人工智能应切实支持临床推理和决策，以弥合转化差距。
Artificial intelligence should genuinely support clinical reasoning and decision making to bridge the translational gap.
作者信息
Sokol Kacper, Fackler James, Vogt Julia E
机构信息
Department of Computer Science, ETH Zurich, Zurich, Switzerland.
Department of Anesthesiology and Critical Care Medicine, Johns Hopkins University School of Medicine, Baltimore, MD, USA.
出版信息
NPJ Digit Med. 2025 Jun 10;8(1):345. doi: 10.1038/s41746-025-01725-9.
Abstract
Artificial intelligence promises to revolutionise medicine, yet its impact remains limited because of the pervasive translational gap. We posit that the prevailing technology-centric approaches underpin this challenge, rendering such systems fundamentally incompatible with clinical practice, specifically diagnostic reasoning and decision making. Instead, we propose a novel sociotechnical conceptualisation of data-driven support tools designed to complement doctors' cognitive and epistemic activities. Crucially, it prioritises real-world impact over superhuman performance on inconsequential benchmarks.
摘要
人工智能有望彻底改变医学，但由于普遍存在的转化差距，其影响仍然有限。我们认为，当前以技术为中心的方法是这一挑战的根源，使得此类系统从根本上与临床实践不兼容，尤其是诊断推理和决策。相反，我们提出了一种全新的社会技术概念，将数据驱动的支持工具设计为补充医生的认知和认识活动。至关重要的是，它将现实世界的影响置于无关紧要的基准上的超人表现之上。
相似文献
1
Artificial intelligence should genuinely support clinical reasoning and decision making to bridge the translational gap.人工智能应切实支持临床推理和决策，以弥合转化差距。
NPJ Digit Med. 2025 Jun 10;8(1):345. doi: 10.1038/s41746-025-01725-9.
2
The Willingness of Doctors to Adopt Artificial Intelligence-Driven Clinical Decision Support Systems at Different Hospitals in China: Fuzzy Set Qualitative Comparative Analysis of Survey Data.中国不同医院医生采用人工智能驱动的临床决策支持系统的意愿：基于调查数据的模糊集定性比较分析
J Med Internet Res. 2025 Jan 7;27:e62768. doi: 10.2196/62768.
3
From clinical decision support to clinical reasoning support systems.从临床决策支持到临床推理支持系统。
J Eval Clin Pract. 2021 Jun;27(3):520-528. doi: 10.1111/jep.13541. Epub 2021 Feb 7.
4
Artificial intelligence for clinical reasoning: the reliability challenge and path to evidence-based practice.用于临床推理的人工智能：可靠性挑战与循证实践之路。
QJM. 2025 May 19. doi: 10.1093/qjmed/hcaf114.
5
Beyond thinking fast and slow: a Bayesian intuitionist model of clinical reasoning in real-world practice.超越快与慢的思考：现实临床实践中临床推理的贝叶斯直觉主义模型
Diagnosis (Berl). 2024 Dec 10;12(2):182-188. doi: 10.1515/dx-2024-0169. eCollection 2025 May 1.
6
Superhuman artificial intelligence can improve human decision-making by increasing novelty.超级人工智能可以通过增加新颖性来提高人类决策能力。
Proc Natl Acad Sci U S A. 2023 Mar 21;120(12):e2214840120. doi: 10.1073/pnas.2214840120. Epub 2023 Mar 13.
7
Recent advancement in integrating artificial intelligence and information technology with real-world data for clinical decision-making in China: A scoping review.近期将人工智能和信息技术与真实世界数据相结合，以用于中国临床决策的进展：范围综述。
J Evid Based Med. 2023 Dec;16(4):534-546. doi: 10.1111/jebm.12549. Epub 2023 Sep 29.
8
Artificial intelligence and the doctor-patient relationship expanding the paradigm of shared decision making.人工智能与医患关系：拓展共同决策模式。
Bioethics. 2023 Jun;37(5):424-429. doi: 10.1111/bioe.13158. Epub 2023 Mar 25.
9
AI-driven decision support systems and epistemic reliance: a qualitative study on obstetricians' and midwives' perspectives on integrating AI-driven CTG into clinical decision making.人工智能驱动的决策支持系统和认知依赖：一项关于妇产科医生和助产士如何将人工智能驱动的 CTG 纳入临床决策的定性研究。
BMC Med Ethics. 2024 Jan 6;25(1):6. doi: 10.1186/s12910-023-00990-1.
10
Artificial intelligence for breast cancer detection and its health technology assessment: A scoping review.用于乳腺癌检测的人工智能及其健康技术评估：一项范围综述。
Comput Biol Med. 2025 Jan;184:109391. doi: 10.1016/j.compbiomed.2024.109391. Epub 2024 Nov 22.
本文引用的文献
1
Comparative Analysis of Bacteremic and Non-bacteremic Sepsis: A Retrospective Study.菌血症性与非菌血症性脓毒症的对比分析：一项回顾性研究
Cureus. 2024 Dec 26;16(12):e76418. doi: 10.7759/cureus.76418. eCollection 2024 Dec.
2
A scoping review on pediatric sepsis prediction technologies in healthcare.一项关于医疗保健中儿童脓毒症预测技术的范围综述。
NPJ Digit Med. 2024 Dec 4;7(1):353. doi: 10.1038/s41746-024-01361-9.
3
Diagnostic stewardship for blood cultures in the pediatric intensive care unit: lessons in implementation from the BrighT STAR Collaborative.儿科重症监护病房血培养的诊断管理：来自BrighT STAR协作组的实施经验教训。
Antimicrob Steward Healthc Epidemiol. 2024 Sep 25;4(1):e148. doi: 10.1017/ash.2024.416. eCollection 2024.
4
All models are wrong and yours are useless: making clinical prediction models impactful for patients.所有模型都是有缺陷的，而你的模型毫无用处：让临床预测模型对患者产生影响。
NPJ Precis Oncol. 2024 Feb 28;8(1):54. doi: 10.1038/s41698-024-00553-6.
5
International Consensus Criteria for Pediatric Sepsis and Septic Shock.国际儿童脓毒症和脓毒性休克共识标准。
JAMA. 2024 Feb 27;331(8):665-674. doi: 10.1001/jama.2024.0179.
6
Experience of Health Care Professionals Using Digital Tools in the Hospital: Qualitative Systematic Review.医疗机构专业人员使用数字工具的体验：定性系统评价。
JMIR Hum Factors. 2023 Oct 17;10:e50357. doi: 10.2196/50357.
7
Effects of machine learning-based clinical decision support systems on decision-making, care delivery, and patient outcomes: a scoping review.基于机器学习的临床决策支持系统对决策制定、护理提供和患者结局的影响：范围综述。
J Am Med Inform Assoc. 2023 Nov 17;30(12):2050-2063. doi: 10.1093/jamia/ocad180.
8
Psychological AI: Designing Algorithms Informed by Human Psychology.心理人工智能：基于人类心理学设计算法。
Perspect Psychol Sci. 2024 Sep;19(5):839-848. doi: 10.1177/17456916231180597. Epub 2023 Jul 31.
9
Estimating treatment effects for time-to-treatment antibiotic stewardship in sepsis.评估脓毒症中抗生素管理的治疗时间的治疗效果。
Nat Mach Intell. 2023 Apr;5(4):421-431. doi: 10.1038/s42256-023-00638-0. Epub 2023 Apr 6.
10
Less is more: Antibiotics at the beginning of life.少即是多：生命早期使用抗生素。
Nat Commun. 2023 Apr 27;14(1):2423. doi: 10.1038/s41467-023-38156-7.
Zotero 插件