Causal Machine Learning Is Not a Panacea: A Roadmap for Observational Causal Inference in Health
Organizations: Division of Computer Science and Engineering, University of Michigan, Ann Arbor, Michigan, United States · Department of Electrical and Electronic Engineering, Imperial College London, London, UK · Courant Institute of Mathematical Sciences, New York University, New York, New York, United States · Center for Data Science, New York University, New York, New York, United States · Department of Mathematics & Statistics, Elon University, Elon, North Carolina, United States · Department of Ophthalmology, Cambridge University Hospitals, Cambridge, UK · Department of Biomedical Informatics, Columbia University, New York, New York, United States · School of Engineering and Applied Science, Harvard University, Cambridge, Massachusetts, United States · Laboratory for Computational Physiology, Institute for Medical Engineering and Science, Massachusetts Institute of Technology, Cambridge, Massachusetts, United States · Department of Medicine, Beth Israel Deaconess Medical Center, Boston, Massachusetts, United States · 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.