Invited Commentary: The Seedy Side of Causal Effect Estimation with Machine Learning

Department of Epidemiology, Gillings School of Global Public Health, University of North Carolina at Chapel Hill, NC, USA Financial Support: PNZ was supported by K01AI177102. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health. Conflicts of Interest: None Acknowledgments: I would like to thank Stephen Cole, Jessie Edwards, and Bonnie Shook-Sa for their feedback on an earlier draft of this commentary. I would also like to thank the University of North Carolina at Chapel Hill and the Research Computing group for providing computational resources and support that have contributed to these research results. Data Availability: Code to generate the data, implement single cross-fit targeted maximum likelihood, and conduct the simulations is available at https://github.com/pzivich/publications-code and https://zenodo.org/records/10845872 Editor's Note: A related article is on p. XXX. About The Author: PAUL ZIVICH is an Assistant Professor of Epidemiology at the University of North Carolina at Chapel Hill. He works on problems in causal inference and computational epidemiology, with particular focus on infectious diseases. His prior work includes practical implementation and application of machine learning algorithms for causal effect estimation. Corresponding Author: Dr. Paul Zivich, Department of Epidemiology, Gillings School of Global Public Health, UNC Campus Box 7435, Chapel Hill, NC 27599-7435 (email: email protected)