Of the 120 million patients seen annually in US Emergency Departments, 85% are discharged home, as are the vast majority of the one billion patients seen in ambulatory clinics. While rates of in-hospital deaths are routinely measured and reported, deaths outside of health facilities are far more challenging to capture because of fragmented health information systems both within and among health care organizations. As a result, providers have no systematic way of knowing when a patient dies unexpectedly after being sent home, and policy makers cannot readily measure how frequently these catastrophic events occur. I propose a series of linked research projects to track and analyze unexpected deaths after medical encounters, using data from a large academic hospital system as well as Medicare claims, in order to identify factors related to individual patients, providers, and system that increase the likelihood of such events. I will subsequently adapt the methods to an international setting, where clinical and administrative data are less complete than in the US. This work would have important implications for improving both clinical care and health services design. In addition, a systematic method for tracking and reporting rates of unexpected early deaths would be a useful way to measure health services performance, and assess trade-offs between quality and cost.
Most of the 1.1 billion patients seen annually in emergency facilities or clinics return home after their visit, but neither doctors nor policy makers have any systematic way of identifying patients who die unexpectedly after being sent home. My project aims to track and analyze these events, with the goals of helping providers identify high-risk patients;understanding the health system factors that make errors of risk assessment more likely;and exploring whether rates of unexpected death after discharge can be used to measure and publicly report on the quality of care delivered by health services.
|Einav, Liran; Finkelstein, Amy; Mullainathan, Sendhil et al. (2018) Predictive modeling of U.S. health care spending in late life. Science 360:1462-1465|
|(2018) Machine Learning in Health Care. Natl Bur Econ Res Bull Aging Health :4-5|
|Obermeyer, Ziad; Lee, Thomas H (2017) Lost in Thought - The Limits of the Human Mind and the Future of Medicine. N Engl J Med 377:1209-1211|
|Asaria, Perviz; Elliott, Paul; Douglass, Margaret et al. (2017) Acute myocardial infarction hospital admissions and deaths in England: a national follow-back and follow-forward record-linkage study. Lancet Public Health 2:e191-e201|
|Mullainathan, Sendhil; Obermeyer, Ziad (2017) Does Machine Learning Automate Moral Hazard and Error? Am Econ Rev 107:476-480|
|Obermeyer, Ziad; Cohn, Brent; Wilson, Michael et al. (2017) Early death after discharge from emergency departments: analysis of national US insurance claims data. BMJ 356:j239|
|Obermeyer, Ziad; Samra, Jasmeet K; Mullainathan, Sendhil (2017) Individual differences in normal body temperature: longitudinal big data analysis of patient records. BMJ 359:j5468|
|Obermeyer, Ziad; Emanuel, Ezekiel J (2016) Predicting the Future - Big Data, Machine Learning, and Clinical Medicine. N Engl J Med 375:1216-9|
|Chang, Bernard P; Pany, Maximilian J; Obermeyer, Ziad (2016) Early death after emergency department discharge in patients with psychiatric illness. Am J Emerg Med :|
|Niedzwiecki, Matthew; Baicker, Katherine; Wilson, Michael et al. (2016) Short-term Outcomes for Medicare Beneficiaries After Low-acuity Visits to Emergency Departments and Clinics. Med Care 54:498-503|
Showing the most recent 10 out of 25 publications