- A Machine Learning Approach to Low-Value Health Care, NBER working paper (with Sendhil Mullainathan), R&R at QJE.
- Group Testing in a Pandemic, NBER working paper (with Ned Augenblick, Jon Kolstad, and Ao Wang).
Machine learning and health policy — automating bias
- Does Machine Learning Automate Moral Hazard and Error? AER: P&P 2017 (with Sendhil Mullainathan)
- Dissecting racial bias in an algorithm used to manage the health of populations, Science 2019 (with Brian Powers, Christine Vogeli, and Sendhil Mullainathan).
- Our GitLab repository with code and (simulated) replication data is here.
- A commentary on the article by Prof. Ruha Benjamin in the same issue of Science is here.
- This article made the Altmetric Top 100 for 2019 and won the ‘Editors’ Pick’ in STAT Madness 2020.
- A NeurIPS workshop talk on the paper is here, and this blog post has a non-technical summary.
- Media: The Wall Street Journal covered the study, and CBS interviewed the WSJ’s Melanie Evans on the story. The Washington Post, LA Times, AP, Guardian, Telegraph, Bloomberg, Wired, Scientific American, STAT, Nature, Breitbart (!), and many others also ran stories.
- Regulatory: The WSJ covered the NY state regulator’s response to the algorithm manufacturer, and Wired covered the letters Sens. Cory Booker and Ron Wyden sent to the Federal Trade Commission, the Centers for Medicare and Medicaid Services, and five of the largest health care companies in the US to ask about bias in light of our findings.
- Next steps: Our Health Affairs blog post talks more about what we’re doing to help fix the problem. We have been in communication with several regulatory agencies and state attorneys general to advise them on their response.
- Racial bias in allocation of COVID-19 relief funding, JAMA 2020 (with Pragya Kakani, Amitabh Chandra, and Sendhil Mullainathan).
Prediction policy problems
- Prediction Policy Problems, AER: P&P 2015 (with Jon Kleinberg, Jens Ludwig, and Sendhil Mullainathan)
- Predictive modeling of US healthcare spending in late life, Science 2018 (with Liran Einav, Amy Finkelstein, and Sendhil Mullainathan)
Machine learning — methods
- Direct Uncertainty Prediction for Medical Second Opinions, ICML 2019 (with Maithra Raghu, Katy Blumer, Rory Sayres, Robert Kleinberg, Sendhil Mullainathan, and Jon Kleinberg)
- Regularizing Latent Variable Models with Discriminative Models, ICML 2019 (with Andy Miller, Jon Cunningham, and Sendhil Mullainathan)
- A Comparison of Patient History- and EKG-based Cardiac Risk Scores, AMIA 2019 (with Andy Miller and Sendhil Mullainathan)
Machine learning — perspectives
- Putting decisions under the microscope, Nature Medicine 2019
- Regulation of predictive analytics in medicine, Science 2019 (with Ravi Parikh and Amol Navathe)
- Lost in Thought—The limits of the human mind and the future of medicine, NEJM 2017 (with Thomas Lee)
- Predicting the Future: Big Data, Machine Learning, and the Future of Clinical Medicine, NEJM 2016 (with Zeke Emanuel)
- Non-random assignment of patients to emergency physicians, JAMA Open 2020 (with CJ Chang)
- Individuals’ body temperatures vary meaningfully and predict mortality, BMJ 2017 (with Jasmeet Samra and Sendhil Mullainathan)
- Early death after discharge from emergency departments, BMJ 2017(with Brent Cohn, Michael Wilson, Bapu Jena, and David Cutler)
Global health (previous life)
- Emergency care delivery in 60 low- and middle-income countries, Bulletin of the World Health Organization 2015 (with Samer Abujaber, Maggie Makar, Samantha Stoll, Stephanie Kayden, Lee Wallis, and Teri Reynolds)
- Coverage of cervical cancer screening in 57 countries, PLoS Medicine 2008 (with Emmanuela Gakidou and Stella Nordhagen)
- Fifty years of violent war deaths , BMJ 2008 (with Chris Murray and Emmanuela Gakidou)
- Measuring adult mortality using sibling survival, PLoS Medicine 2010 (with Julie Rajaratnam, Chang Park, Emmanuela Gakidou, Mollie Hogan, Alan Lopez, and Chris Murray)