Therapeutic effect driven medical performance and payment system based on active medical economics and DIKWP semantic modeling

Abstract

The invention provides a curative effect driving type medical performance and payment system oriented to active medical treatment. Active medical economics and DIKWP (data / information / knowledge / wisdom / intention) five-layer semantic modeling are fused. The system semantically converts diagnosis and treatment behaviors into a semantic bill, constructs a target chain by taking a patient purpose as a core, continuously tracks causal contribution of each content unit to a curative effect, and quantifies a doctor service value by a semantic value increment; therefore, payment according to effects and remuneration according to effects are realized through a fair payment engine, medical insurance and an intelligent contract are compatible, and automatic settlement and dispute arbitration are realized. The system can be used for internet hospitals, chronic disease management and medical insurance payment reform, the medical quality, transparency and fund efficiency are improved, and supervision and policy optimization are supported.

Description

Technical Field

[0001] This invention relates to the fields of medical informatics and medical payment management, and in particular to a efficacy-driven medical performance and payment system that combines the concepts of proactive medical economics with DIKWP (Data, Information, Knowledge, Wisdom, Purpose) five-layer semantic modeling. This system aims to serve proactive healthcare scenarios, achieving refined evaluation of medical service performance and equitable payment settlement through semantic modeling and efficacy tracking. Background Technology

[0002] This invention provides a efficacy-driven medical performance and payment system based on proactive medical economics and DIKWP semantic modeling to address the aforementioned technical problems. The system breaks down medical behavior into five semantic content units: data, information, knowledge, wisdom, and intent. It tracks the effect of each semantic unit on the patient's recovery goals, quantifies the doctor's service contribution, and performs fair payment settlement accordingly. Specific technical innovations include:

[0003] DIKWP Semantic Modeling of Medical Practices: This approach maps medical behaviors such as consultation records, examination results, diagnoses, medication regimens, and rehabilitation suggestions into five semantic output layers: Data (D), Information (I), Knowledge (K), Wisdom (W), and Purpose (P), forming a structured "semantic bill." Each medical service item is broken down and labeled within the semantic bill. For example, when a patient complains of "chest tightness," the system generates the following semantic entries: Layer D records pain intensity of 5 / 10; Layer I records that symptoms worsen with activity; Layer K identifies possible myocardial ischemia; Layer W provides recommendations for further examination based on risk factors; and Layer P corresponds to preventing myocardial infarction and alleviating symptoms. In this way, every consultation, explanation, and treatment is transformed into standardized semantic content units, achieving semantic expression and interpretable recording of medical behaviors.

[0004] Patient Recovery Path and Semantic Goal Chain: The system explicitly models the patient's health intentions as Purpose nodes, constructing a target recovery path for the patient. It tracks the causal links of each semantic intervention provided by the doctor in achieving that goal. For example, in chronic disease management, the system uses the patient's long-term health goal (such as "blood pressure controlled below 130 / 80") as a P-level semantic node, linking various interventions in the medical process (lifestyle recommendations, medication adjustments, follow-up monitoring, etc.) to this goal, forming a semantic "goal chain." Each medication, examination, or intervention clearly corresponds to its specific health goal, and the system can assess in real time whether the efficacy is progressing towards the goal. Through causal link analysis, the system can identify which content positively contributes to goal achievement and which may be ineffective or require adjustment, truly achieving a patient-centered, closed-loop diagnosis and treatment system.

[0005] The Semantic Performance Calculation Module introduces a "semantic value increment" metric to measure the contribution of physician services. This metric quantifies the value created by each service content based on the impact of semantic content on patient recovery and its match with individual patient needs. The system evaluates the gain of each DIKWP unit in achieving the goal through semantic tensor operations: for example, the value increment of an important knowledge output (K layer, such as correct diagnosis and medication) in improving efficacy will be higher than that of general health advice (W layer) or simple data recording (D layer). By elevating raw medical data into an interpretable and actionable semantic structure, and consistently embedding its representative meaning (I / K layer), reasoning path (W layer), and service goal (P layer), the system realizes the semantic transformation and value gain of medical information from data to knowledge to intent. This module quantitatively evaluates the "semantic value" of physician services, providing an objective basis for performance evaluation.

[0006] Fair Payment Engine: Establishing a equitable payment and settlement mechanism for all parties. For patients, payment is based on the personalized value contribution of the semantic content they actually receive to their health goals, avoiding paying for ineffective or redundant services. For doctors, performance-based compensation is settled according to the effectiveness of their treatment content within the patient's recovery pathway, encouraging doctors to provide appropriate and effective services rather than over-treatment. This engine can be understood as a "semantic pricing" mechanism: the fees paid by patients directly correspond to the effective content required to achieve their recovery goals, while doctors' income depends on the actual role their content units play in the semantic goal chain. Through this two-way incentive, the system balances the interests of all parties in healthcare, promoting the rational and efficient allocation of medical resources.

[0007] Support for Medical Insurance and Smart Contract Interfaces: The system of this invention is compatible with the existing medical insurance system, capable of mapping semantic content units to correspondences with the national medical insurance catalog, clinical pathway standards, etc., achieving recognition and coverage of medical insurance payments. Simultaneously, the system reserves a smart contract interface, which can automatically execute settlement and dispute resolution based on preset rules or efficacy achievement. For example, when a patient achieves the expected recovery goal or treatment effect indicator, the smart contract automatically triggers medical insurance payment or commercial insurance claim payment; if the efficacy does not meet the standard, the cost-sharing ratio is adjusted according to the agreement. This mechanism improves the transparency and efficiency of the payment process and facilitates supervision of medical service quality by regulatory authorities and payers. In the event of a dispute, the semantic bills and efficacy data recorded by the smart contract can serve as objective evidence to assist in the adjudication. In summary, by integrating with medical insurance and blockchain technology, the system realizes a trustworthy and automated medical payment environment.

[0008] Figure 1Semantic Performance Billing Model Diagram: This system records the medical services provided by doctors according to the DIKWP five-layer semantic structure, generating a semantic performance bill. The example in the diagram illustrates how various semantic contents provided by a doctor during a consultation are mapped to five levels: Data (D), Information (I), Knowledge (K), Wisdom (W), and Intent (P), forming structured bill entries. Each level of content is assigned a clear semantic label, facilitating subsequent calculation of its contribution to patient recovery. The semantic bill intuitively presents "what was done" and "why it was done" in this consultation: for example, the D layer displays the collected objective indicators, the I layer displays the doctor's explanation of the condition, the K layer represents the diagnosis and application of medical knowledge, the W layer represents personalized decisions or plans, and the P layer is linked to the patient's goals for this consultation. Patients and payers can clearly understand the content and value of their payment based on this bill.

[0009] Figure 2 A semantic goal chain diagram of the patient rehabilitation pathway: This diagram depicts the causal link between the patient's health goal (Purpose) and various semantic content units. In the example scenario, the patient's goal is to "achieve target blood pressure control" (P-level node). Around this goal, the doctor provides a series of interventions: including data-level blood pressure monitoring (D), information-level explanation of the causes of hypertension and risk communication (I), knowledge-level medication adjustment plans (K), and wisdom-level lifestyle management suggestions (W). These interventions, through the semantic link, progressively point to the patient's ultimate goal, establishing a clear connection between each item and "what effect to achieve." The system evaluates efficacy by tracking the state changes of each node on the link: for example, the improvement in blood pressure data (D-level), combined with the patient's understanding of information (I-level), medication regimen implementation (K-level), and lifestyle changes (W-level), jointly determine the progress of achieving the patient's goal (P). The semantic goal chain provides a structured representation of the complex rehabilitation process, ensuring that all diagnostic and treatment behaviors revolve around a shared rehabilitation intention.

[0010] Figure 3Smart Pricing Settlement Flowchart: This flowchart illustrates the interaction process between patients, doctors, medical insurance / insurance companies, and the settlement engine in this invention's system. First, the doctor provides DIKWP semantic content services to the patient through their treatment (arrow ①), which the system records in the semantic bill and assesses its value. Then, in the settlement phase, the patient pays the fee through the settlement engine based on the received valid semantic content value (arrow ②), and medical insurance or commercial insurance automatically reimburses the portion eligible for reimbursement through a smart interface according to policy (arrow ③). The settlement engine aggregates the semantic value increment, calculates the doctor's performance-based compensation, and pays the corresponding amount to the doctor (arrow ④). The entire process is supported by smart contract technology, ensuring automatic payment or refund when preset conditions (such as efficacy indicators) are met, and storing all semantic bills and efficacy data on the blockchain for verification by all parties. This mechanism realizes dynamic pricing of fund flow and medical value output: patients "pay for results," doctors "receive compensation based on results," and medical insurance funds are used more efficiently.

[0011] In summary, this invention's system creatively provides a efficacy-centered performance evaluation and payment model by closely linking medical services with patient outcomes through semantic modeling. Unlike traditional fee-for-service or disease-group-based payments, this system focuses on "how much health benefit each medical service actually brings," thereby guiding medical practices towards optimizing efficacy and patient satisfaction. The system has the following beneficial effects:

[0012] Improving the quality and efficiency of healthcare: Doctors' diagnostic and treatment processes are more focused on patients' actual needs, reducing redundant and unnecessary interventions and increasing the proportion of effective medical services. Studies have shown that the introduction of the DIKWP model significantly improves patients' health goal achievement rates and enhances patient compliance. Simultaneously, the system monitors efficacy data in real time, facilitating timely optimization of treatment plans and improving overall healthcare quality.

[0013] Promoting doctor-patient collaboration and trust: Semantic billing allows patients to clearly understand the treatment content and expected results associated with each expense, greatly improving medical transparency and reducing patient doubts about the reasonableness of costs. Patients shift from passively receiving treatment to actively participating in goal management. Collaboration between doctors and patients around shared goals helps build trust. Doctors, because their contributions are objectively recognized and rewarded, are more willing to invest time and effort in improving service quality, achieving a win-win situation for both doctors and patients.

[0014] Ensuring the rational use of medical insurance funds: Through a value-driven payment mechanism, medical insurance funds will prioritize payments for services that truly contribute to patient recovery, preventing resources from being wasted on inefficient or ineffective projects. This will improve the cost-effectiveness of medical insurance fund utilization and promote the development of the healthcare system towards "value-based healthcare." Simultaneously, smart contract-based automated claims processing and review functions can reduce manual review costs and decrease insurance fraud and disputes.

[0015] Supporting Policy Making and Regulation: The semantic performance data accumulated by the system can provide a basis for optimizing medical insurance payment policies and clinical pathways. Regulatory authorities can use this data to more accurately assess the performance of hospitals and doctors, intervene in a timely manner in cases of over-treatment or under-treatment, and formulate more scientific payment standards and incentive mechanisms.

[0016] This invention's medical performance and payment system adheres to the principles of proactive medical economics, utilizing DIKWP semantic modeling to deeply link medical behavior with patient outcomes, achieving digital measurement of medical value and precise matching of financial flows. It provides a feasible path for medical payment reform in the new era, possessing significant clinical application value and socio-economic benefits. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the semantic performance billing model structure.

[0018] Figure 2 This is a semantic target chain diagram of the patient's rehabilitation pathway.

[0019] Figure 3 This is a flowchart of the intelligent pricing and settlement process. Detailed Implementation

[0020] The specific embodiments of the present invention will be further described below with reference to the accompanying drawings. It should be understood that the following embodiments are only for illustrating the present invention and not for limiting the present invention; without departing from the spirit and substance of the present invention, those skilled in the art can make equivalent modifications or substitutions, all of which fall within the protection scope of the present invention.

[0021] I. System Overall Architecture

[0022] The efficacy-driven medical performance and payment system of this invention (hereinafter referred to as the "System") adopts a distributed microservice architecture, consisting of a front-end interaction layer, a business service layer, an intelligent algorithm layer, a settlement and compliance module, and data and blockchain infrastructure. Figures 1-3 The system includes at least:

[0023] The Semantic Modeling Module (DIKWP Engine) extracts and generates five semantic units—Data (D), Information (I), Knowledge (K), Wisdom (W), and Purpose (P)—from structured / unstructured medical data, forming a "semantic bill." It supports multi-source access from EMR / EHR, follow-up, wearable devices, imaging examinations, and online consultations, and provides standard mappings for HL7 FHIR, ICD-10 / 11, LOINC, and ATC.

[0024] Outcome Tracker: Centered on patient health goals, it constructs a "semantic goal chain" graph model to track the causal and temporal contributions of each DIKWP unit to goal achievement.

[0025] The Semantic Performance Calculator module (Value Calculator) evaluates the marginal contribution of each semantic unit to the objective, generates an interpretable record of "value increments," and aggregates them by doctor / team / institution.

[0026] The Settlement Engine dynamically balances the settlement of patients on a "pay-for-performance" basis with the performance-based settlement of doctors, and supports automatic execution of medical insurance / commercial insurance interfaces and smart contracts.

[0027] Compliance and Security Module: Access Control, Data Masking, Audit Logs, Explainable Reports, and Regulatory Reports.

[0028] Data and on-chain infrastructure: transaction database, time series database, graph database, data lake and consortium blockchain / national cryptographic smart contract network.

[0029] II. Data Structure and Generation Process of Semantic Bills

[0030] Semantic Billing Entries (SBI) must include at least: patient / visit metadata, five semantic units of DIKWP, evidence pointers (lab reports, images, guideline entries), responsible person's signature and version number, and observation windows and resource consumption estimates for billing and evaluation.

[0031] The generation process includes: data access → semantic extraction and standardization → target binding → quality control → database entry and on-chain notarization. Entries that fail verification will undergo manual review.

[0032] III. Modeling and Maintenance of the Patient's "Semantic Target Chain"

[0033] Nodes: Objective (P), Decision / Treatment (K), Individualized Plan (W), Explanation and Risk Communication (I), Observational Data (D).

[0034] Relationships: support, inhibition, necessary prerequisite, evidence association, etc.

[0035] Attributes: Status, deadline, responsible person, priority, importance weight, etc.

[0036] Maintenance strategy: When a new entry arrives, it is placed in the relevant subgraph based on the time window and semantic similarity and the weight is updated; relations that exceed the observation window and do not show positive effects are downweighted or marked as "inefficient"; when the target is adjusted, the relevant priorities are automatically recalculated.

[0037] IV. Measurement and Aggregation of Value Increment

[0038] The system defines "value increment" as: in the current diagnostic and treatment context, the positive increase in the "probability of achieving" a patient's specific goal by a certain semantic unit, taking into account the following factors:

[0039] Goal importance: Ranked by clinical pathway or patient preference;

[0040] Individual fit: taking into account population stratification, contraindications, compliance, and accessibility;

[0041] Timeliness: The earlier and more critical the decision or measure, the higher its weight.

[0042] Causal contribution: Supervised evaluation and expert rules are used to correct for confounding effects.

[0043] Evaluation process: Data preparation → Causal correction → Contribution assessment → Stability check (including interval confidence and anomaly detection) → Accounting.

[0044] Aggregation principle: Within the same medical visit, the team's contribution is additively distributed using a fair allocation method; across cycles, it is naturally summarized in descending order over time to generate a multi-dimensional performance vector and visualization report for doctors / departments / institutions.

[0045] V. Fair Payment Engine and Smart Contract Execution

[0046] Pricing benchmark: Establish benchmark price vectors and upper and lower limits, and co-payment rules for various targets;

[0047] Patient billing: The value increment of each target is summarized on a periodic basis and priced accordingly. A "protective belt" is set up for compliant and necessary but unachieved expenditures to avoid adverse incentives.

[0048] Doctor settlement: Performance bonuses are distributed based on the increased value after allocation;

[0049] Reinsurance and Corrective Measures: Utilize reinsurance pools and anomaly exclusion rules for rare events and uncontrollable risks;

[0050] Smart contracts: Automatic claims / payments, difference adjustments, and on-chain arbitration under trigger conditions such as target achievement, end of observation window, and approval.

[0051] VI. Typical Application Process (Taking Hypertension Management as an Example)

[0052] Target setting: For example, control the average household blood pressure to below a specified threshold within 12 weeks, and set weights and observation windows.

[0053] Initial consultation: collect baseline blood pressure and laboratory indicators; complete risk communication; develop initial medication and lifestyle prescriptions; systematically record corresponding value increments and observation windows.

[0054] Follow-up: Collect family blood pressure curves and adjust treatment and follow-up plans accordingly; the system continuously updates the target chain and value increments.

[0055] Settlement: After the observation window ends, the consideration settlement and performance clearing are carried out based on the achievement of the objectives, and an interpretable evidence package is generated.

[0056] Quality closed loop: Inefficient processes are recorded as an improvement list and fed back into the rule base.

[0057] VII. Medical Insurance / Commercial Insurance Interface and Standard Mapping

[0058] Semantic units such as K / W / D are coded and mapped to medical service items, consumables / drugs, and test categories; during the review, scores are given from two dimensions: "necessity" and "target contribution," and items with low contribution and low necessity are automatically reduced or rejected for compensation; after discharge or the observation period ends, a second settlement or incentive / refund is carried out, and "semantic performance bill," "target chain contribution graph," and "therapeutic efficacy evidence package" are output.

[0059] VIII. Terminal Form and Interaction

[0060] Doctor's side: Semantic billing editor, target chain visualization, real-time contribution prompts, best practices and medication warnings.

[0061] For patients: Goal-centered to-do and progress boards, adherence tracking, cost-benefit comparison, informed consent, and privacy controls.

[0062] Payer / Regulator: Population segmentation dashboard, institution / department comparison, rule backtesting sandbox, and workflow for random auditing of suspicious points.

[0063] IX. Security, Privacy and Explainability

[0064] Implement the principle of minimum necessity and multi-level desensitization; ensure full-chain traceability, with each settlement result corresponding to a specific semantic unit, evidence, and responsible person; model governance includes data versioning, drift monitoring, and a closed loop of manual confirmation.

[0065] 10. Optional Embodiments and Variations

[0066] Offline / edge deployment: Value increments are evaluated at the grassroots level through local lightweight models and periodically recorded on the blockchain;

[0067] Specialized disease center model: adopts multi-level target trees and shares representations for scenarios such as oncology and heart failure;

[0068] Population fit: In pediatric / gerontology settings, compliance and caregiving ability are incorporated into the fit, and the observation window and guideline evidence level are adjusted.

[0069] XI. Computer Implementation

[0070] This invention also provides a computer device and storage medium: the processor executes storage instructions to complete semantic modeling, target tracking, value assessment, and settlement processes. The device can be a physical server, cloud host, or edge gateway, and the medium can be ROM, RAM, disk, or optical disk, etc.

[0071] Internet hospital scenario

[0072] In internet hospitals (online medical service platforms), this invention's system effectively improves the quality and transparency of online medical services. Because doctors and patients don't meet in person, internet hospitals often suffer from insufficient standardization of treatment procedures and difficulty in monitoring medical quality. With this system, all doctor-patient interactions during online consultations are structurally recorded using a semantic model, forming a clear semantic record and target chain. On one hand, after receiving treatment through the online platform, patients immediately receive a semantic performance record detailing the doctor's suggestions and explanations (I-layer, W-layer), diagnostic and medication decisions made (K-layer), and the expected therapeutic goals for these services (P-layer). This clarity enhances patients' trust in online treatment and compensates for the information asymmetry inherent in virtual clinics. On the other hand, hospital administrators and regulatory bodies can monitor the semantic record and efficacy data in real time, ensuring that online treatments are compliant and focused on efficacy. When a patient's condition changes and requires in-person consultation, the system's accumulated semantic medical records can seamlessly connect to the offline hospital, improving the efficiency of continuous treatment. In terms of commercial value, internet hospitals can leverage this system to create a unique "pay-for-performance" service, attracting more patients to use online healthcare. Simultaneously, by improving the quality of diagnosis and treatment and patient satisfaction, the platform's reputation and user stickiness will be significantly enhanced. In terms of social value, this scenario helps to solve the trust problem in online healthcare, ensuring that internet-based diagnosis and treatment are of "consistent quality and effectiveness," allowing patients to enjoy high-quality, responsible medical services from home.

[0073] Chronic disease management platform scenario

[0074] Chronic disease management requires long-term, continuous medical intervention and patient self-management. The application of this invention's system in a chronic disease management platform will change the traditional model of "patients passively seeking medical treatment and intermittent follow-ups," establishing a new paradigm of proactive, goal-oriented health management. Taking chronic diseases such as diabetes and hypertension as examples, the platform establishes a DIKWP semantic health profile for each patient, dynamically integrating medical institution diagnostic and treatment data with the patient's daily life data, and continuously tracking the achievement of the patient's health goals (such as blood glucose control goals and blood pressure targets). During each follow-up visit or remote visit, doctors use the system to understand the patient's data changes (D layer) and symptom information (I layer) since the last visit, and combine this with a medical knowledge base to determine the current disease progression (K layer), adjusting treatment plans or lifestyle guidance accordingly (W layer). All decisions are automatically linked to the established health goals (P layer). The system calculates the semantic value increment of each intervention, such as how much HbA1c is expected to decrease further and the probability of avoiding complications, and feeds this information back to the doctor and patient. This quantification makes patients more willing to follow medical advice and cooperate with management because they understand the significance of each step to the ultimate goal, thus significantly enhancing patient compliance. For doctors and health management teams, semantic performance indicators can help identify which interventions are most effective and which patients need more attention, thereby optimizing resource allocation. In terms of commercial value, chronic disease management platforms can use this system to demonstrate the tangible improvements in health indicators brought about by their management services to insurance companies or medical insurance departments, thereby obtaining service revenue based on performance (e.g., insurance companies pay management institutions for improvements in patients' health indicators). At the same time, platform user stickiness increases, and chronic disease patients are more inclined to stay on a platform that allows them to continuously improve their health, forming a virtuous cycle. In terms of social value, large-scale promotion of this scenario will increase the rate of chronic disease target achievement, reduce the incidence of complications and hospitalization rates, save huge sums of money for the medical system, improve the quality of life of people with chronic diseases, and contribute to the realization of the "Healthy China" goal.

[0075] Medical insurance payment system scenario

[0076] This invention's system can also serve as a powerful tool for reforming medical insurance payment methods, applicable to payment and settlement systems for national medical insurance or commercial health insurance. Currently, medical insurance funds face the dual challenges of improving efficiency and controlling unreasonable expenditures. Ensuring that every penny of medical insurance funds is used for effective treatment is a core focus of medical insurance payment reform. This system provides a refined solution through semantic modeling: the medical insurance system can perform semantic analysis on each electronic medical record / bill uploaded by the hospital, identifying each diagnostic and treatment item and its corresponding expected therapeutic goals, and assessing its necessity and value accordingly. For example, the medical insurance system can determine, based on the semantic bill, whether a patient's multiple imaging examinations (D-level content) are necessary to achieve the diagnosis, and whether the use of certain high-value consumables (K-level content) truly contributes to improving the patient's prognosis (P-level goal), thereby rejecting payment for redundant and inefficient items and prioritizing payment for key therapeutic processes. Simultaneously, for medical institutions using this system, medical insurance can implement a new model of settlement based on therapeutic efficacy: that is, after discharge, based on the patient's actual recovery and goal achievement, further settlement of expenses or bonus / penalty payments with the hospital will be conducted. This efficacy-based payment incentive will encourage hospitals to improve quality and avoid the profit-driven tendency of simply charging for each item, helping medical institutions shift from "competing on projects" to "competing on results." Technically, the system's reserved smart contract interface can connect to the medical insurance settlement platform to achieve automatic claims and settlement: when a patient completes the prescribed treatment goals or meets the indicators, the smart contract triggers the corresponding payment to the hospital; if the goals are not met, the fees are adjusted according to the agreement. This not only reduces cumbersome manual review and improves settlement efficiency but also avoids disputes, achieving "clear efficacy and clear responsibility." In terms of commercial value, insurance companies can use this system to develop innovative insurance products based on health outcomes (such as managed health insurance and insurance products bundled with chronic disease services), determining payouts based on the actual health improvement of the insured, thus reducing risk expenditures. For medical insurance regulatory departments, the data and analysis tools provided by this system can be used for refined fund management, plugging loopholes, and improving fund utilization. In terms of social value, this scenario will drive medical insurance payments from extensive to intensive, truly implementing the "patient-centered" medical service concept: patients will receive higher quality medical security, doctors and hospitals will receive reasonable returns for high-quality services, medical insurance funds will achieve sustainable operation, and the entire medical ecosystem will develop in a more equitable and efficient direction.

[0077] In summary, the efficacy-driven medical performance and payment system based on proactive medical economics and DIKWP semantic modeling demonstrates significant application potential across various scenarios. Through technological innovation, it addresses the core demands of both the supply side and payers of healthcare services: enabling the scientific evaluation and representation of the value of medical services, truly realizing the initial goal of "paying for health through medical care." Commercially, the system creates new value-sharing models for medical institutions and payers, fostering new business models and cooperation opportunities based on efficacy-based payment. Socially, it is expected to improve doctor-patient relationships, enhance medical efficiency, reduce unnecessary medical expenditures, and facilitate a profound transformation of the healthcare system from "quantity-driven" to "quality-driven." It is foreseeable that the system proposed in this invention will become an important tool for medical performance management and medical insurance payment reform, possessing broad application prospects and profound social significance.

Claims

1. A treatment efficacy-driven medical performance and payment system, designed for proactive healthcare scenarios, comprising a semantic modeling module, a treatment efficacy tracking module, a performance calculation module, and a payment engine, characterized in that: The system models medical behaviors according to five layers of semantic service content, and performs performance evaluation and payment allocation based on the contribution of semantic content to the patient's rehabilitation goals.

2. The system according to claim 1, wherein the semantic modeling module decomposes medical behavior into five layers of semantic output: data, information, knowledge, wisdom, and intention, maps each medical service provided by the doctor to a corresponding DIKWP semantic unit and generates a structured semantic bill.

3. The system according to claim 1, wherein the efficacy tracking module models the patient's rehabilitation goals as Purpose semantic nodes and constructs a semantic goal chain to track the causal link of each semantic content unit to the realization of the rehabilitation goal, and evaluates the effect of each content unit in the closed loop of the patient's rehabilitation path.

4. The system according to claim 1, wherein the performance calculation module introduces the "semantic value increment" indicator, which quantifies the value contribution of the services provided by the doctor based on the influence of the semantic content unit on the patient's rehabilitation and its matching degree with the individual needs of the patient, and stores the value in association with the corresponding content unit for performance evaluation.

5. The system according to claim 1, wherein the payment engine includes a patient-side payment submodule and a doctor-side settlement submodule: the patient-side payment submodule calculates the fee payable by the patient based on the personalized value contribution of the semantic content unit received by the patient; the doctor-side settlement submodule calculates the doctor's performance compensation based on the effectiveness of the semantic content provided by the doctor in the patient's rehabilitation goal chain, thereby achieving a dynamic balance between patient payment and doctor performance.

6. The system according to claim 1, wherein the system further supports medical insurance and smart contract interfaces: characterized in that... It is compatible with the medical insurance payment catalog, mapping semantic content units to medical insurance reimbursement items; and through the smart contract module, it automatically executes medical insurance reimbursement, expense settlement and arbitration of medical disputes based on preset rules or the achievement of treatment effects, ensuring the fairness, transparency and efficiency of the payment process.

Images