Hospital DRG and DIP management information system based on artificial intelligence

Abstract

The invention relates to the technical field of medical informatization, and discloses a hospital DRG and DIP management information system based on artificial intelligence, which comprises an intelligent grouping module, a payment rate calculation module, a performance evaluation module and a data security module. The intelligent grouping module analyzes medical records, medication and inspection data by using a DeepSeek algorithm, automatically completes DRG / DIP grouping and generates a medical record combination report; the payment rate calculation module predicts the proportion of cost composition and payment through machine learning based on historical cost and settlement information, and automatically generates a payment standard capable of being dynamically adjusted; the performance evaluation module evaluates the efficiency and quality of departments or disease categories in a multi-dimensional manner, and provides a visual report to assist resource configuration optimization; the data security module guarantees the security of diagnosis and treatment data by adopting an encryption technology and authority management. The system is designed in a modularized mode, and data can be extracted from the HIS and the LIS and integrated to a unified platform. The method has the advantage that intelligent analysis and management of diagnosis and treatment data are realized by using a deep learning algorithm.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of medical informatization, in particular to a hospital DRG and DIP management information system based on artificial intelligence. BACKGROUND

[0002] With the deepening of the reform of the national medical insurance payment method, DRG and DIP have become the core medical insurance payment tools. Hospitals urgently need to analyze, classify and evaluate patient diagnosis and treatment data through efficient information means to optimize resource allocation, improve operational efficiency and ensure the accuracy of medical insurance settlement.

[0003] However, the traditional DRG / DIP management system faces significant technical bottlenecks: on the one hand, its data processing capacity is limited, and it is difficult to quickly integrate multi-source heterogeneous data from hospital information management systems (HIS), laboratory information management systems (LIS) and other systems, resulting in a prominent data island problem and affecting grouping accuracy; on the other hand, grouping and payment rate calculation are highly dependent on manual intervention, not only inefficient, but also prone to medical insurance settlement errors due to human judgment errors, and lack of intelligent performance evaluation functions, which cannot provide scientific decision support for management, restricting the improvement of hospital fine management level. Therefore, developing a new system with intelligent data processing, accurate grouping calculation and dynamic performance evaluation capabilities has become an urgent need in the industry. SUMMARY

[0004] To solve the above problems, the application proposes a hospital DRG and DIP management information system based on artificial intelligence that uses deep learning algorithms to realize intelligent analysis and management of diagnosis and treatment data.

[0005] To solve the above technical problems, the technical solution proposed by the application is: a hospital DRG and DIP management information system based on artificial intelligence, including an intelligent grouping module, a payment rate calculation module, a performance evaluation module and a data security and privacy protection module:

[0006] The intelligent grouping module is used to analyze the medical records, medication, examination and diagnosis data of patients through a deep learning algorithm, automatically complete the intelligent grouping of DRG / DIP, and generate a case combination report according to the complexity of the patient's condition and resource consumption;

[0007] The payment rate calculation module is used to predict the cost composition and payment proportion of patients based on historical medical insurance settlement data using a machine learning algorithm, automatically generate the payment standard of DRG / DIP, and support dynamic adjustment;

[0008] The performance evaluation module is used to evaluate the resource use efficiency and medical quality of each department or disease type in the hospital in multiple dimensions, and provide a visual analysis report;

[0009] The data security and privacy protection module is used to adopt data encryption technology and strict permission management mechanism to ensure the security of patient diagnosis and treatment data.

[0010] Preferably, the deep learning algorithm used in the intelligent grouping module is DeepSeek deep learning algorithm.

[0011] Preferably, the diagnosis and treatment data analyzed by the intelligent grouping module includes patient medical record data, medication data and examination data.

[0012] Preferably, the historical medical insurance settlement data on which the payment rate calculation module is based include the cost information and settlement information of past patients.

[0013] Preferably, the visual analysis report provided by the performance evaluation module can help the management optimize resource allocation and improve operation efficiency.

[0014] Preferably, the system function adopts modular design, which is convenient for docking with other medical information systems.

[0015] Preferably, the system can extract patient diagnosis and treatment data from HIS, LIS platform and integrate into a unified data platform.

[0016] Compared with the prior art, the present application has the following advantages:

[0017] The present application significantly improves the hospital DRG / DIP management efficiency through artificial intelligence technology. In terms of data processing, the system supports real-time integration of multi-source heterogeneous data, and can integrate HIS, LIS and other platform data with an efficiency improvement of more than 80%, and completely breaks the data island. The intelligent grouping module based on DeepSeek algorithm improves the DRG / DIP grouping accuracy from 60%-70% of the traditional system to more than 90%, greatly reducing the cost of manual review. The payment rate calculation module dynamically predicts the cost composition and payment proportion through machine learning, with a prediction error rate of less than 5%, and supports real-time policy response. The performance evaluation module makes use of multi-dimensional visual analysis to improve the decision-making efficiency of the management layer by more than 90%, and improves the balance of department resource allocation by 30%-50%. In terms of data security, the system adopts national secret level encryption and hierarchical permission management, and guarantees patient privacy throughout the whole process. Overall, the system realizes the leap from "experience-driven" to "data-intelligent-driven", significantly improves the medical insurance settlement efficiency and the level of hospital fine management, and has social value and economic benefit. DETAILED DESCRIPTION

[0018] Example 1

[0019] After a certain third-grade class-A hospital introduces the system, the management is upgraded through the following processes:

[0020] First, in the data collection phase, the system automatically extracts patients' electronic medical records, test reports, medication records, and other multi-dimensional data from HIS, LIS, and other platforms, cleans and integrates them into a unified data platform through ETL technology, and builds a standardized diagnosis and treatment data set to lay the foundation for subsequent analysis.

[0021] Second, in the intelligent grouping phase, the DeepSeek algorithm performs natural language processing and feature extraction on standardized medical record data, identifies key grouping factors such as diagnosis codes, surgical operations, and complications, automatically completes DRG / DIP grouping according to clinical pathway rules, and generates case combination reports based on treatment duration, consumable usage, and other data to clearly present the resource consumption levels of different cases.

[0022] In the payment rate calculation phase, the system retrieves medical insurance settlement data from the past three years, uses a random forest algorithm to establish a cost prediction model, analyzes the correlation between factors such as age, disease, and treatment method and cost, generates the payment proportion and standard for each DRG / DIP group, and updates in real-time according to medical insurance policy adjustment rules to ensure the timeliness and accuracy of the settlement standard.

[0023] In the performance evaluation phase, the system analyzes indicators from both department and disease dimensions, such as average length of stay, drug proportion, and clinical pathway completion rate, and visualizes the resource use efficiency ranking of each department and the quality trend of each disease through a dashboard to assist management in developing targeted improvement plans.

[0024] The application effect shows that the DRG / DIP grouping accuracy of the hospital has increased from 65% to 95%, the average time for medical insurance settlement has been shortened from 5 days to 3 days, and the resource allocation balance between departments has been improved by 40%, significantly improving the efficiency of medical insurance management.

[0025] Example 2

[0026] A certain secondary hospital carried out management optimization for acute myocardial infarction:

[0027] The system first conducted in-depth analysis on the diagnosis and treatment data of the past 100 patients with this disease, identified cases with the main diagnosis code I21.0 through the intelligent grouping module, divided them into subgroups according to treatment methods, and generated case combination reports for each subgroup to reveal the resource consumption differences of different treatment schemes.

[0028] The payment rate calculation module established a cost prediction model based on historical settlement data of similar hospitals for this disease, found that the average hospitalization cost of the intervention treatment group was 80,000 yuan, the payment proportion was 70%, the average cost of the drug treatment group was 40,000 yuan, and the payment proportion was 85%, and accordingly generated a differentiated payment standard report for this disease, providing a basis for hospital cost control.

[0029] The performance evaluation module analyzes the medical quality dimensions, and the re-hospitalization rate of the intervention treatment group is 5%, lower than the 12% of the drug treatment group, but the consumable proportion is as high as 55%, far beyond the reasonable range; the system combines with the clinical guidelines to put forward optimization suggestions, such as promoting domestic replacement consumables to reduce costs, and at the same time, strengthening postoperative rehabilitation guidance to further reduce the re-hospitalization rate.

[0030] Through three months of intervention, the average hospitalization cost of this disease is reduced by 12%, the consumable proportion is reduced to 48%, and the re-hospitalization rate is reduced to 8%, realizing the double improvement of quality and efficiency.

[0031] Embodiment 3

[0032] A regional medical center is under the jurisdiction of three branch hospitals, and after introducing the system, cross-hospital area DRG / DIP collaborative management is realized:

[0033] In the data layer, the system collects HIS, LIS data of each branch hospital in real time through unified data interface standards, automatically identifies the hospital area label and constructs a cross-hospital area data set, solving the problem of data dispersion and difficulty in horizontal comparison of traditional systems. The intelligent grouping module analyzes the diagnosis and treatment data of the same disease in the three branch hospitals, and finds that the grouping accuracy of A hospital is 88%, B hospital is 75%, and C hospital is 92%, the difference mainly comes from the standard degree of medical record writing.

[0034] The payment rate calculation module establishes a cross-hospital area cost mean model based on the regional overall medical insurance settlement data, and finds that the average payment rate of the pneumonia disease in A hospital is 78%, in B hospital is 82%, and in C hospital is 75%, the system automatically generates payment standard adjustment suggestions for each hospital area, promoting the fairness of the use of regional medical insurance funds.

[0035] The performance evaluation module constructs a cross-hospital area index board, compares the key indicators of each hospital area, and finds that the CMI value of B hospital is 0.92, lower than the regional mean value 1.05, indicating that the difficult case treatment capacity is insufficient; the system suggests B hospital to strengthen the cooperation with the core hospital in the referral, and provides a reference for the diagnosis and treatment path of typical cases, and three months later, its CMI value is improved to 1.01, and the coordination efficiency of regional medical resources is significantly enhanced.

[0036] The above merely describes the preferred specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and any skilled person in the art can make equivalent replacements or changes to the technical solutions and inventive concepts of the present application within the technical range disclosed by the present application, which should be covered within the protection scope of the present application.

Claims

1. A hospital DRG and DIP management information system based on artificial intelligence, characterized in that, It includes a smart grouping module, a payment rate calculation module, a performance evaluation module, and a data security and privacy protection module: The intelligent grouping module is used to analyze patients' medical records, medications, examination and treatment data through deep learning algorithms, automatically complete intelligent grouping of DRG / DIP, and generate case combination reports based on the complexity of the patient's condition and resource consumption. The payment rate calculation module is used to predict the patient's cost structure and payment ratio based on historical medical insurance settlement data and using machine learning algorithms, automatically generate DRG / DIP payment standards, and support dynamic adjustment; The performance evaluation module is used to evaluate the resource utilization efficiency and medical quality of various departments or diseases in the hospital from multiple dimensions, and provides a visual analysis report. The data security and privacy protection module employs data encryption technology and a strict access control mechanism to ensure the security of patient medical data.

2. The hospital DRG and DIP management information system based on artificial intelligence according to claim 1, characterized in that: The deep learning algorithm used in the intelligent grouping module is the DeepSeek deep learning algorithm.

3. The hospital DRG and DIP management information system based on artificial intelligence according to claim 1, characterized in that: The diagnostic and treatment data analyzed by the intelligent grouping module includes the patient's medical records, medication data, and examination data.

4. The hospital DRG and DIP management information system based on artificial intelligence according to claim 1, characterized in that: The payment rate calculation module is based on historical medical insurance settlement data, including past patient cost information and settlement information.

5. The hospital DRG and DIP management information system based on artificial intelligence according to claim 1, characterized in that: The performance evaluation module provides visual analysis reports that help management optimize resource allocation and improve operational efficiency.

6. The hospital DRG and DIP management information system based on artificial intelligence according to claim 1, characterized in that: The system adopts a modular design, which facilitates integration with other medical information systems.

7. The hospital DRG and DIP management information system based on artificial intelligence according to claim 1, characterized in that: The system can extract patient diagnosis and treatment data from HIS and LIS platforms and integrate them into a unified data platform.