Even when human point forecasts are less accurate than data-based algorithm predictions, they can still help boost performance by being used as algorithm inputs. Assuming one uses human judgment indirectly in this manner, we propose changing the elicitation question from the traditional direct...

Because a hospital is an interconnected, interdependent network of care units, allocating resources — beds, nurses, and improvement initiatives — to one unit to reduce its congestion may have spillover effects on other units. As such, to identify the bottleneck unit and improve access to...

In the emergency department (ED), temporary teams of physicians and nurses work together to deliver patient care. We examine how team familiarity and partner variety affect the performance of ED teams and whether these effects vary depending on how long ago the experiences were accumulated....

The Centers for Medicare & Medicaid Services (CMS) and the National Quality Forum have endorsed 30-day mortality rates as important indicators of hospital quality. Concerns have been raised, however, as to whether post-discharge mortality rates are reasonable measures of hospital quality as they...

Most data-driven decision support tools do not include input from people. We study whether and how to incorporate physician input into such tools, in an empirical setting of predicting the surgery duration. Using data from a hospital, we evaluate and compare the performances of three families of...

Providing patients with timely care from the appropriate unit involves both correct clinical evaluation of patient needs and making admission decisions to effectively manage a unit with limited capacity in the face of stochastic patient arrivals and lengths of stay. We study human decision...

Intensive Care Units (ICUs) play a vital role in hospitals and they often have capacity strain. Using data from a major teaching hospital, we empirically examine the effect of ICU capacity strain on patient discharge. Our data has a dynamic measure of patient health status, allowing us to study...

We explore the challenges of re-using machine learning models originally developed for patient-level predictions to forecast system-wide quantities in hospitals. As a running example, we examine the use of patient-level predictions of length of stay to predict short-term occupancy in an...