DRG-based payment settlement method

Abstract

The invention discloses a DRG-based payment and settlement method, relates to the technical field of medical payment and settlement, and forms a comprehensive payment and settlement system through integrating dynamic adjustment payment standards, intelligent diagnosis code correction, block chain technology guarantee payment transparency, patient health management performance pooling, cross-mechanism payment and settlement and other technologies. According to the invention, by designing a dynamic adjustment payment standard mechanism and introducing machine learning and data mining technologies, the function of automatically adjusting the payment amount according to medical process factors is realized, and the problem that the payment amount is static in a traditional payment settlement mode is solved. The problem that the payment amount is inaccurate and unfair due to the fact that illness conditions and treatment factors are not considered is solved, the medical service level is improved, and meanwhile the patient is promoted to better follow treatment and health management plans.

Description

Technical Field

[0001] The present invention relates to the technical field of medical payment and settlement, and in particular to a payment and settlement method based on DRG. Background Art

[0002] In the current medical payment system, the traditional payment by project and by disease often leads to uneven allocation of medical resources, uneven quality of patient treatment, excessive medical expenses, and increased pressure on medical insurance payment. In order to solve these problems, the DRG diagnosis-related group payment model has gradually become one of the reform directions of medical insurance and medical payment worldwide. The DRG model divides patients into different groups based on factors such as the patient's diagnosis, treatment methods, and complexity of the disease, and settles according to the average cost of each group. This method can effectively control medical costs and encourage medical institutions to improve treatment efficiency.

[0003] However, the traditional DRG payment method still has some limitations. For example, the payment standard is fixed and fails to fully consider factors such as individual differences among patients, treatment effects, and different performances of hospitals. Therefore, this application proposes a payment and settlement method based on DRG, which gradually overcomes the shortcomings of the traditional DRG payment and settlement model by introducing dynamic adjustment mechanisms, intelligent diagnostic coding corrections, and blockchain technology to ensure payment transparency, and achieves more accurate and fair medical payment settlement. This can not only promote the improvement of the quality of medical services, but also optimize the allocation of medical resources, effectively reduce the burden on the medical insurance system, and promote the sustainable development of the medical system.

[0004] Application document CN118469720A discloses a basic medical insurance fund payment method and system. The above patent optimizes the basic medical insurance fund payment method to apply to qualified medical institutions that provide inpatient services, but the above patent cannot realize the function of automatically adjusting the payment amount according to medical process factors.

[0005] Application document CN116364258A discloses a DRG-based polling grouping method and system. The above patent can help relevant personnel quickly and intuitively discover problems, locate problems, and solve problems in a timely manner, thereby avoiding losses and preventing manual review from missing erroneous medical records / settlement lists due to human negligence. However, the above patent cannot realize the function of automatically extracting and correcting diagnostic codes.

[0006] Application document CN115440351A discloses a method for evaluating and predicting the rationality of DRG benchmark point correction based on CC big data. The above patent achieves the improvement of the interpretability of the rationality evaluation method of the DRG benchmark point correction system, and provides a reference correction benchmark with practical significance for optimizing the benchmark point correction and differential settlement related specific measures in the DRG medical insurance payment system, which is conducive to improving the rationality of the settlement function algorithm of the medical insurance computer management system. However, the above patent cannot realize the transparency, traceability and non-tamperability of settlement data.

[0007] Application document CN114461616A discloses a CHS-DRG data quality management system. The above patent facilitates DRG payment pricing so as to meet the requirements of regional medical insurance funds paying according to DRG as soon as possible, but the above patent cannot realize data sharing and intercommunication functions between different institutions.

[0008] In summary, the above patents cannot realize the functions of automatically adjusting the payment amount according to medical process factors, automatically extracting and correcting the diagnosis code, making the settlement data transparent, traceable and tamper-proof, and sharing and communicating data between different institutions, resulting in the problems of opaque payment and settlement data, low payment and settlement efficiency, unfair payment and settlement, and unavailable payment and settlement information; To this end, this application proposes a DRG-based payment settlement method that can realize the functions of automatically adjusting the payment amount according to medical process factors, automatically extracting and correcting diagnostic codes, making the settlement data transparent, traceable and tamper-proof, and sharing and interoperating data between different institutions. Summary of the invention

[0009] The purpose of the present invention is to provide a payment settlement method based on DRG to solve the technical problems proposed in the above-mentioned background technology that the functions of automatically adjusting the payment amount according to medical process factors, automatically extracting and correcting diagnosis codes, making settlement data transparent, traceable and tamper-proof, and sharing and communicating data between different institutions cannot be realized, resulting in opaque payment and settlement data, low payment and settlement efficiency, unfair payment and settlement, and lack of payment and settlement information.

[0010] To achieve the above object, the present invention provides the following technical solution: a payment settlement method based on DRG, the payment settlement method comprising the following steps: S1. Determine the initial payment amount based on the DRG payment model according to the patient's treatment process; S2. Introduce a dynamic adjustment mechanism to dynamically adjust the payment amount based on influencing factors; S3, using machine learning algorithms and big data analysis technology to optimize the payment settlement model in real time and automatically adjust the payment amount; S4. Use blockchain technology to record data on the payment and settlement process, and use smart contracts to automatically execute payment and settlement; S5, automatically correct the patient's diagnosis code based on the intelligent diagnosis coding system; S6. Introduce the patient's treatment participation and health management data, combine the patient's physiological indicators and treatment compliance, dynamically evaluate the patient's treatment effect, and adjust the payment amount based on the treatment performance; S7. Provide a cross-institutional payment and settlement platform to support data sharing and payment settlement among different medical institutions; S8. After payment is settled, the adaptive payment feedback system will be used to automatically feedback the settlement results based on the actual treatment effect and the quality of service provided by the hospital, and the payment standards will be revised through the data feedback mechanism to ensure that the payment amount is reasonable and fair.

[0011] Preferably, the dynamic adjustment mechanism further comprises: Automatically adjust payment amounts based on real-time assessment of the complexity of the patient's condition, diagnosis category, treatment method, and comorbidities to reflect the patient's treatment difficulty and needs; Dynamically adjust payment amounts based on the quality of care indicators provided by the hospital and the patient's recovery, and reward hospitals that provide high-quality care; Adjust the payment amount based on the patient's treatment compliance and health management to encourage patients' active treatment participation.

[0012] Preferably, the intelligent diagnostic coding system comprises: Use natural language processing technology to automatically extract diagnostic information from patients' electronic medical records and identify and correct inaccurate diagnostic data; Use machine learning algorithms to automatically infer the most appropriate DRG code based on historical data and actual treatment records, and make recommendations and corrections; Automatically generate standardized codes based on patients' treatment and surgical records, medication use data, and clinical diagnosis to ensure coding consistency and accuracy.

[0013] Preferably, the blockchain technology is used for: All payment settlement transactions are encrypted and payment information and diagnostic data are recorded in the blockchain to ensure the immutability, transparency and traceability of payment data; Smart contracts are used to automatically execute payment settlements. Smart contracts automatically calculate the payment amount according to payment rules, execute settlements and transfers, reducing manual intervention; Through the distributed ledger of blockchain, the consistency and sharing of payment settlement information across institutions can be ensured, ensuring that all relevant parties can obtain accurate settlement information in a timely manner.

[0014] Preferably, the adaptive payment feedback system includes: A data analysis module that evaluates payment rationality in real time and generates feedback reports based on hospital treatment quality, patient recovery, and payment amount; Automatically generate payment optimization suggestions after settlement and automatically adjust payment standards based on feedback results to improve the accuracy and fairness of the payment settlement model; Optimize payment standards through long-term data accumulation, and adjust future payment strategies based on trends and changes in historical data.

[0015] Preferably, the payment settlement process further includes: Generate settlement list through automated data processing module based on patient's electronic medical record, diagnosis information, treatment record and patient's health data; Send the settlement list to the hospital and medical insurance agency for review, and determine the payment amount based on the preset payment rules and adjustment mechanism; Once the payment amount is confirmed, the payment is automatically executed through the blockchain smart contract, the funds are transferred to the hospital account, and a settlement result notification is sent to the patient.

[0016] Preferably, the cross-institution payment and settlement platform includes: A distributed data platform based on cloud computing supports the sharing of diagnosis and treatment information and payment data among multiple medical institutions; A unified data interface enables data intercommunication between different hospitals and medical insurance institutions, simplifies the payment and settlement process, and improves settlement efficiency; Through the data mapping function of the distributed data platform based on cloud computing, the payment standards and coding systems adopted by different medical institutions and insurance companies are automatically converted to ensure the consistency and accuracy of settlement information.

[0017] Preferably, the payment settlement method further includes: Based on the patient's treatment compliance, follow-up records and health monitoring data, AI technology is used to evaluate the patient's treatment effect; Adjust payment amounts based on the difference between expected and actual patient outcomes to ensure long-term effectiveness of patient health management; Introduce patient health data tracking, adjust payment amounts and treatment plans in real time, and encourage patients to participate in health management.

[0018] Preferably, the payment amount in the payment settlement process includes: The payment amount is calculated through a dynamic payment standard adjustment formula based on the patient's diagnosis and treatment type, ensuring that the payment amount reflects the difficulty of treatment and the patient's needs; Linking multi-dimensional data on hospital treatment quality, treatment efficiency, and patient health management with the patient's payment settlement information to form a personalized payment standard; Evaluate the performance of hospitals and doctors, and adjust payment amounts and methods based on the quality of medical services provided by the hospitals.

[0019] Preferably, the intelligent diagnosis coding system further comprises: Automatically detect and correct errors and inconsistencies in diagnostic coding, using rule-based models and data validation mechanisms to improve coding accuracy; During multiple diagnosis and treatment processes, the diagnosis code is automatically updated and adjusted based on the patient's health data and treatment effects to ensure that settlement payments are accurately calculated based on the latest treatment data; Through cross-validation technology, the patient's medical records and diagnostic information are ensured to be consistent across different medical institutions and payment systems, avoiding payment disputes caused by inconsistent data.

[0020] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention is designed with a mechanism for dynamically adjusting payment standards. By introducing machine learning and data mining technology, the function of automatically adjusting the payment amount according to medical process factors is realized. This solves the problem that the payment amount in the traditional payment settlement model is static and the payment amount is inaccurate and unfair due to the failure to consider the condition and treatment factors. This improves the level of medical services and encourages patients to better follow treatment and health management plans. 2. The present invention realizes the function of automatically extracting and correcting diagnostic codes by designing an intelligent diagnostic code correction system, solves the problems of errors, omissions and irregularities in manual input, improves the accuracy of diagnostic codes, avoids payment disputes caused by manual coding errors, and improves settlement accuracy and efficiency; 3. The present invention uses blockchain technology to encrypt, store, manage and execute settlement data, thus achieving transparency, traceability and non-tamperability of settlement data, solving the problem of irregular risks in traditional payment and settlement systems, improving the transparency and trust of the payment process, reducing medical fraud, ensuring the safety of medical insurance funds, and enhancing the confidence of hospitals and patients in the payment and settlement system; 4. The present invention realizes data sharing and intercommunication functions among different institutions by designing a cross-institutional payment and settlement platform, solves the problem of barriers to data interaction in traditional payment and settlement systems, optimizes the payment and settlement process, improves payment and settlement efficiency, reduces information islands, promotes collaboration between medical institutions and medical insurance institutions, and enhances the accuracy and timeliness of payment and settlement. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1It is a schematic diagram of the payment settlement process of the present invention. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] See also Figure 1 , an embodiment of the present invention provides: a payment settlement method based on DRG, the payment settlement method comprising the following steps: S1. Determine the initial payment amount based on the DRG payment model according to the patient's treatment process; S2. Introduce a dynamic adjustment mechanism to dynamically adjust the payment amount based on influencing factors; S3, using machine learning algorithms and big data analysis technology to optimize the payment settlement model in real time and automatically adjust the payment amount; S4. Use blockchain technology to record data on the payment and settlement process, and use smart contracts to automatically execute payment and settlement; S5, automatically correct the patient's diagnosis code based on the intelligent diagnosis coding system; S6. Introduce the patient's treatment participation and health management data, combine the patient's physiological indicators and treatment compliance, dynamically evaluate the patient's treatment effect, and adjust the payment amount based on the treatment performance; S7. Provide a cross-institutional payment and settlement platform to support data sharing and payment settlement among different medical institutions; S8. After payment is settled, the adaptive payment feedback system will automatically feedback the settlement results based on the actual treatment effect and the quality of service provided by the hospital, and the payment standards will be revised through the data feedback mechanism to ensure that the payment amount is reasonable and fair; Furthermore, by integrating technologies such as dynamic adjustment of payment standards, intelligent diagnosis coding correction, blockchain technology to ensure payment transparency, patient health management performance linkage, and cross-institutional payment settlement, a comprehensive payment and settlement system is formed. When patients receive diagnosis and treatment in hospitals, medical information such as diagnosis, treatment, examination, and surgery is uploaded to the payment and settlement system in real time through the electronic medical record system. The payment and settlement system uses the diagnosis-related group DRG model to assign patients to corresponding DRG groups based on the patient's main diagnosis, treatment methods, complications, and other data. The system preliminarily calculates the payment amount based on the patient's DRG group and the hospital's medical insurance payment policy. The DRG-based payment settlement model introduces data streams in multiple dimensions, including the complexity of the patient's condition, i.e. the complexity of diagnosis-related groups, the quality of hospital treatment, i.e. the comparison between treatment results and standards, the patient's treatment compliance, i.e. timely follow-up visits, and treatment records. All data are processed in real time through a machine learning algorithm to establish a multi-level weight model to dynamically adjust the payment amount.

[0024] See also Figure 1 , an embodiment of the present invention provides: a payment settlement method based on DRG, the dynamic adjustment mechanism further includes: Automatically adjust payment amounts based on real-time assessment of the complexity of the patient's condition, diagnosis category, treatment method, and comorbidities to reflect the patient's treatment difficulty and needs; Dynamically adjust payment amounts based on the quality of care indicators provided by the hospital and the patient's recovery, and reward hospitals that provide high-quality care; Adjust payment amounts based on patient treatment compliance and health management to encourage active treatment participation; Furthermore, the system not only preliminarily calculates the payment amount based on the DRG group, but also adjusts the payment amount based on real-time data; for example, when the patient has multiple complications or special treatment needs, the payment amount will be dynamically adjusted through the machine learning model. The system will use the random forest model to evaluate the difficulty of treatment and adjust the payment amount based on factors such as the complexity of the patient's condition and treatment plan; the hospital's treatment quality will also affect the payment amount. For example, hospitals with high surgical success rates can get more payment amounts. The system uses a regression analysis model to evaluate hospital performance based on the hospital's historical treatment data, such as postoperative infection rates and complication rates, and adjusts the payment amount accordingly; health management is an important factor in dynamic payment adjustment. The system collects patients' health data, such as follow-up records, drug compliance, etc., and optimizes the payment amount through reinforcement learning algorithms. If the patient complies with the health management plan, the system automatically increases the payment amount, otherwise it decreases.

[0025] See also Figure 1 , an embodiment of the present invention provides: a payment settlement method based on DRG, the intelligent diagnosis coding system includes: Use natural language processing technology to automatically extract diagnostic information from patients' electronic medical records and identify and correct inaccurate diagnostic data; Use machine learning algorithms to automatically infer the most appropriate DRG code based on historical data and actual treatment records, and make recommendations and corrections; Automatically generate standardized codes based on patients' treatment and surgical records, drug use data, and clinical diagnosis to ensure coding consistency and accuracy; The intelligent diagnostic coding system further comprises: Automatically detect and correct errors and inconsistencies in diagnostic coding, using rule-based models and data validation mechanisms to improve coding accuracy; During multiple diagnosis and treatment processes, the diagnosis code is automatically updated and adjusted based on the patient's health data and treatment effects to ensure that settlement payments are accurately calculated based on the latest treatment data; Through cross-validation technology, the patient's medical records and diagnostic information are ensured to be consistent across different medical institutions and payment systems, thus avoiding payment disputes caused by inconsistent data. Furthermore, the system extracts diagnostic information from the patient's medical records through natural language processing technology. The system automatically identifies keywords entered by doctors in medical records, such as disease names, symptoms, test results, etc., and maps them to standard ICD-10 diagnostic codes. When the system detects inconsistencies between diagnostic information and codes, it prompts the doctor to make corrections. For example, if the diagnosis of a complex disease is not correctly coded, the system will automatically provide suggestions, prompt possible correct codes, and continuously optimize the accuracy of the suggestions through machine learning models. Through the decision tree algorithm, the system can quickly identify incorrect coding inputs. If the diagnostic description does not match the treatment measures, or the code is used improperly, the system will automatically mark it and ask the doctor to check and modify it; The intelligent diagnostic coding system can automatically identify and correct diagnostic codes based on the doctor's input using a deep neural network DNN model. The system can handle complex terms and disease names in doctors' medical records and automatically recommend the correct ICD-10 code through a trained DNN model. As new diseases or treatments emerge, the system will continuously optimize the coding rules through incremental learning. The DNN model will regularly learn new medical knowledge and update the new information into the coding system to ensure that it always complies with the latest medical standards and practices.

[0026] See also Figure 1 , an embodiment provided by the present invention: a payment settlement method based on DRG, wherein the blockchain technology is used for: All payment settlement transactions are encrypted and payment information and diagnostic data are recorded in the blockchain to ensure the immutability, transparency and traceability of payment data; Smart contracts are used to automatically execute payment settlements. Smart contracts automatically calculate the payment amount according to payment rules, execute settlements and transfers, reducing manual intervention; Through the distributed ledger of blockchain, the consistency and sharing of payment and settlement information across institutions are ensured, ensuring that all relevant parties can obtain accurate settlement information in a timely manner; The payment amount in the payment settlement process includes: The payment amount is calculated through a dynamic payment standard adjustment formula based on the patient's diagnosis and treatment type, ensuring that the payment amount reflects the difficulty of treatment and the patient's needs; Linking multi-dimensional data on hospital treatment quality, treatment efficiency, and patient health management with the patient's payment settlement information to form a personalized payment standard; Evaluate the performance of hospitals and doctors and adjust the payment amount and payment method according to the quality of medical services provided by the hospital; Furthermore, all payment settlement-related data such as diagnosis information, payment amount, hospital information, etc. are stored on the blockchain through public-private key encryption technology. Each settlement operation, such as payment amount confirmation, will generate a new block and add it to the blockchain to ensure that the data cannot be tampered with; when the payment amount is confirmed, the system executes automatic payment through the smart contract in the blockchain. Smart contracts automatically trigger fund transfers based on preset rules such as payment amount calculation formulas and payment objects, without the need for human intervention, to ensure the accuracy and transparency of the payment process; all payment records are stored in the blockchain and have timestamps, and anyone can query payment records to ensure the transparency and traceability of the payment process. If a payment dispute occurs, the relevant parties can consult the records on the blockchain at any time to resolve the dispute; The system will calculate the payment amount through a weighted average model based on factors such as the DRG group, complexity of the patient's condition, hospital performance, and treatment effectiveness. For example, if the patient's treatment process is complicated, the system will increase the payment amount based on the disease complexity model; if the hospital's treatment quality is high, the payment amount will also increase accordingly; the system will also make adjustments through a machine learning model based on the patient's health management status and behavior, such as whether they have follow-up visits on time and whether they comply with the drug treatment plan, to ensure that the payment amount is linked to the patient's health management results.

[0027] See also Figure 1 , an embodiment of the present invention provides: a payment settlement method based on DRG, the payment settlement process further includes: Generate settlement list through automated data processing module based on patient's electronic medical record, diagnosis information, treatment record and patient's health data; Send the settlement list to the hospital and medical insurance agency for review, and determine the payment amount based on the preset payment rules and adjustment mechanism; Once the payment amount is confirmed, the payment is automatically executed through the blockchain smart contract, the funds are transferred to the hospital account, and a settlement result notification is sent to the patient; The cross-institution payment and settlement platform includes: A distributed data platform based on cloud computing supports the sharing of diagnosis and treatment information and payment data among multiple medical institutions; A unified data interface enables data intercommunication between different hospitals and medical insurance institutions, simplifies the payment and settlement process, and improves settlement efficiency; Through the data mapping function of the distributed data platform based on cloud computing, the payment standards and coding systems adopted by different medical institutions and insurance companies are automatically converted to ensure the consistency and accuracy of settlement information; The adaptive payment feedback system comprises: A data analysis module that evaluates payment rationality in real time and generates feedback reports based on hospital treatment quality, patient recovery, and payment amount; Automatically generate payment optimization suggestions after settlement and automatically adjust payment standards based on feedback results to improve the accuracy and fairness of the payment settlement model; Optimize payment standards through long-term data accumulation, and adjust future payment strategies based on trends and changes in historical data; Furthermore, during the settlement process, the system will automatically generate a settlement list based on the patient's medical information, including diagnosis, treatment, and drug use. The settlement list includes the patient's diagnostic information, treatment plan, drug use, surgical records, cost details, etc.; the system submits the settlement list to the hospital and medical insurance agency for review. The hospital and medical insurance agency verify it through the system's built-in rule engine. The rule engine checks the correctness of the settlement list based on standardized payment rules, such as medical insurance payment standards, DRG group payment standards, etc. If there are any inconsistencies, the system will mark and prompt the relevant parties to make corrections; after the review is completed, the settlement amount is automatically paid through a smart contract. The payment amount will be transferred directly to the hospital account through an encrypted payment channel, and the patient will also receive a settlement result notification; The cross-institutional payment and settlement platform uses RESTful API to achieve data exchange, ensuring smooth data exchange between different hospitals and medical insurance institutions. Each hospital and medical insurance institution serves as a node, and the platform ensures data consistency and real-time updates between different nodes; all payment settlement data in the platform, such as DRG groups, diagnosis codes, payment amounts, etc., use a unified standard format, such as HL7 or FHIR standards. The system converts payment data from different hospitals into a unified format through the ETL process to ensure seamless data connection across institutions; After payment is settled, the system will collect and analyze settlement data. Through data mining techniques such as clustering algorithms, multi-dimensional analysis of payment amounts, patient treatment effects, hospital treatment quality, etc. is performed to identify abnormal data in settlements; the system will compare historical data with existing settlement data and use regression analysis models to evaluate the rationality of payment amounts. If certain payment amounts are abnormally high or low, the system will automatically mark them and generate optimization suggestions; the system will adjust payment strategies and optimize payment standards based on the analysis results. For example, if the payment amount for a certain type of disease is found to be too low, the system will make adjustment suggestions to increase the payment amount; if a certain type of treatment is not effective, the system will reduce the payment amount.

[0028] See also Figure 1 , an embodiment of the present invention provides: a payment settlement method based on DRG, the payment settlement method further comprising: Based on the patient's treatment compliance, follow-up records and health monitoring data, AI technology is used to evaluate the patient's treatment effect; Adjust payment amounts based on the difference between expected and actual patient outcomes to ensure long-term effectiveness of patient health management; Introduce patient health data tracking, adjust payment amounts and treatment plans in real time, and encourage patients to participate in health management; Furthermore, the patient's health management data is monitored in real time through smart wearable devices such as bracelets and smart watches. The data monitored by the equipment, such as psychology, blood sugar, and number of steps, will be uploaded to the health management platform through the Internet of Things technology. The system evaluates the relationship between the patient's health status and the payment amount through health data analysis models such as regression analysis models. If the patient is in good health, such as taking medicine on time and regular follow-up visits, the payment amount will increase accordingly; if the patient does not follow the health management plan, the payment amount may decrease.

[0029] Working principle: The DRG-based payment and settlement method relies on a large amount of data in the medical service process, including the patient's diagnosis and treatment information, treatment methods, and hospital performance. First, when the patient receives treatment in the hospital, medical information such as diagnosis, surgery, treatment plan, and drug use are uploaded to the payment and settlement system in real time through the electronic medical record system. The system uses the DRG grouping algorithm based on the patient's medical record data to assign the patient to the corresponding DRG group, and identifies the complexity of the patient's condition, the difficulty of treatment, etc. By integrating all relevant patient data including medical history, treatment, examination, and surgery into the payment and settlement platform, the system lays the foundation for subsequent payment calculations and adjustments; Once the patient's treatment information is sorted out, the system calculates the initial payment amount for the patient based on the DRG group. The payment amount is not only related to the DRG group, but also affected by factors such as the patient's health status, treatment quality, and hospital performance. On this basis, the payment settlement method introduces a dynamic adjustment mechanism to adjust the payment amount in real time. This mechanism takes into account factors in multiple dimensions, such as the hospital's treatment quality, the patient's health management, and the complexity of the patient's condition. Through machine learning and data mining technology, the system can dynamically adjust the payment amount based on treatment effects, patient health data, etc., to ensure the fairness and rationality of payment settlement; In order to ensure the transparency and credibility of the payment and settlement process, this method introduces blockchain technology. The payment and settlement data is encrypted, stored and managed through the blockchain to ensure that the data cannot be tampered with. Each settlement operation will generate a block and be permanently recorded in the blockchain. The relevant parties can query the historical settlement data at any time to ensure the transparency and traceability of the payment process. In addition, the cross-institutional payment and settlement platform realizes data sharing and interaction between different hospitals and medical insurance institutions through standardized data interfaces, ensuring the smoothness and consistency of payment and settlement between different institutions.

[0030] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A payment settlement method based on DRG, characterized by: The payment settlement method comprises the following steps: S1. Determine the initial payment amount based on the DRG payment model according to the patient's treatment process; S2. Introduce a dynamic adjustment mechanism to dynamically adjust the payment amount based on influencing factors; S3, using machine learning algorithms and big data analysis technology to optimize the payment settlement model in real time and automatically adjust the payment amount; S4. Use blockchain technology to record data on the payment and settlement process, and use smart contracts to automatically execute payment and settlement; S5, automatically correct the patient's diagnosis code based on the intelligent diagnosis coding system; S6. Introduce the patient's treatment participation and health management data, combine the patient's physiological indicators and treatment compliance, dynamically evaluate the patient's treatment effect, and adjust the payment amount based on the treatment performance; S7. Provide a cross-institutional payment and settlement platform to support data sharing and payment settlement among different medical institutions; S8. After payment is settled, the adaptive payment feedback system will be used to automatically feedback the settlement results based on the actual treatment effect and the quality of service provided by the hospital, and the payment standards will be revised through the data feedback mechanism to ensure that the payment amount is reasonable and fair.

2. A DRG-based payment settlement method according to claim 1, characterized in that: The dynamic adjustment mechanism further includes: Automatically adjust payment amounts based on real-time assessment of the complexity of the patient's condition, diagnosis category, treatment method, and comorbidities to reflect the patient's treatment difficulty and needs; Dynamically adjust payment amounts based on the quality of care indicators provided by the hospital and the patient's recovery, and reward hospitals that provide high-quality care; Adjust the payment amount based on the patient's treatment compliance and health management to encourage patients' active treatment participation.

3. A DRG-based payment settlement method according to claim 1, characterized in that: The intelligent diagnostic coding system comprises: Use natural language processing technology to automatically extract diagnostic information from patients' electronic medical records and identify and correct inaccurate diagnostic data; Use machine learning algorithms to automatically infer the most appropriate DRG code based on historical data and actual treatment records, and make recommendations and corrections; Automatically generate standardized codes based on patients' treatment and surgical records, medication use data, and clinical diagnosis to ensure coding consistency and accuracy.

4. A DRG-based payment settlement method according to claim 1, characterized in that: The blockchain technology is used to: All payment settlement transactions are encrypted and payment information and diagnostic data are recorded in the blockchain to ensure the immutability, transparency and traceability of payment data; Smart contracts are used to automatically execute payment settlements. Smart contracts automatically calculate the payment amount according to payment rules, execute settlements and transfers, reducing manual intervention; Through the distributed ledger of blockchain, the consistency and sharing of payment settlement information across institutions can be ensured, ensuring that all relevant parties can obtain accurate settlement information in a timely manner.

5. A DRG-based payment settlement method according to claim 1, characterized in that: The adaptive payment feedback system comprises: A data analysis module that evaluates payment rationality in real time and generates feedback reports based on hospital treatment quality, patient recovery, and payment amount; Automatically generate payment optimization suggestions after settlement and automatically adjust payment standards based on feedback results to improve the accuracy and fairness of the payment settlement model; Optimize payment standards through long-term data accumulation, and adjust future payment strategies based on trends and changes in historical data.

6. A DRG-based payment settlement method according to claim 1, characterized in that: The payment settlement process further includes: Generate settlement list through automated data processing module based on patient's electronic medical record, diagnosis information, treatment record and patient's health data; Send the settlement list to the hospital and medical insurance agency for review, and determine the payment amount based on the preset payment rules and adjustment mechanism; Once the payment amount is confirmed, the payment is automatically executed through the blockchain smart contract, the funds are transferred to the hospital account, and a settlement result notification is sent to the patient.

7. A DRG-based payment settlement method according to claim 1, characterized in that: The cross-institution payment and settlement platform includes: A distributed data platform based on cloud computing supports the sharing of diagnosis and treatment information and payment data among multiple medical institutions; A unified data interface enables data intercommunication between different hospitals and medical insurance institutions, simplifies the payment and settlement process, and improves settlement efficiency; Through the data mapping function of the distributed data platform based on cloud computing, the payment standards and coding systems adopted by different medical institutions and insurance companies are automatically converted to ensure the consistency and accuracy of settlement information.

8. A DRG-based payment settlement method according to claim 1, characterized in that: The payment settlement method also includes: Based on the patient's treatment compliance, follow-up records and health monitoring data, AI technology is used to evaluate the patient's treatment effect; Adjust payment amounts based on the difference between expected and actual patient outcomes to ensure long-term effectiveness of patient health management; Introduce patient health data tracking, adjust payment amounts and treatment plans in real time, and encourage patients to participate in health management.

9. A DRG-based payment settlement method according to claim 1, characterized in that: The payment amount in the payment settlement process includes: The payment amount is calculated through a dynamic payment standard adjustment formula based on the patient's diagnosis and treatment type, ensuring that the payment amount reflects the difficulty of treatment and the patient's needs; Linking multi-dimensional data on hospital treatment quality, treatment efficiency, and patient health management with the patient's payment settlement information to form a personalized payment standard; Evaluate the performance of hospitals and doctors, and adjust payment amounts and methods based on the quality of medical services provided by the hospitals.

10. A DRG-based payment settlement method according to claim 1, characterized in that: The intelligent diagnostic coding system further comprises: Automatically detect and correct errors and inconsistencies in diagnostic coding, using rule-based models and data validation mechanisms to improve coding accuracy; During multiple diagnosis and treatment processes, the diagnosis code is automatically updated and adjusted based on the patient's health data and treatment effects to ensure that settlement payments are accurately calculated based on the latest treatment data; Through cross-validation technology, the patient's medical records and diagnostic information are ensured to be consistent across different medical institutions and payment systems, avoiding payment disputes caused by inconsistent data.

Images