Auxiliary diagnosis and treatment artificial intelligence application evaluation framework and evaluation method

A technology of artificial intelligence and evaluation indicators, applied in the field of health technology evaluation, can solve the problems of lack of medical artificial intelligence evaluation models and methods

Pending Publication Date: 2021-09-14
国家卫生健康委卫生发展研究中心
0 Cites 2 Cited by

AI-Extracted Technical Summary

Problems solved by technology

Lack of specific medical AI ...
View more

Abstract

The invention discloses an auxiliary diagnosis and treatment artificial intelligence application evaluation framework and evaluation method, and relates to the technical field of health technology evaluation. The framework comprises an institution/facility/equipment layer, a process layer, a result layer and an application planning evaluation layer; wherein the mechanism/facility/equipment layer mainly considers three dimensions of technical safety effectiveness, technical accessibility and technical burdenability; the process layer mainly focuses on two dimensions of operation effectiveness and user satisfaction; the result layer mainly focuses on two dimensions of an individual result and a group result; and the application planning evaluation layer analyzes a policy influence layer, including influences on a supervision system, a medical insurance payment system, a health budget system and the like in China, and mainly pays attention to two dimensions of a process and a result. The framework is suitable for providing a product for diagnosis and treatment activities by a new-generation artificial intelligence technology, including but not limited to diagnosis and treatment decision, diagnosis and treatment execution, curative effect evaluation, dynamic optimization and process management.

Application Domain

Medical automated diagnosisHealthcare resources and facilities

Technology Topic

Diagnosis treatmentUser satisfaction +5

Image

  • Auxiliary diagnosis and treatment artificial intelligence application evaluation framework and evaluation method
  • Auxiliary diagnosis and treatment artificial intelligence application evaluation framework and evaluation method
  • Auxiliary diagnosis and treatment artificial intelligence application evaluation framework and evaluation method

Examples

  • Experimental program(1)

Example Embodiment

[0040] Next, the technical solutions in the embodiments of the present invention will be apparent from the embodiment of the present invention, and it is clearly described, and it is understood that the described embodiments are merely embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, there are all other embodiments obtained without making creative labor without making creative labor premises.
[0041] likefigure 1 As shown, the specific embodiment employing the auxiliary diagnosis and treatment of the auxiliary diagnosis and treatment in the present invention, including mechanism / facility / equipment layer, process layer, result layer, and application planning assessment layer; / Equipment layers are mainly three dimensions, technical accessibility, and technical aggressive; process layer, main attention to operation effectiveness and user satisfaction; result layer mainly pays attention to individual results and group results Two dimensions; application planning assessment layer analysis policy impact level, including the impact on my country's supervision system, medical insurance payment system, health budget system, mainly focusing on process and results.
[0042] The auxiliary diagnosis and treatment of the auxiliary diagnosis and treatment method according to the present embodiment is as follows:
[0043] The first step, formation assessment work group
[0044] The assessment work group consists of a number of fields of professionals, including artificial intelligence technologists, data scientists, hospital management experts, clinical experts, health public policy research experts, medical health consumers (patients), etc .;
[0045] Artificial intelligence technology experts, engaged in the research and development of artificial intelligence technology, it is best to have experience in participating in the research and development of intelligent public health management and diagnosis and treatment system, understanding health medical data standards; artificial intelligence experts can help assess the feasibility, reliability of the algorithm, Portability and efficiency, as well as the technical infrastructure of the product;
[0046] Data scientists, professional knowledge in the fields of statistics, machine learning, data mining, databases, and understanding health care business, to help assess the data set required for algorithm training, and which data can be used for assessment, and estimate the collection and handling required Workload, etc .;
[0047] Hospital management experts, engaged in the management of hospitals and medical health services. Such experts understand the use of intelligent public health management and medical management and medical management systems to people, wealth, things, information, time and other resources, to determine assessment indicators from the perspective of the management of hospitals and medical effects;
[0048] Clinical experts, long-term engage in clinical work, have clinical understanding and expertise, understand the needs of clinicians and challenges; and intelligent public health management and medical system expectations have almost improving clinical efficacy; therefore, clinicians participating It is possible to ensure that clinical assessment indicators make sense, will be the main determinants of the success and sustainability of this assessment;
[0049] Health policy research experts, rich in health policies research experience and health economics knowledge, understand the research progress of international public policy and my country's health service system, can help determine which assessments are reasonable and appropriate in terms of resource and approach;
[0050] Patients and people representatives, these are patients or their individuals, they can bring patient perspectives into the assessment team. Ideally, the patient representative should have influential and respected respect, which can better express medical consumers experience, and can share the first hand of the patient or caregiver; even if almost everyone can be a patient, but the most There is a dedicated patient representative, rather than ask other team members to represent multiple perspectives;
[0051] Step 2, describe the evaluation object
[0052] Description Evaluation Objects is a very important part of the assessment process, which determines the content and scope of the assessment; to collect descriptive documents as possible, form a descriptive report, including intelligent public health management and diagnosis and treatment system research and development background, demand, Expected effect, the resources required (such as time, talent, funds, equipment, data, etc.), logical model, technology use, various development phases (planning, implementation and effectiveness), applicable environment, applicable people, control technology Description, clinical results measurement, cost measurement, and other information, including relevant policies, guidelines, standard specifications, etc. After the reporting preliminary draft is reviewed by all stakeholders, the formal description report is finally generated;
[0053] The third step, the design evaluation plan
[0054] according to figure 2 image 3 Design assessment programs, schemes include evaluation purposes, select assessment indicators, user, use, methods, and protocols for evaluation results;
[0055] Clearly assess the purpose. Evaluate the purpose of determining based on the development phase of intelligent public health management and diagnosis and treatment system (demand, design, operation, maintenance, etc.) and application scenarios. For example, analyzing the main technical features of intelligent public health management and diagnosis and treatment system and clinical promotion application characteristics, providing decision-making evidence for decision-making, medical insurance payment methods and services.
[0056] Refine the assessment indicator, depending on the dimension and boundaries of the assessment. Write the assessment indicator set by reviewing the literature and brainstorming method. Through expert consultation law, understand which issues need to answer this assessment, and the priority of these issues, thereby surrounding the assessment framework;
[0057] The user of the evaluation results directly affect the focus of the assessment, and their participation makes the assessment personnel more clearly understand the expected use of the assessment, determine the priority of the goals and methods, and prevent the assessment results from the use.
[0058] Use refers to how to apply assessment information, closely related to the user of the evaluation results;
[0059] The evaluation method is based on the evaluation index, and the type, source, collection tool, data management, analysis, and method of data is determined. For example, the accuracy of intelligent public health management and diagnosis and treatment system can adopt an exam evaluation method, clinical effect analysis can pass system overview, patient satisfaction can pass expert scoring method or the like;
[0060] The agreement includes the duties of the distribution personnel, how to make full use of limited human, material, financial resources and other resources to implement assessment programs;
[0061] Step 4, collect evidence
[0062] In order to assess the product, the evidence collection table is made from the assessment indicator, source, quality, quantity, and acquisition mode, the quality of the assessment is improved;
[0063] Evidence includes product manual, product certification report, literature (from PubMed, Embase, The Cochranelibrary, China Biomedical Library, China Journal Full-text Database, Chinese Science and Technology Periodical Database, Wanfang Digital Journal Full-text Database and Domestic & Exam Health Technology Evaluation Unit Website) , Real-world evidence (electronic medical record, electronic health file), model related information (operating conditions and environment constraints, function description, design description, source code, etc.), training set related information (source, scale, label source, etc.). Technical acceptance, suitable sex, patient tendency, feasibility, and fairness. These evidence is obtained by literature review, questionnaire, expert consultation and other means;
[0064] Step 5, implement an assessment plan
[0065] Using the test evaluation method, expert scoring method, systematic review, etc., systematically assessing the clinical effect, cost effect, fairness, and impact on health systems, etc., and forms an evaluation report;
[0066] 1) Expert score method
[0067] Based on the characteristics of intelligent public health management and diagnosis and treatment system, the evaluation index is assigned to form a value-based scoring standard. Hiring a number of representative experts give the evaluation score of each item by this evaluation criteria with their own experience, and then set it;
[0068] 2) Exam evaluation method
[0069] The test evaluation method is used to measure the accuracy of intelligent public health management and diagnosis and treatment system. It is intended to draw a diagnosed medical record from the national medical center, thereby calculating the accuracy of intelligent public health management and diagnosis and treatment system;
[0070] 3) System review method
[0071] Using keywords to search for relevant literature, analysis, domestic and foreign intelligent public health management and medical applications, cost information, configuration, payment situation, clinical security and effectiveness, and health economics evaluation, etc.
[0072] Step 6, summarize the results of the assessment
[0073] The assessment team organizes multi-party meetings, explains the assessment results, and discusses, forms the final recommendation, generates the final formal assessment report, and ensure the sharing and use of the assessment results; a new round of evaluation is carried out according to the results of the assessment.
[0074] After the above structure, the beneficial effects of the present invention are as follows: This specific embodiment provides an auxiliary diagnosis and treatment of artificial intelligence application assessment framework and evaluation method, which is suitable for the "New Generation Artificial Intelligence Technology". Including, but not only limited to diagnosis, treatment, efficacy evaluation, dynamic optimization, and process management.
[0075] Although the present invention will be described in detail, the technical solution described in the foregoing embodiments may be modified, and the technical scheme described in the foregoing embodiments may be modified, or some technical features are still modified, or some technical features are equivalent. Within the spirit and principles of the invention, any modifications, equivalents, improvements, etc., should be included within the scope of the invention.

PUM

no PUM

Description & Claims & Application Information

We can also present the details of the Description, Claims and Application information to help users get a comprehensive understanding of the technical details of the patent, such as background art, summary of invention, brief description of drawings, description of embodiments, and other original content. On the other hand, users can also determine the specific scope of protection of the technology through the list of claims; as well as understand the changes in the life cycle of the technology with the presentation of the patent timeline. Login to view more.
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products