| 孙凤,章萌,詹思延.基于深度循证医学理念构建新一代循证决策生态系统[J].Chinese journal of Epidemiology,2024,45(8):1164-1170 |
| 基于深度循证医学理念构建新一代循证决策生态系统 |
| Construction of a new generation of evidence-based decision-making ecosystem based on the concept of deep evidence-based medicine |
| Received:April 27, 2024 |
| DOI：10.3760/cma.j.cn112338-20240427-00224 |
| KeyWord: 深度循证医学 循证决策生态系统 证据整合 随机对照试验 |
| English Key Word: Deep evidence-based medicine Evidence-based decision ecosystem Evidence integration Randomized controlled trials |
| FundProject:国家自然科学基金（72074011） |
| Author Name | Affiliation | E-mail | | Sun Feng | Department of Epidemiology and Biostatistics, School of Public Health, Peking University, Beijing 100191, China
Key Laboratory of Epidemiology of Major Diseases (Peking University), Ministry of Education, Beijing 100191, China
Peking University Center for Evidence-based Medical and Clinical Research, Beijing 100191, China
Xinjiang Medical University, Urumqi 830017, China | | | Zhang Meng | Department of Epidemiology and Biostatistics, School of Public Health, Peking University, Beijing 100191, China
Key Laboratory of Epidemiology of Major Diseases (Peking University), Ministry of Education, Beijing 100191, China
Peking University Center for Evidence-based Medical and Clinical Research, Beijing 100191, China | | | Zhan Siyan | Department of Epidemiology and Biostatistics, School of Public Health, Peking University, Beijing 100191, China
Key Laboratory of Epidemiology of Major Diseases (Peking University), Ministry of Education, Beijing 100191, China
Peking University Center for Evidence-based Medical and Clinical Research, Beijing 100191, China
Clinical Epidemiology Research Center, Peking University Third Hospital, Beijing 100191, China | siyan-zhan@bjmu.edu.cn |
|
| Hits: 1016 |
| Download times: 294 |
| Abstract: |
| 传统循证医学在医疗实践和卫生决策中发挥了重要作用，与此同时也不断暴露出证据生成效率低、覆盖范围窄、整合策略不完善等不足，难以及时服务临床诊疗及监管决策，因此亟须根据前沿技术的发展，对循证医学理念进行深入拓展和完善。2023年提出的深度循证医学倡导运用最新人工智能和自然语言处理技术，全面扩大证据的广度、深度和可整合性，提高证据生产和整合效率。基于深度循证医学理念建立新一代循证决策生态系统具有广阔的实际应用前景，可推动循证医学证据检索、生产、整合、传播、转化和应用等各环节的发展，深入挖掘影像学、多组学和真实世界数据，增大真实世界证据的利用潜力，建立动态文献管理平台和决策辅助工具，减少资源浪费，促进证据流动。借助此系统有助于获取以个体为中心的临床综合证据进行精准决策，并在人才培养、循证教学改革、科普宣传等方面发挥重大作用，最终推动同一健康的实现。 |
| English Abstract: |
| Traditional evidence-based medicine has been essential in medical practice and health decision-making. However, it has also continuously exposed shortcomings such as low efficiency in evidence generation, narrow scope of coverage, and imperfect integration strategies, making it challenging to serve clinical diagnosis and treatment and regulatory decision-making. Therefore, it is urgent to adapt to the development of cutting-edge technology and to expand and improve the concept of evidence-based medicine. Deep evidence-based medicine proposed in 2023 aims to advocate the innovative use of the latest artificial intelligence and natural language processing technologies, comprehensively expanding the breadth, depth, and integrability of evidence and improving the efficiency of evidence generation and integration. Building a new generation of evidence-based decision-making ecosystems based on deep evidence-based medicine has broad prospects for practical application. It can promote the development of evidence retrieval, generation, integration, dissemination, transformation, and application, deeply explore imaging, multi-omics, and real-world data to increase the utilization potential of real-world evidence, establish dynamic literature management platforms and decision support tools, reduce resource waste, and promote evidence flow. Utilizing this system can help obtain individual-centered comprehensive clinical evidence and play a significant role in talent training, reforming evidence-based teaching, popularizing science, and ultimately promoting the goal of "One Health". |
|
View Fulltext
Html FullText
View/Add Comment Download reader |
| Close |
|
|
|