用于人工智能驱动的临床决策支持系统的临床医生告知的可解释人工智能评估清单及指标（CLIX-M）
Clinician-informed XAI evaluation checklist with metrics (CLIX-M) for AI-powered clinical decision support systems.
作者信息
Brankovic Aida, Cook David, Rahman Jessica, Delaforce Alana, Li Jane, Magrabi Farah, Cabitza Federico, Coiera Enrico, Bradford DanaKai
机构信息
CSIRO's Australian eHealth Research Centre, Herston, QLD, Australia.
The University of Queensland, Brisbane, QLD, Australia.
出版信息
NPJ Digit Med. 2025 Jun 14;8(1):364. doi: 10.1038/s41746-025-01764-2.
Abstract
The rapid growth of clinical explainable AI (XAI) models raised concerns over unclear purposes and false hope regarding explanations. Currently, no standardised metrics exist for XAI evaluation. We developed a clinician-informed, 14-item checklist including clinical, machine and decision attributes. This is the first step toward XAI standardisation and transparent reporting XAI methods to enhance trust, reduce risks, foster AI adoption, and improve decisions to determine the true clinical potential of applied XAI.
摘要
临床可解释人工智能（XAI）模型的快速发展引发了人们对其目的不明确以及解释带来的虚假希望的担忧。目前，XAI评估尚无标准化指标。我们制定了一份由临床医生提供信息的、包含14项内容的清单，涵盖临床、机器和决策属性。这是迈向XAI标准化以及透明报告XAI方法的第一步，目的是增强信任、降低风险、促进人工智能的应用，并改进决策，以确定应用XAI的真正临床潜力。
相似文献
1
Clinician-informed XAI evaluation checklist with metrics (CLIX-M) for AI-powered clinical decision support systems.用于人工智能驱动的临床决策支持系统的临床医生告知的可解释人工智能评估清单及指标（CLIX-M）
NPJ Digit Med. 2025 Jun 14;8(1):364. doi: 10.1038/s41746-025-01764-2.
2
How Explainable Artificial Intelligence Can Increase or Decrease Clinicians' Trust in AI Applications in Health Care: Systematic Review.可解释人工智能如何增加或降低临床医生对医疗保健中人工智能应用的信任：系统评价
JMIR AI. 2024 Oct 30;3:e53207. doi: 10.2196/53207.
3
Decoding the black box: Explainable AI (XAI) for cancer diagnosis, prognosis, and treatment planning-A state-of-the art systematic review.解码黑箱：癌症诊断、预后和治疗计划的可解释人工智能（XAI）——最新系统评价。
Int J Med Inform. 2025 Jan;193:105689. doi: 10.1016/j.ijmedinf.2024.105689. Epub 2024 Nov 4.
4
Unveiling the black box: A systematic review of Explainable Artificial Intelligence in medical image analysis.揭开黑箱：医学图像分析中可解释人工智能的系统综述。
Comput Struct Biotechnol J. 2024 Aug 12;24:542-560. doi: 10.1016/j.csbj.2024.08.005. eCollection 2024 Dec.
5
Enhancing Clinical Decision Support: A Heuristic Evaluation of Explainable AI in Healthcare Dashboards.
Stud Health Technol Inform. 2025 May 15;327:343-347. doi: 10.3233/SHTI250341.
6
Systematic literature review on the application of explainable artificial intelligence in palliative care studies.关于可解释人工智能在姑息治疗研究中应用的系统文献综述。
Int J Med Inform. 2025 Aug;200:105914. doi: 10.1016/j.ijmedinf.2025.105914. Epub 2025 Apr 8.
7
Towards clinical prediction with transparency: An explainable AI approach to survival modelling in residential aged care.迈向具有透明度的临床预测：一种用于老年护理机构生存建模的可解释人工智能方法。
Comput Methods Programs Biomed. 2025 May;263:108653. doi: 10.1016/j.cmpb.2025.108653. Epub 2025 Feb 15.
8
Do explainable AI (XAI) methods improve the acceptance of AI in clinical practice? An evaluation of XAI methods on Gleason grading.可解释人工智能（XAI）方法能否提高人工智能在临床实践中的接受度？对XAI方法在 Gleason分级中的评估。
J Pathol Clin Res. 2025 Mar;11(2):e70023. doi: 10.1002/2056-4538.70023.
9
Investigating Protective and Risk Factors and Predictive Insights for Aboriginal Perinatal Mental Health: Explainable Artificial Intelligence Approach.探究原住民围产期心理健康的保护因素、风险因素及预测性见解：可解释人工智能方法
J Med Internet Res. 2025 Apr 30;27:e68030. doi: 10.2196/68030.
10
Evaluating Explainable Artificial Intelligence (XAI) techniques in chest radiology imaging through a human-centered Lens.从以人为中心的角度评估胸部放射影像学中的可解释人工智能（XAI）技术。
PLoS One. 2024 Oct 9;19(10):e0308758. doi: 10.1371/journal.pone.0308758. eCollection 2024.
本文引用的文献
1
Benchmarking the most popular XAI used for explaining clinical predictive models: Untrustworthy but could be useful.对用于解释临床预测模型的最流行的可解释人工智能方法进行基准测试：不可信但可能有用。
Health Informatics J. 2024 Oct-Dec;30(4):14604582241304730. doi: 10.1177/14604582241304730.
2
The Role of AI in Hospitals and Clinics: Transforming Healthcare in the 21st Century.人工智能在医院和诊所中的作用：变革21世纪的医疗保健
Bioengineering (Basel). 2024 Mar 29;11(4):337. doi: 10.3390/bioengineering11040337.
3
TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods.TRIPOD+AI 声明：报告使用回归或机器学习方法的临床预测模型的更新指南。
BMJ. 2024 Apr 16;385:e078378. doi: 10.1136/bmj-2023-078378.
4
Elucidating Discrepancy in Explanations of Predictive Models Developed Using EMR.阐明使用电子病历开发的预测模型解释中的差异。
Stud Health Technol Inform. 2024 Jan 25;310:865-869. doi: 10.3233/SHTI231088.
5
Rams, hounds and white boxes: Investigating human-AI collaboration protocols in medical diagnosis.公羊、猎犬和白盒子：探索医学诊断中人机协作协议。
Artif Intell Med. 2023 Apr;138:102506. doi: 10.1016/j.artmed.2023.102506. Epub 2023 Feb 8.
6
Guidelines and evaluation of clinical explainable AI in medical image analysis.医学影像分析中临床可解释人工智能的指南和评估。
Med Image Anal. 2023 Feb;84:102684. doi: 10.1016/j.media.2022.102684. Epub 2022 Nov 17.
7
Explainable medical imaging AI needs human-centered design: guidelines and evidence from a systematic review.可解释的医学影像人工智能需要以人类为中心的设计：系统评价的指南与证据
NPJ Digit Med. 2022 Oct 19;5(1):156. doi: 10.1038/s41746-022-00699-2.
8
The false hope of current approaches to explainable artificial intelligence in health care.当前医疗保健中可解释人工智能方法的虚假希望。
Lancet Digit Health. 2021 Nov;3(11):e745-e750. doi: 10.1016/S2589-7500(21)00208-9.
9
Checklist for Artificial Intelligence in Medical Imaging (CLAIM): A Guide for Authors and Reviewers.医学影像人工智能清单（CLAIM）：作者和审稿人指南
Radiol Artif Intell. 2020 Mar 25;2(2):e200029. doi: 10.1148/ryai.2020200029. eCollection 2020 Mar.
10
From Local Explanations to Global Understanding with Explainable AI for Trees.利用可解释人工智能实现从局部解释到树木的全局理解
Nat Mach Intell. 2020 Jan;2(1):56-67. doi: 10.1038/s42256-019-0138-9. Epub 2020 Jan 17.
Zotero 插件