design of the patient 360-degree view unit and the patient label system unit enables doctors and researchers to understand patient information comprehensively and from multiple angles, and achieve accurate management and research positioning of patients; secondly, the medical record exploration unit conducts a data content survey on the record writing situation, completes the preliminary feasibility analysis of the inclusion and exclusion conditions, and provides data support for the design and implementation of scientific research projects; the scientific research data management module provides researchers with project management, inclusion and exclusion patient management, automatic collection and management of variables of interest, and scientific research form design, etc., covering the data management needs of the entire life cycle of scientific research projects, greatly reducing the data processing burden of scientific researchers; the introduction of the scientific research authority system management module ensures the privacy and security of patient data, and provides the required minimum data set for different roles on the premise of complying with the ethical standards and information security standards of the medical industry, balancing the relationship between data sharing and privacy protection. The regional decision-making application module provides data support for hospital management decisions through multi-dimensional analysis of data such as performance appraisal of tertiary public hospitals, clinical application management of anti-tumor drugs, and tumor diagnosis and treatment; in addition, the integration of the multidisciplinary MDT system, two-way referral system and unified scheduling system in the regional collaborative application module significantly improves the efficiency of multi-center medical collaboration and promotes the sharing of high-quality medical resources; the regional multi-center online imaging integration module realizes the collection and sharing of imaging data from multiple hospital campuses, especially the specialized collection and processing of radiotherapy data, meeting the special needs of tumor specialty hospitals.

[0052] In summary, this invention maximizes the value of medical data by constructing an integrated clinical and scientific research platform with a disease-specific database as its core, providing strong technical support for multi-center medical collaboration and scientific research based on real-world data. It is of great significance to improving the diagnosis and treatment level of complex diseases such as tumors and the ability of scientific research and innovation. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0054] Figure 1 A schematic diagram of the structure of a smart hospital management system based on the integration of clinical and scientific research provided by an embodiment of the present invention;

[0055] Figure 2 A schematic diagram of the structure of the clinical research integration platform provided by an embodiment of the present invention;

[0056] Figure 3 This is a schematic diagram of the structure of the disease-specific database data service module provided in an embodiment of the present invention.

[0057] Reference numerals:

[0058] 100. Clinical research integration platform; 200. Regional decision-making application module; 300. Regional collaborative application module; 400. Regional multi-center online imaging integration module;

[0059] 110. Special disease database data service module; 120. Scientific research data management module; 130. Scientific research authority system management module;

[0060] 111. Data integration unit; 112. Special disease data set management unit; 113. Special disease database data overview unit; 114. Case retrieval unit; 115. Patient 360-degree view unit; 116. Patient labeling system unit; 117. Medical record exploration unit. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with the drawings in the present invention. Obviously, the embodiments described are part of the embodiments of the present invention, not all of the embodiments, and they should not be understood as limitations on the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. In the description of the present invention, it should be understood that the terms used are only for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0062] The embodiments of the present invention are described below with reference to the accompanying drawings.

[0063] like Figure 1 As shown, the present invention provides a smart hospital management system based on the integration of clinical and scientific research, including:

[0064] The clinical and scientific research integrated platform 100 is respectively connected to the regional decision-making application module 200, the regional collaborative application module 300 and the regional multi-center online imaging integration module 400 to support data sharing. The clinical and scientific research integrated platform 100 is provided with a special disease database data service module 110. The special disease database data service module 110 is used to integrate the multi-hospital data and the imaging system data into patient-centered patient clinical data, wherein the special disease database data service module 110 includes a special disease scientific research data center, and the special disease scientific research data center is used to store high-quality multi-dimensional structured patient data processed by artificial intelligence technology.

[0065] Furthermore, the integrated clinical and scientific research platform can achieve efficient use of medical data by integrating clinical data with scientific research applications. The integrated clinical and scientific research platform is equipped with a disease-specific database data service module, which serves as the core data processing unit of the system and is specifically responsible for integrating patient clinical data with a patient-centered approach. Its core is the disease-specific scientific research data center, which uses artificial intelligence technology to process raw clinical data, including data cleaning, structured conversion, semantic standardization, etc., and ultimately generates high-quality, multi-dimensional structured patient data. The processed data can meet the precise needs of different disease-specific studies and provide a reliable data foundation for clinical scientific research.

[0066] like Figure 3 As shown, the disease database data service module 110 includes:

[0067] The data integration unit 111 is used to integrate patient clinical data in a patient-centric manner.

[0068] Furthermore, the data integration unit uses patient identification technology to correlate, match and integrate patient data scattered in different medical information systems (such as HIS, EMR, etc.). The data integration process first identifies the same patient through a unique identifier (such as patient ID, ID number, etc.), and then uses ETL technology to extract data from the source system. After format conversion and data cleaning, data from different sources are uniformly stored in the data warehouse. The data integration unit realizes the integration of real-time and historical data, ensures the integrity and timeliness of patient data, and provides basic data support for subsequent disease-specific data analysis.

[0069] The disease-specific data set management unit 112 is used to customize disease-specific data sets that meet research needs with reference to clinical data sets, guidelines and expert consensus of professional institutions.

[0070] Furthermore, the disease-specific dataset management unit is responsible for constructing disease-specific datasets based on clinical standards. Specifically, it first defines disease-specific data elements and data structures based on clinical dataset standards, disease diagnosis and treatment guidelines, and expert consensus issued by professional organizations. Then, mapping rules are used to convert general clinical data into disease-specific datasets that meet the research needs of specific diseases. The disease-specific dataset management unit supports flexible configuration and can customize datasets containing disease-specific indicators based on the characteristics of different cancer types (such as lung cancer, gastric cancer, esophageal cancer, colorectal cancer, etc.), and dynamically update dataset definitions based on research progress. The disease-specific dataset management unit ensures the scientific nature and theoretical value of disease-specific data by managing standardized datasets.

[0071] The disease-specific database data overview unit 113 is used to display an overview of the disease-specific database patients and medical records, variables of interest, data period distribution and other information.

[0072] Furthermore, the data overview unit of the disease-specific database provides a data visualization function that can intuitively display the data distribution and quality status of the disease-specific database. Specifically, the disease-specific database data overview unit generates statistical charts based on dimensions such as basic patient characteristics, medical record completeness, coverage of variables of interest, and data time distribution. It also uses data statistical algorithms to calculate the distribution of various indicators, such as patient age distribution, gender ratio, stage distribution, and treatment method distribution, to form an overview of the disease-specific database data. In addition, it also has a data quality monitoring function, which calculates indicators such as data completeness, accuracy, and consistency, and promptly discovers data problems. This visual overview can help researchers quickly evaluate data availability and provide a data foundation for scientific research design.

[0073] The medical record retrieval unit 114 is used to perform full-text search and complex condition retrieval based on patient and medical record keywords.

[0074] Furthermore, the medical record retrieval unit provides data retrieval capabilities, enabling rapid location of required information from massive amounts of clinical data, enabling accurate retrieval of patients and their medical records. Specifically, the medical record retrieval unit performs full-text retrieval based on an inverted index, establishes an index library after segmenting the medical record text, and supports functions such as keyword fuzzy matching and synonym expansion. Structured queries use SQL statements to conditionally filter structured fields in the database. It also supports complex condition combinations, connecting multiple search conditions through Boolean logic such as AND, OR, and NOT to achieve refined queries. The search results are displayed in a list format, and a result export function is provided to facilitate subsequent data analysis.

[0075] The disease-specific database data service module 110 further includes:

[0076] The patient 360 view unit 115 is used to enter the patient 360 view by clicking on the patient number and conduct a comprehensive view browsing of the patient information.

[0077] Furthermore, the patient 360 view unit associates all relevant clinical data based on the patient's unique identifier (such as the patient number) to construct a patient medical data timeline. When the user clicks on the patient number, the system automatically collects the patient's basic information, outpatient records, hospitalization records, test results, medical prescriptions, surgical records, pathology reports, imaging data and other full-dimensional information to form a unified view interface.

[0078] The patient 360-degree view unit uses a tabbed layout design to categorize and display different types of clinical data, and supports timeline navigation, making it easy to view the patient's diagnosis and treatment status at different stages. The final unit uses a data association algorithm to associate and integrate scattered patient data, providing a comprehensive perspective for medical decision-making and scientific research analysis.

[0079] The patient tag system unit 116 is used to perform customized management of patient tags and perform rapid patient location query according to the tags.

[0080] Furthermore, the patient label system unit first automatically generates basic labels based on clinical characteristics, such as demographic feature labels (age group, gender, etc.), disease feature labels (diagnosis type, stage, pathology type, etc.), treatment feature labels (surgery type, chemotherapy regimen, radiotherapy dose, etc.) and prognosis feature labels (recurrence status, survival status, etc.). It also supports user-defined labels and creates a personalized label system based on research needs. The labels form a complete label network through hierarchical and associated relationships, and support composite label queries. The patient label system unit uses label indexing technology to achieve rapid retrieval and statistics of labels. Users can quickly locate specific groups among massive patients by combining multiple label conditions, thereby improving patient screening efficiency.

[0081] The medical record exploration unit 117 is used to conduct a data content survey based on the record writing situation and complete the preliminary feasibility analysis of the inclusion and exclusion conditions.

[0082] Furthermore, the Medical Record Exploration Unit uses data mining technology to systematically analyze medical record compilation and assess data integrity, standardization, and usability. Specifically, it first calculates the completion and completeness rates of various medical record documents, identifying key areas where data is missing. It then analyzes data consistency and detects inconsistencies and conflicts between different documents. It then assesses the degree of data standardization, calculating the structuring rate and coding standardization. Finally, based on these analysis results, it conducts preliminary feasibility assessments based on the inclusion and exclusion criteria for specific studies, predicting the number of eligible patients and data quality. By replacing traditional manual sampling inspections with automated analysis, the Medical Record Exploration Unit has comprehensively improved data quality control capabilities and the accuracy of research feasibility assessments.

[0083] like Figure 2 As shown, the clinical research integrated platform 100 also includes:

[0084] The scientific research data management module 120 includes:

[0085] The project management unit is used to manage project progress, project members, project descriptions and project attachments.

[0086] The scientific research data management module is specifically responsible for the full-process data management of scientific research projects. Specifically, the subject management unit serves as the management center of scientific research projects, providing functions such as project creation, progress tracking, and member management. When a subject is created, the system records basic project information, research objectives, research design, and implementation plans. Subject progress management adopts a milestone model, setting key nodes and automatic reminders. Subject member management supports role allocation and clarifies the authority and responsibilities of each member. Subject description and attachment management provide document storage and version control functions. The subject management unit integrates scattered scientific research activities into a unified platform through scientific research data integration technology, realizing digital management of the entire cycle of scientific research projects.

[0087] The patient admission management unit is used to manage the patients admitted according to the subject, and update the patients who meet the admission conditions in real time according to the admission condition data.

[0088] The Patient Inclusion and Exclusion Management Unit first converts the inclusion and exclusion criteria defined in the study protocol into query conditions recognizable by the system. It then automatically screens eligible patient populations based on a specialized disease database. This screening process utilizes rule engine technology to convert complex inclusion and exclusion criteria into logical expressions and perform multiple condition matching on patient data. The Patient Inclusion and Exclusion Management Unit supports real-time data updates. When new patient data enters the system or existing patient data changes, it automatically reassesses inclusion and exclusion status to ensure dynamic updates of the study population. It also provides patient grouping capabilities, enabling stratified management of enrolled patients based on different characteristics, assisting in stratified analysis and statistics.

[0089] The focus variable collection unit is used to automatically fill the variables after scientific research domain management into the data set.

[0090] Furthermore, the focus variable collection unit is responsible for automatically collecting and managing the core data indicators required for scientific research. First, through the definition of the scientific research domain, the variable set of research focus is clarified, including baseline characteristic variables, exposure variables, outcome variables, etc., and then based on the variable mapping rules, the relevant data is automatically extracted from the disease database and filled into the scientific research data set. For highly structured variables, such as laboratory test results, the system can directly extract them. For semi-structured or unstructured data, such as image descriptions and pathology reports, natural language processing technology is used to extract information. The focus variable collection unit also supports data verification function, which checks the rationality of the collected variable values to ensure data quality. Through automated variable collection, the tedious data entry work in traditional scientific research is greatly reduced, while improving data accuracy.

[0091] A scientific research form design unit is used to design and edit the case report form required for the scientific research project and to fill in the follow-up stage and follow-up content according to the research design.

[0092] Furthermore, the scientific research form design unit is based on electronic data capture (EDC) system technology and supports users to customize the design of case report forms. During the form design process, users can select the input control type (such as radio button, check box, date selector, etc.), set data validity rules, define calculation fields, etc.

[0093] The system also provides a form template library that includes standardized forms for commonly used research designs. Users can modify and customize them based on the templates. For follow-up studies, the scientific research form design unit supports the design of multi-stage follow-up forms, configures follow-up time points and follow-up content, and automatically generates a complete follow-up plan. The final form data obtained is associated with the patient's basic data, achieving seamless connection between clinical data and research data.

[0094] The scientific research data management module 120 further includes:

[0095] A medical record display unit is used to display patient medical record data.

[0096] The medical record display unit adopts a multi-level data visualization solution to transform complex medical record information into an intuitive and easy-to-read interface. The medical record display is organized according to chronological order and document type, and supports classified browsing of different types of documents such as outpatient medical records, inpatient medical records, surgical records, examination reports, etc.

[0097] The data query and export unit is used to support various logical queries and export multi-modal data such as patient dimension, time dimension, and medical consultation dimension.

[0098] The data query and export unit supports data query and statistics from multiple angles, such as patient dimension, time dimension, and medical treatment dimension, by constructing a multidimensional data analysis model. Query operations are implemented through a visual query builder. Users can set query conditions and output fields by dragging and dropping without writing complex SQL statements. In addition, query results can be exported in multiple formats, including Excel and CSV files for general data processing, and SPSS and SAS formats for professional statistical analysis, to meet the data needs of different research scenarios.

[0099] The integrated clinical research platform 100 further includes:

[0100] Scientific research authority system management module 130.

[0101] Furthermore, the scientific research authority system management module is the security assurance system of the integrated clinical research platform. It ensures data security and compliance through refined authority management. The scientific research authority system management module adopts a role-based access control (RBAC) architecture and realizes comprehensive data security protection through the collaborative work of multiple functional units.

[0102] The scientific research authority system management module 130 includes:

[0103] The user management unit is used to add new users and authorize them according to their identities.

[0104] Furthermore, the user management unit is responsible for the creation and permission allocation of system users, supports batch import of existing hospital personnel information, and automatically creates user accounts. The user addition process includes steps such as basic information entry, role allocation, and permission setting. The user management unit assigns appropriate system roles to different users based on user identity attributes (such as position, department, research role, etc.), and associates corresponding operation permissions through roles.

[0105] The data permission unit is used to provide different roles with browsing and searching permissions for hospital-level data, department-level data, and medical group-level data.

[0106] Furthermore, based on the principle of data stratification, the data permission unit divides medical data into three permission ranges: hospital-wide, department-level, and medical group-level. Specifically, hospital-wide permissions are open to hospital managers, allowing them to view hospital-wide aggregated data; department-level permissions limit users to accessing only patient data within their department; and medical group-level permissions are further refined, allowing only access to patient information treated by the individual or their medical group. The data permission unit uses a data filtering mechanism to automatically apply permission restrictions during query execution, ensuring that users can only access data within the authorized scope. It also supports special authorization functions, temporarily granting project team members access to designated patient data if a scientific research project is approved.

[0107] The medical record anonymization unit is used to perform anonymization processing on the medical record.

[0108] The medical record anonymization unit provides data desensitization to protect patient privacy. Specifically, it first identifies sensitive fields, such as the patient's name, ID number, and contact information. It then processes this sensitive information according to anonymization rules, such as direct deletion, replacement with random codes, or obfuscation. Finally, it generates an anonymized dataset for research use. This unit protects privacy while maximizing the value of data analysis. It also provides re-identification mapping table management, ensuring traceability to the original data when necessary.

[0109] The minimum authority setting unit is used to comply with the medical industry's ethical standards and information security standards and provide the required minimum data sets for different roles.

[0110] Furthermore, the least privilege setting unit implements precise data access control based on medical ethics and data security standards. The unit adheres to the principle of least privilege, meaning that users can only access the minimum dataset necessary to complete their work. This is achieved by first defining standard dataset templates based on user roles (such as administrator, researcher, data analyst, etc.). Then, for specific research projects, project-specific data access scopes are customized based on ethical approval requirements. Finally, through data view technology, user-visible fields are controlled at the database level to ensure that sensitive information is not accessed without authorization.

[0111] The regional decision-making application module 200 is used to collect data from multiple hospital areas and conduct multi-dimensional analysis of hospital diagnosis and treatment and medication data.

[0112] Furthermore, the regional decision-making application module is used to aggregate medical data from multiple campuses. Through data capture, cleaning, calculation, and visualization technologies, this dispersed raw data is converted into analytical results that can be used for hospital management decisions, allowing for multi-dimensional analysis of hospital diagnosis, treatment, and medication data. Specifically, the regional decision-making application module utilizes an ETL (Extract-Transform-Load) data processing architecture. It first extracts raw data from source systems such as the hospital information system, electronic medical record system, and laboratory information system of each campus. After data standardization and quality control, it is loaded into a unified data warehouse. Finally, online analytical processing is performed using OLAP technology to achieve multi-dimensional data analysis.

[0113] The regional decision application module 200 includes:

[0114] The hospital performance assessment submodule is used to analyze the hospital district dimension and time trend data of functional positioning indicators, quality and safety indicators, rational drug use indicators, resource efficiency indicators, revenue and expenditure structure indicators and cost control indicators.

[0115] The hospital performance assessment submodule comprehensively assesses hospital performance through functions such as indicator system construction, automatic data collection, and multi-dimensional calculation and presentation. It includes data processing for six key indicators: functional positioning indicators, quality and safety indicators, rational drug use indicators, resource efficiency indicators, revenue and expenditure structure indicators, and cost control indicators. The functional positioning indicator processing process first extracts raw data on outpatient visits and discharges from the HIS system, and calculates the ratio of outpatient visits to discharges through ratio calculation. Surgical data is extracted from the surgical information system and, based on surgical type classification, calculates indicators such as the proportion of day surgeries to elective surgeries, the proportion of surgeries for discharged patients, the proportion of minimally invasive surgeries, and the proportion of level 4 surgeries. The quality and safety indicator processing process extracts complication data from the adverse event reporting system and calculates the complication rate of surgical patients based on the total number of inpatients. Infection data is extracted from the infection monitoring system and calculated the infection rate of specific types of incisions based on the number of surgeries. Based on the data on the medical record homepage, statistics are compiled for 17 single tumor disease types, including the number of cases, average length of stay, total discharge costs, and mortality rate. The processing of rational drug use indicators involves extracting prescription data through the medical order system, calculating indicators such as the ratio of reviewed prescriptions and the ratio of basic drug use, and extracting procurement data from the pharmacy management system to analyze the basic drug supply situation.

[0116] The anti-tumor drug clinical application management submodule is used to perform hospital district dimension and time trend data analysis on anti-tumor drug usage indicators, anti-tumor drug usage amount indicators and anti-tumor drug prescription rationality indicators.

[0117] Furthermore, the anticancer drug clinical application management submodule leverages core technologies such as an anticancer drug classification system, a medication monitoring engine, and a prescription rationality evaluation algorithm to enable data monitoring of the entire clinical use of anticancer drugs. The anticancer drug usage indicator processing process first classifies anticancer drugs in the hospital drug catalog based on drug coding standards, distinguishing between general use and restricted use. It then extracts anticancer drug usage data from the outpatient prescription system and inpatient medical order system, performs statistical analysis based on outpatient / inpatient status and drug grade, and calculates the utilization rate of each type of anticancer drug. The anticancer drug usage amount indicator processing process extracts drug cost data from the hospital billing system and, combined with drug classification information, calculates indicators such as the percentage of anticancer drug usage amount and the percentage of restricted use anticancer drug usage amount. Furthermore, through data correlation analysis, it compiles statistics on the number of patients using key monitored anticancer drugs and adjuvant therapy medications and their costs. The anticancer drug prescription rationality indicator processing process extracts review results from the prescription review system and uses rule engine technology to evaluate prescription rationality. It calculates indicators such as the outpatient anticancer drug prescription qualification rate, the prescription intervention success rate, and the inpatient anticancer drug usage rationality rate.

[0118] The tumor diagnosis and treatment analysis submodule is used to analyze hospital-area dimensions and time trend data on indicators such as outpatient visits, discharges, surgeries, anti-tumor drug treatments, and radiotherapy for patients with various types of cancer.

[0119] The tumor diagnosis and treatment analysis submodule focuses on the mining and analysis of diagnosis and treatment data for patients with different types of cancer. Through technologies such as disease classification mapping, patient diagnosis and treatment pathway tracking, and treatment plan statistical analysis, a complete tumor patient diagnosis and treatment data analysis system has been constructed. Data processing for tumor diagnosis and treatment analysis first extracts data on various types of tumor patients from the electronic medical record system based on the ICD-10 disease coding standard, including ten common tumors such as lung cancer, gastric cancer, esophageal cancer, kidney cancer, colorectal cancer, prostate cancer, breast cancer, thyroid cancer, liver cancer, and cervical cancer. Then, the corresponding diagnosis and treatment data is extracted by linking data sources such as the outpatient system, inpatient system, surgical system, chemotherapy system, and radiotherapy system through the patient's unique identifier. Then, a tumor diagnosis and treatment indicator system is constructed based on data warehouse technology, including core indicators such as outpatient visits, outpatient treatment number, discharge number, discharge number, surgical number and proportion, anti-tumor drug treatment number and proportion, and radiotherapy number and proportion. Finally, OLAP multidimensional analysis technology is used to display and analyze data from two dimensions: hospital area dimension and time trend.

[0120] The regional collaborative application module 300 is used to realize the sharing of medical resources among multiple hospital areas.

[0121] Furthermore, the regional collaborative application module can be used to break down information barriers between hospitals and realize the sharing of medical resources among multiple hospital districts. The regional collaborative application module adopts a distributed architecture design. Through standardized data interfaces, secure data transmission channels and unified identity authentication mechanisms, it connects the information systems of different hospital districts to form a collaborative medical network. The regional collaborative application module contains three core sub-modules: a multidisciplinary MDT system sub-module, a two-way referral system sub-module and a scheduling system sub-module, which respectively solve inter-hospital collaboration problems in different scenarios. In terms of data processing, the regional collaborative application module first maps the heterogeneous data of different hospital district systems into a unified format through data standardization conversion; then, inter-hospital data exchange is carried out through a data security encryption channel; finally, data integration is achieved at the application layer through the professional functions of each sub-module.

[0122] The regional collaborative application module 300 includes:

[0123] The multidisciplinary MDT system submodule is used to support multi-hospital MDT integration and to view and reference the patient's current visit information and previous medical records.

[0124] Furthermore, MDT (Multidisciplinary Team) refers to a team composed of medical experts with different professional backgrounds who work together to develop the best diagnosis and treatment plans for complex cases. The multidisciplinary MDT system sub-module realizes the aggregation and sharing of clinical data of patients across hospital campuses.

[0125] Specifically, the MDT application process is to first collect the patient's basic information and consultation purpose, then call historical medical records through the MDT medical record interconnection unit, and the remote MDT unit coordinates the participation of multiple experts. Finally, a standardized consultation report is formed through the consultation data integration unit. Therefore, the multidisciplinary MDT system sub-module includes four functional units: MDT application unit, MDT medical record interconnection unit, remote MDT unit and consultation data integration unit, which work together to support the full process management of MDT consultation.

[0126] The multidisciplinary MDT system submodules include:

[0127] The MDT application unit is used to support the viewing and reference of the patient's current medical information and previous medical records.

[0128] Furthermore, the MDT application unit uses the Master Patient Index (MPI) technology to identify the patient's unique identifier, associate it with the current electronic medical record, and provide a structured MDT application form. The MDT application form consists of four parts: the patient's basic information area, the clinical data area, the consultation purpose area, and the expert invitation area, enabling the creation, submission, and circulation management of the MDT consultation application. The patient's basic information area automatically obtains the patient's demographic information and medical information from the HIS system through the data interface; the clinical data area provides a reference function for the current and previous medical records, and associates clinical documents in the electronic medical record library through the document reference identifier (DocumentReferenceID), including medical records, medical order information, examination reports, test results, etc.; the consultation purpose area provides auxiliary input of professional terms based on the disease-specific knowledge base and supports semi-structured descriptions; the expert invitation area provides a list of experts within the group and other specialists in the hospital, and based on the expert knowledge graph technology, intelligently recommends suitable consultation experts based on the patient's disease characteristics. The MDT application unit uses a workflow engine to drive the application flow, automatically distributes applications to relevant roles according to the configured approval rules, and ultimately realizes the full process management of application-review-arrangement-execution.

[0129] The MDT medical record interconnection unit is used to support multi-dimensional query of case reports and panoramic view of patient diagnosis and treatment.

[0130] Furthermore, the MDT medical record interconnection unit is a technical component that realizes the integration and sharing of multi-source heterogeneous medical record data. Based on the medical data exchange standard, the MDT medical record interconnection unit has built a unified clinical data model to support cross-hospital and cross-system medical record data access. In the data processing process, the MDT medical record interconnection unit first extracts the original medical record data from the source system through the configured data interface; then performs data standardization conversion to unify the data formats of different systems into a standard structure; then performs data quality control, repairs missing values, corrects outliers, and eliminates data redundancy; finally, the processed data is loaded into a temporary data storage area for query use.

[0131] The remote MDT unit is used to support the authorization of a single hospital, open up remote consultation application permissions, and invite medical alliance hospitals and experts within the permission to conduct MDT remote consultations.

[0132] Furthermore, the remote MDT unit aims to achieve cross-hospital and cross-regional remote consultation process management and technical support. The remote MDT unit first implements a role-based access control (RBAC) mechanism to assign differentiated permissions to users in different hospitals. After the remote consultation application is created, the system pushes a consultation notification to the invited experts through the message middleware, supporting multiple notification methods such as SMS and in-app messages. In addition, the core function of the remote MDT unit is remote video conferencing support. Based on real-time communication technology, it realizes low-latency, high-definition multi-party video interaction. The system supports document sharing and is integrated with the MDT medical record interconnection unit to achieve real-time synchronization of consultation medical records. At the same time, it provides collaborative annotation tools, allowing participating experts to mark and measure on shared medical images to accurately point out the location of lesions.

[0133] The consultation data integration unit is used to integrate document data and image data to form an independent MDT patient document library.

[0134] Furthermore, the consultation data integration unit uses template engine technology to define consultation report templates based on the needs of different diseases and specialties, including structured fields such as patient basic information, medical history summary, examination results, multidisciplinary discussion content, comprehensive diagnosis, and treatment recommendations. For medical imaging data, the consultation data integration unit supports the upload, storage, and display of DICOM format images, achieving unified management of multimodal images such as CT, MRI, and ultrasound. It also supports the upload and storage of non-DICOM format images (such as endoscopic images, pathological slice images, etc.) in standard formats such as JPEG. The integrated document data and imaging data are linked through the patient's unique identifier to form a complete MDT patient file, which is stored in the document database and indexed for subsequent retrieval and call-up.

[0135] The bidirectional referral system submodule is used to support the integration of multi-hospital referral systems, including referral application, administrator review, department director review, referral acceptance, comprehensive referral query and medical record sharing and retrieval.

[0136] In the healthcare system, two-way referral refers to a mechanism for mutual referral of patients between higher-level hospitals and grassroots hospitals, including three modes: upward referral (grassroots to higher-level), downward referral (superior to grassroots), and horizontal referral (between hospitals of the same level). The two-way referral system submodule establishes a unified patient identification mechanism, ensuring the continuity of patient information between different hospitals through unique identifiers such as ID numbers; secondly, it designs a standardized referral application form, which includes fields such as referral type (outpatient / inpatient), referral direction (upward / downward / horizontal), diagnosis information, and referral reason; then, based on the referral process configuration set by the hospital, it supports multi-level review or filing processes; finally, through the electronic medical record sharing interface, cross-hospital access to patients' historical diagnosis and treatment information is achieved.

[0137] The scheduling system submodule is used to support multi-campus scheduling management and scheduling data sharing.

[0138] Furthermore, the scheduling system submodule first establishes a unified resource coding system, including standardized descriptions of human resources (doctors, nurses, etc.) and physical resources (consulting rooms, beds, equipment, etc.); then obtains basic resource data from source systems such as the personnel system and HIS system of each hospital district through the data interface; then builds a scheduling rule library, and configures constraints including working hours, continuous work requirements, professional matching, etc.; finally, through the intelligent scheduling algorithm, generates the optimal scheduling plan under the premise of meeting various constraints.

[0139] The regional multi-center online image integration module 400 is used to collect image system data of multiple hospital areas and realize sharing and mutual recognition.

[0140] The purpose of the regional multi-center online imaging integration module is to realize the collection, storage, sharing and analysis of medical imaging data from multiple hospital campuses. The regional multi-center online imaging integration module adopts cloud computing architecture design. Through standardized DICOM interface, high-performance data transmission network and distributed storage technology, it builds a medical imaging cloud platform covering multiple hospital campuses, forming a complete medical imaging data lifecycle management system.

[0141] The regional multi-center online image integration module 400 includes:

[0142] The multi-center imaging cloud platform data acquisition submodule is used to collect DICOM imaging data from multiple hospital areas.

[0143] Furthermore, DICOM (Digital Imaging and Communications in Medicine) is an international standard for medical imaging equipment, which defines the format and transmission protocol of medical imaging data. The data acquisition submodule of the multi-center imaging cloud platform supports data acquisition of various imaging devices including CT, MR, DR, CR, US, endoscopes, etc. by implementing a complete DICOM standard protocol stack. The data acquisition submodule of the multi-center imaging cloud platform first configures the pre-acquisition service through the DICOM network service and establishes a connection with the PACS (Picture Archiving and Communication System) of each hospital area; then receives DICOM image data; then verifies the integrity and consistency of the received data through DICOM Validation; and finally caches the valid data in the local temporary storage area.

[0144] The storage management service of the data acquisition submodule of the multi-center imaging cloud platform adopts a three-level storage architecture, including hot storage, warm storage and archive storage. Hot storage uses high-performance hard disk arrays to store image data that has been frequently accessed in the recent period. Warm storage uses low-cost storage devices to store historical image data with less frequent access. Archive storage uses large-capacity tape libraries or object storage systems to preserve important historical data that meets specific conditions for a long time.

[0145] The multi-center radiotherapy data acquisition submodule is used to acquire various types of radiotherapy DICOM and DICOMRT data.

[0146] The multicenter radiotherapy data acquisition submodule focuses on the collection and management of radiotherapy-related medical imaging data, encompassing various DICOM data types, including DICOM RTStructure (radiotherapy structure set), DICOM RTPlan (radiotherapy plan), DICOM RTDose (radiotherapy dose), and DICOM RTDImage (radiotherapy image). The multicenter radiotherapy data acquisition submodule also adheres to the DICOM standard protocol for data acquisition, but is specifically optimized for the unique characteristics of radiotherapy data. First, the submodule integrates a parsing engine for radiotherapy-specific data types, enabling accurate identification and extraction of target volume and organ-at-risk contour data from RTStructure, field parameters and machine settings from RTPlan, and three-dimensional dose distribution data from RTDose. The extracted data is then structured and converted into a standard format for easy storage and analysis. Data integrity and consistency are then verified using data validation algorithms, such as verifying the matching of dose distribution with the treatment plan and examining the relationship between target volume and dose coverage. Finally, the validated data is stored in a dedicated radiotherapy database.

[0147] The image data BI application submodule is used to perform statistical analysis on archived data, and supports graphic analysis, ratio analysis, trend analysis and comparative analysis.

[0148] The imaging data BI application submodule aims to conduct multi-dimensional statistical analysis of imaging data and unlock its value. In terms of data processing, the imaging data BI application submodule first extracts DICOM header information (including metadata such as examination type, device information, and examination time) and related clinical tags from the imaging storage system through a data extraction interface. It then performs data conversion processing to clean, standardize, and calculate the raw data to generate various statistical indicators. The processed data is then loaded into a dedicated analysis database to construct a multidimensional data cube model. Finally, the front-end visualization engine intuitively displays the analysis results in the form of charts, dashboards, and other formats.

[0149] Taking lung cancer research as an example, data collection is carried out first. Specifically, the regional multi-center online image integration module captures DICOM format CT images of lung cancer patients from the PACS system of each hospital district through the multi-center imaging cloud platform data collection sub-module, and stores them in the disease-specific research data center. Then, the images are standardized by automatically verifying the image resolution and patient ID consistency, and missing data triggers a quality control alarm. Subsequently, the regional decision-making application module summarizes the diagnosis and treatment records of lung cancer patients in the EMR of each hospital district (such as the type of surgery, chemotherapy regimen), calculates indicators (such as the proportion of minimally invasive surgery) through the hospital performance appraisal sub-module, and pushes them to the clinical research integration platform. The MDT medical record interconnection unit of the regional collaborative application module can integrate multidisciplinary consultation opinions and link the pathology report and genetic test results in the patient's 360-degree view.

[0150] After all the data are collected, the raw data are processed through the disease-specific database data service module: data from different modules (imaging + medication records) are merged through the patient ID, and then through the disease-specific data set management unit: lung cancer research fields (EGFR mutation status, PFS time) are defined according to the NCCN guidelines, and finally key information in the unstructured pathology report (such as "adenocarcinoma, EGFRexon19 deletion") is extracted through natural language processing (NLP).

[0151] After processing, the processed data is called through the scientific research data management module. The patient inclusion management unit can automatically screen the target research population: the "EGFR mutation + osimertinib treatment" patient cohort, while the variable of interest acquisition unit extracts the maximum tumor diameter from the imaging data and fills it into the scientific research data set. The data query and export unit generates an SPSS format file for statistical analysis, and finds the conclusion that "the PFS of patients with brain metastases is shortened."

[0152] The final scientific research conclusion was a high risk of drug hepatotoxicity. The result was fed back to the regional decision-making application module, triggering rational drug use monitoring rules. At the same time, the MDT consultation records were updated to each hospital area through the regional collaborative application module to ensure treatment consistency.

[0153] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0154] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0155] Finally, 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 aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A smart hospital management system based on the integration of clinical and scientific research, characterized by: include: A regional decision-making application module, which is used to aggregate data from multiple hospital districts and conduct multi-dimensional analysis of hospital diagnosis, treatment, and medication data; A regional collaborative application module, which is used to realize the sharing of medical resources among multiple hospital districts; A regional multi-center online imaging integration module, which is used to collect multi-type imaging system data from multiple hospital districts and realize sharing and mutual recognition; An integrated clinical and scientific research platform, wherein the integrated clinical and scientific research platform is respectively connected to the regional decision-making application module, the regional collaborative application module and the regional multi-center online imaging integration module to support data sharing. The integrated clinical and scientific research platform is provided with a special disease database data service module, and the special disease database data service module is used to integrate the multi-hospital data and the imaging system data into patient-centered patient clinical data, wherein the special disease database data service module includes a special disease scientific research data center, and the special disease scientific research data center is used to store high-quality multi-dimensional structured patient data processed by artificial intelligence technology.

2. The smart hospital management system based on the integration of clinical and scientific research according to claim 1 is characterized in that: The disease-specific database data service module includes: A data integration unit, configured to integrate patient clinical data in a patient-centric manner; A disease-specific dataset management unit, which is used to customize disease-specific datasets that meet research needs by referring to clinical datasets, guidelines, and expert consensus from professional institutions; A disease-specific database data overview unit, which is used to display an overview of the disease-specific database patients and medical records, variables of interest, data period distribution, and other information; A medical record retrieval unit is used to perform full-text search and complex condition retrieval based on patient and medical record keywords.

3. The smart hospital management system based on the integration of clinical and scientific research according to claim 2 is characterized in that: The disease-specific database data service module also includes: A patient 360-degree view unit is used to enter the patient 360-degree view by clicking on the patient number, and to conduct a comprehensive view browsing of the patient information; A patient label system unit, which is used to perform customized management of patient labels and perform rapid patient location query according to the labels; The medical record exploration unit is used to conduct a data content survey based on the record writing situation and complete the preliminary feasibility analysis of the inclusion and exclusion conditions.

4. The smart hospital management system based on the integration of clinical and scientific research according to claim 1 is characterized in that: The integrated clinical research platform also includes: A scientific research data management module, comprising: A project management unit, which is used to manage project progress, project members, project descriptions, and project attachments; An admission and exclusion patient management unit is used to manage the admission and exclusion patients according to the subject, and to update the patients who meet the admission conditions in real time according to the admission and exclusion condition data; A focus variable collection unit, which is used to automatically fill the variables after scientific research domain management into the data set; A scientific research form design unit is used to design and edit the case report form required for the scientific research project and to fill in the follow-up stage and follow-up content according to the research design.

5. The smart hospital management system based on the integration of clinical and scientific research according to claim 4 is characterized in that: The scientific research data management module also includes: A medical record display unit, which is used to display patient medical record data; The data query and export unit is used to support various logical queries and export multi-modal data such as patient dimension, time dimension, and medical consultation dimension.

6. The smart hospital management system based on the integration of clinical and scientific research according to claim 4 is characterized in that: The integrated clinical research platform also includes: A scientific research authority system management module, which includes: A user management unit, which is used to add new users and authorize them according to their identities; A data permission unit, which is used to provide different roles with browsing and searching permissions for hospital-level data, department-level data, and medical group-level data; A medical record anonymization unit, configured to anonymize medical records; The minimum authority setting unit is used to comply with the medical industry's ethical standards and information security standards and provide the required minimum data sets for different roles.

7. The smart hospital management system based on the integration of clinical and scientific research according to claim 1 is characterized in that: The regional decision application module includes: A hospital performance assessment submodule, which is used to analyze hospital district dimensions and time trend data on functional positioning indicators, quality and safety indicators, rational drug use indicators, resource efficiency indicators, revenue and expenditure structure indicators, and cost control indicators; An anti-tumor drug clinical application management submodule, which is used to analyze hospital-area dimensions and time trend data on anti-tumor drug usage indicators, anti-tumor drug usage amount indicators, and anti-tumor drug prescription rationality indicators; The tumor diagnosis and treatment analysis submodule is used to analyze hospital-area dimensions and time trend data on indicators such as outpatient visits, discharges, surgeries, anti-tumor drug treatments, and radiotherapy for patients with various types of cancer.

8. The smart hospital management system based on the integration of clinical and scientific research according to claim 1 is characterized in that: The regional collaborative application module includes: Multidisciplinary MDT system submodule, which is used to support multi-hospital MDT integration and view and reference the patient's current visit information and previous medical records; A two-way referral system submodule, which is used to support the integration of multi-hospital referral systems, including referral application, administrator review, department director review, referral acceptance, comprehensive referral query, and medical record sharing and retrieval; The scheduling system submodule is used to support multi-campus scheduling management and scheduling data sharing.

9. The smart hospital management system based on the integration of clinical and scientific research according to claim 8 is characterized in that: The multidisciplinary MDT system submodules include: MDT application unit, which is used to support the viewing and reference of the patient's current medical information and previous medical records; MDT medical record interconnection unit, which is used to support multi-dimensional query of case reports and panoramic view of patient diagnosis and treatment; Remote MDT unit, which is used to support authorization of a single hospital, open remote consultation application permissions, and invite medical alliance hospitals and experts within the permission to conduct MDT remote consultations; The consultation data integration unit is used to integrate document data and image data to form an independent MDT patient document library.

10. The smart hospital management system based on the integration of clinical and scientific research according to claim 1 is characterized in that: The regional multi-center online image integration module includes: A multi-center imaging cloud platform data acquisition submodule, which is used to collect DICOM imaging data from multiple hospital areas; A multi-center radiotherapy data acquisition submodule, which is used to acquire various types of radiotherapy DICOM data and DICOMRT data; The image data BI application submodule is used to perform statistical analysis on archived data, and supports graphic analysis, ratio analysis, trend analysis and comparative analysis.

Images