Fairness metrics for health AI: we have a long way to go.
作者信息
Mbakwe Amarachi B, Lourentzou Ismini, Celi Leo Anthony, Wu Joy T
机构信息
Department of Computer Science, Virginia Tech, Blacksburg, VA 24061, USA.
Institute of Medical Engineering and Science, Massachusetts Institute of Technology, Cambridge, MA 02139, USA; Department of Medicine, Beth Israel Deaconess Medical Center, Boston, MA 02215, USA; Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA 02115, USA.
出版信息
EBioMedicine. 2023 Apr;90:104525. doi: 10.1016/j.ebiom.2023.104525. Epub 2023 Mar 14.
Abstract
摘要
相似文献
1
Fairness metrics for health AI: we have a long way to go.健康人工智能的公平性指标：我们还有很长的路要走。
EBioMedicine. 2023 Apr;90:104525. doi: 10.1016/j.ebiom.2023.104525. Epub 2023 Mar 14.
2
Fairness in Artificial Intelligence: Regulatory Sanbox Evaluation of Bias Prevention for ECG Classification.人工智能中的公平性：用于 ECG 分类的偏见预防的监管沙盒评估。
Stud Health Technol Inform. 2023 May 18;302:488-489. doi: 10.3233/SHTI230184.
3
Show Your Work: Responsible Model Reporting in Health Care Artificial Intelligence.展示你的工作：医疗人工智能中的负责任模型报告。
Surg Clin North Am. 2023 Jun;103(2S):e1-e11. doi: 10.1016/j.suc.2023.03.002. Epub 2023 May 9.
4
Using the Veil of Ignorance to align AI systems with principles of justice.利用无知之幕使人工智能系统与正义原则保持一致。
Proc Natl Acad Sci U S A. 2023 May 2;120(18):e2213709120. doi: 10.1073/pnas.2213709120. Epub 2023 Apr 24.
5
Framework and metrics for the clinical use and implementation of artificial intelligence algorithms into endoscopy practice: recommendations from the American Society for Gastrointestinal Endoscopy Artificial Intelligence Task Force.将人工智能算法临床应用及实施于内镜检查实践的框架与指标：美国胃肠内镜学会人工智能特别工作组的建议
Gastrointest Endosc. 2023 May;97(5):815-824.e1. doi: 10.1016/j.gie.2022.10.016. Epub 2023 Feb 8.
6
A clarification of the nuances in the fairness metrics landscape.厘清公平性指标领域的细微差别。
Sci Rep. 2022 Mar 10;12(1):4209. doi: 10.1038/s41598-022-07939-1.
7
Artificial Intelligence and Cancer Control: Toward Prioritizing Justice, Equity, Diversity, and Inclusion (JEDI) in Emerging Decision Support Technologies.人工智能与癌症防控：新兴决策支持技术中优先考虑公正、公平、多样性和包容性（JEDI）
Curr Oncol Rep. 2023 May;25(5):387-424. doi: 10.1007/s11912-023-01376-7. Epub 2023 Feb 22.
8
Benchmarks for social justice: assessing the fairness of academic conference participation.社会正义的基准：评估学术会议参与的公平性。
Promot Educ. 2005;12(2):71-6.
9
Artificial Intelligence Algorithms in Diabetic Retinopathy Screening.人工智能算法在糖尿病视网膜病变筛查中的应用。
Curr Diab Rep. 2022 Jun;22(6):267-274. doi: 10.1007/s11892-022-01467-y. Epub 2022 Apr 19.
10
Who should be first? How and when AI-human order influences procedural justice in a multistage decision-making process.谁应排在首位？人工智能与人的顺序如何以及何时影响多阶段决策过程中的程序正义。
PLoS One. 2023 Jul 17;18(7):e0284840. doi: 10.1371/journal.pone.0284840. eCollection 2023.
引用本文的文献
1
Using a Multilingual AI Care Agent to Reduce Disparities in Colorectal Cancer Screening for Higher Fecal Immunochemical Test Adoption Among Spanish-Speaking Patients: Retrospective Analysis.使用多语言人工智能护理代理来减少结直肠癌筛查中的差异，以提高西班牙语患者对粪便免疫化学检测的接受度：回顾性分析。
J Med Internet Res. 2025 Jun 25;27:e71211. doi: 10.2196/71211.
2
A scoping review and evidence gap analysis of clinical AI fairness.临床人工智能公平性的范围综述与证据差距分析
NPJ Digit Med. 2025 Jun 14;8(1):360. doi: 10.1038/s41746-025-01667-2.
3
Learning and diSentangling patient static information from time-series Electronic hEalth Records (STEER).从时间序列电子健康记录（STEER）中学习并解缠患者静态信息。
PLOS Digit Health. 2024 Oct 21;3(10):e0000640. doi: 10.1371/journal.pdig.0000640. eCollection 2024 Oct.
4
Addressing fairness issues in deep learning-based medical image analysis: a systematic review.解决基于深度学习的医学图像分析中的公平性问题：一项系统综述。
NPJ Digit Med. 2024 Oct 17;7(1):286. doi: 10.1038/s41746-024-01276-5.
5
Unmasking biases and navigating pitfalls in the ophthalmic artificial intelligence lifecycle: A narrative review.揭示眼科人工智能生命周期中的偏见并规避陷阱：一篇叙述性综述。
PLOS Digit Health. 2024 Oct 8;3(10):e0000618. doi: 10.1371/journal.pdig.0000618. eCollection 2024 Oct.
6
Health equity assessment of machine learning performance (HEAL): a framework and dermatology AI model case study.机器学习性能的健康公平性评估（HEAL）：一个框架及皮肤病学人工智能模型案例研究
EClinicalMedicine. 2024 Mar 14;70:102479. doi: 10.1016/j.eclinm.2024.102479. eCollection 2024 Apr.
7
Diagnostic suspicion bias and machine learning: Breaking the awareness deadlock for sepsis detection.诊断怀疑偏倚与机器学习：打破脓毒症检测的认知僵局
PLOS Digit Health. 2023 Nov 1;2(11):e0000365. doi: 10.1371/journal.pdig.0000365. eCollection 2023 Nov.
8
A translational perspective towards clinical AI fairness.临床人工智能公平性的转化视角。
NPJ Digit Med. 2023 Sep 14;6(1):172. doi: 10.1038/s41746-023-00918-4.
本文引用的文献
1
Algorithmic encoding of protected characteristics in chest X-ray disease detection models.算法对胸部 X 射线疾病检测模型中受保护特征的编码。
EBioMedicine. 2023 Mar;89:104467. doi: 10.1016/j.ebiom.2023.104467. Epub 2023 Feb 13.
2
Algorithmic transparency and interpretability measures improve radiologists' performance in BI-RADS 4 classification.算法透明度和可解释性度量可提高放射科医生在 BI-RADS 4 分类中的表现。
Eur Radiol. 2023 Mar;33(3):1844-1851. doi: 10.1007/s00330-022-09165-9. Epub 2022 Oct 25.
3
AI recognition of patient race in medical imaging: a modelling study.人工智能识别医学影像中的患者种族：一项建模研究。
Lancet Digit Health. 2022 Jun;4(6):e406-e414. doi: 10.1016/S2589-7500(22)00063-2. Epub 2022 May 11.
4
Underdiagnosis bias of artificial intelligence algorithms applied to chest radiographs in under-served patient populations.人工智能算法应用于服务不足患者人群的胸部 X 光片时的漏诊偏倚。
Nat Med. 2021 Dec;27(12):2176-2182. doi: 10.1038/s41591-021-01595-0. Epub 2021 Dec 10.
5
Transparency of deep neural networks for medical image analysis: A review of interpretability methods.用于医学图像分析的深度神经网络透明度：可解释性方法综述
Comput Biol Med. 2022 Jan;140:105111. doi: 10.1016/j.compbiomed.2021.105111. Epub 2021 Dec 4.
Zotero 插件