反事实人工智能模型的临床潜力。 - Suppr

Suppr

超能文献

The clinical potential of counterfactual AI models.

作者信息

Lee Su-In, Topol Eric J

机构信息

Paul G Allen School of Computer Science & Engineering, University of Washington, Seattle, WA 98195, USA.

Scripps Research Translational Institute, La Jolla, CA, USA.

出版信息

Lancet. 2024 Feb 24;403(10428):717. doi: 10.1016/S0140-6736(24)00313-1.

DOI:10.1016/S0140-6736(24)00313-1

PMID:38401957

Abstract

摘要

相似文献

The clinical potential of counterfactual AI models.

Lancet. 2024 Feb 24;403(10428):717. doi: 10.1016/S0140-6736(24)00313-1.

GANterfactual-Counterfactual Explanations for Medical Non-experts Using Generative Adversarial Learning.

Front Artif Intell. 2022 Apr 8;5:825565. doi: 10.3389/frai.2022.825565. eCollection 2022.

Can counterfactual explanations of AI systems' predictions skew lay users' causal intuitions about the world? If so, can we correct for that?

Patterns (N Y). 2022 Dec 9;3(12):100635. doi: 10.1016/j.patter.2022.100635.

Explaining the black-box smoothly-A counterfactual approach.

Med Image Anal. 2023 Feb;84:102721. doi: 10.1016/j.media.2022.102721. Epub 2022 Dec 13.

Explaining Black Box Drug Target Prediction Through Model Agnostic Counterfactual Samples.

IEEE/ACM Trans Comput Biol Bioinform. 2023 Mar-Apr;20(2):1020-1029. doi: 10.1109/TCBB.2022.3190266. Epub 2023 Apr 3.

A Trustworthy Counterfactual Explanation Method With Latent Space Smoothing.

IEEE Trans Image Process. 2024;33:4584-4599. doi: 10.1109/TIP.2024.3442614. Epub 2024 Aug 23.

Counterfactual Explanation of Brain Activity Classifiers Using Image-To-Image Transfer by Generative Adversarial Network.

Front Neuroinform. 2022 Mar 16;15:802938. doi: 10.3389/fninf.2021.802938. eCollection 2021.

Dissection of medical AI reasoning processes via physician and generative-AI collaboration.

medRxiv. 2023 May 16:2023.05.12.23289878. doi: 10.1101/2023.05.12.23289878.

: counterfactual explanations for fairness.

Mach Learn. 2023 Mar 28:1-32. doi: 10.1007/s10994-023-06319-8.

Counterfactual links to the proportion of treatment effect explained by a surrogate marker.

Biometrics. 2005 Dec;61(4):1102-11. doi: 10.1111/j.1541-0420.2005.00380.x.

引用本文的文献

ToPoMesh: accurate 3D surface reconstruction from CT volumetric data via topology modification.

Med Biol Eng Comput. 2025 May 27. doi: 10.1007/s11517-025-03381-3.

Development and validation of an AI algorithm to generate realistic and meaningful counterfactuals for retinal imaging based on diffusion models.

PLOS Digit Health. 2025 May 15;4(5):e0000853. doi: 10.1371/journal.pdig.0000853. eCollection 2025 May.

An Introductory Module of Generative Artificial Intelligence in Medical Education.

Med Sci Educ. 2024 Nov 7;35(1):57-61. doi: 10.1007/s40670-024-02218-2. eCollection 2025 Feb.

Controllable Sequence Editing for Biological and Clinical Trajectories.

ArXiv. 2025 Jun 3:arXiv:2502.03569v2.

Artificial Intelligence to Diagnose Complications of Diabetes.

J Diabetes Sci Technol. 2025 Jan;19(1):246-264. doi: 10.1177/19322968241287773. Epub 2024 Nov 22.

Building an Ethical and Trustworthy Biomedical AI Ecosystem for the Translational and Clinical Integration of Foundation Models.

Bioengineering (Basel). 2024 Sep 29;11(10):984. doi: 10.3390/bioengineering11100984.

文献AI研究员

20分钟写一篇综述，助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型，支持多种主流文档格式。

立即体验

The clinical potential of counterfactual AI models.

作者信息

Lee Su-In, Topol Eric J

机构信息

Paul G Allen School of Computer Science & Engineering, University of Washington, Seattle, WA 98195, USA.

Scripps Research Translational Institute, La Jolla, CA, USA.

出版信息

Lancet. 2024 Feb 24;403(10428):717. doi: 10.1016/S0140-6736(24)00313-1.

DOI:10.1016/S0140-6736(24)00313-1

PMID:38401957

Abstract

摘要

相似文献

The clinical potential of counterfactual AI models.

Lancet. 2024 Feb 24;403(10428):717. doi: 10.1016/S0140-6736(24)00313-1.

GANterfactual-Counterfactual Explanations for Medical Non-experts Using Generative Adversarial Learning.

Front Artif Intell. 2022 Apr 8;5:825565. doi: 10.3389/frai.2022.825565. eCollection 2022.

Can counterfactual explanations of AI systems' predictions skew lay users' causal intuitions about the world? If so, can we correct for that?

Patterns (N Y). 2022 Dec 9;3(12):100635. doi: 10.1016/j.patter.2022.100635.

Explaining the black-box smoothly-A counterfactual approach.

Med Image Anal. 2023 Feb;84:102721. doi: 10.1016/j.media.2022.102721. Epub 2022 Dec 13.

Explaining Black Box Drug Target Prediction Through Model Agnostic Counterfactual Samples.

IEEE/ACM Trans Comput Biol Bioinform. 2023 Mar-Apr;20(2):1020-1029. doi: 10.1109/TCBB.2022.3190266. Epub 2023 Apr 3.

A Trustworthy Counterfactual Explanation Method With Latent Space Smoothing.

IEEE Trans Image Process. 2024;33:4584-4599. doi: 10.1109/TIP.2024.3442614. Epub 2024 Aug 23.

Counterfactual Explanation of Brain Activity Classifiers Using Image-To-Image Transfer by Generative Adversarial Network.

Front Neuroinform. 2022 Mar 16;15:802938. doi: 10.3389/fninf.2021.802938. eCollection 2021.

Dissection of medical AI reasoning processes via physician and generative-AI collaboration.

medRxiv. 2023 May 16:2023.05.12.23289878. doi: 10.1101/2023.05.12.23289878.

: counterfactual explanations for fairness.

Mach Learn. 2023 Mar 28:1-32. doi: 10.1007/s10994-023-06319-8.

Counterfactual links to the proportion of treatment effect explained by a surrogate marker.

Biometrics. 2005 Dec;61(4):1102-11. doi: 10.1111/j.1541-0420.2005.00380.x.

引用本文的文献

ToPoMesh: accurate 3D surface reconstruction from CT volumetric data via topology modification.

Med Biol Eng Comput. 2025 May 27. doi: 10.1007/s11517-025-03381-3.

Development and validation of an AI algorithm to generate realistic and meaningful counterfactuals for retinal imaging based on diffusion models.

PLOS Digit Health. 2025 May 15;4(5):e0000853. doi: 10.1371/journal.pdig.0000853. eCollection 2025 May.

An Introductory Module of Generative Artificial Intelligence in Medical Education.

Med Sci Educ. 2024 Nov 7;35(1):57-61. doi: 10.1007/s40670-024-02218-2. eCollection 2025 Feb.

Controllable Sequence Editing for Biological and Clinical Trajectories.

ArXiv. 2025 Jun 3:arXiv:2502.03569v2.

Artificial Intelligence to Diagnose Complications of Diabetes.

J Diabetes Sci Technol. 2025 Jan;19(1):246-264. doi: 10.1177/19322968241287773. Epub 2024 Nov 22.

Building an Ethical and Trustworthy Biomedical AI Ecosystem for the Translational and Clinical Integration of Foundation Models.

Bioengineering (Basel). 2024 Sep 29;11(10):984. doi: 10.3390/bioengineering11100984.