Authors:Donna Tjandra (1), Trenton Chang (1), Sonali Parbhoo (2), Rajesh Ranganath (3 and 4), Andre Kurepa Waschka (5), William Mitchell (6), Maggie Makar (1), Shalmali Joshi (7), Finale Doshi-Velez (8), Leo Anthony Celi (9, 10, and 11), Jenna Wiens (1) ((1) Division of Computer Science and Engineering, University of Michigan, Ann Arbor, Michigan, United States, (2) Department of Electrical and Electronic Engineering, Imperial College London, London, UK, (3) Courant Institute of Mathematical Sciences, New York University, New York, New York, United States, (4) Center for Data Science, New York University, New York, New York, United States, (5) Department of Mathematics & Statistics, Elon University, Elon, North Carolina, United States, (6) Department of Ophthalmology, Cambridge University Hospitals, Cambridge, UK, (7) Department of Biomedical Informatics, Columbia University, New York, New York, United States, (8) School of Engineering and Applied Science, Harvard University, Cambridge, Massachusetts, United States, (9) Laboratory for Computational Physiology, Institute for Medical Engineering and Science, Massachusetts Institute of Technology, Cambridge, Massachusetts, United States, (10) Department of Medicine, Beth Israel Deaconess Medical Center, Boston, Massachusetts, United States, (11) Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, Massachusetts, United States)
Abstract:Objective: The growing availability of large-scale observational clinical datasets and challenges in conducting randomized controlled trials have spurred enthusiasm in using causal machine learning (ML) for causal inference in observational data. We present a roadmap for applying causal ML to observational data. Materials and methods: We outline the importance of assessing validity assumptions within available data and applying causal ML responsibly for clinical experts using causal ML and ML practitioners with limited clinical expertise. Observations: Despite advances in causal ML, its limitations remain largely under-appreciated across disciplines. This gap in shared knowledge may impact the validity of findings. Discussion: Causal assumptions must be satisfied and modeling choices justified. Otherwise, these approaches risk producing biased or misleading results, with consequences for clinical research and patient care. Conclusion: Causal ML can be a powerful tool for generating causal hypotheses. We provide a template to strengthen the rigor and interpretability of causal analyses.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.20782 [cs.LG] |
| (or arXiv:2605.20782v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.20782 arXiv-issued DOI via DataCite (pending registration) |
From: Donna Tjandra [view email]
[v1]
Wed, 20 May 2026 06:22:57 UTC (1,008 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。