Surgical scheduling via optimization and machine learning with long-tailed data : Health care management science, in press.

Using data from cardiovascular surgery patients with long and highly variable post-surgical lengths of stay (LOS), we develop a modeling framework to reduce recovery unit congestion. We estimate the LOS and its probability distribution using machine learning models, schedule procedures on a rolling basis using a variety of optimization models, and estimate performance with simulation. The machine learning models achieved only modest LOS prediction accuracy, despite access to a very rich set of patient characteristics.

Increased dominance of heat-tolerant symbionts creates resilient coral reefs in near-term ocean warming.

Climate change is radically altering coral reef ecosystems, mainly through increasingly frequent and severe bleaching events. Yet, some reefs have exhibited higher thermal tolerance after bleaching severely the first time. To understand changes in thermal tolerance in the eastern tropical Pacific (ETP), we compiled four decades of temperature, coral cover, coral bleaching, and mortality data, including three mass bleaching events during the 1982 to 1983, 1997 to 1998 and 2015 to 2016 El Niño heatwaves.

Cardiovascular Imaging for Systemic Sclerosis Monitoring and Management.

Systemic sclerosis (SSc) is a complex connective tissue disease with multiple clinical and subclinical cardiac manifestations. SSc can affect most structural components of the heart, including the pericardium, myocardium, valves, and conduction system through a damaging cycle of inflammation, ischemia, and fibrosis. While cardiac involvement is the second leading SSc-related cause of death, it is frequently clinically silent in early disease and often missed with routine screening.

Validating Coding for the Identification of Pediatric Treatment Resistant Epilepsy Patients.

The International Classification of Diseases (ICD) system includes sub codes to indicate that an individual with epilepsy is treatment resistant. These codes would be a valuable tool to identify individuals for quality improvement and population health, as well as for recruitment into clinical trials. However, the accuracy of these codes is unclear.