Patient Flight Plan Predictor


Catalyst’s core predictive analytics technology is based upon a model first developed in the US Air Force and later adopted by commercial airlines to predict the arrival and turnaround times of inbound aircraft. The aircraft turnaround time is analogous to a patient’s outcome in healthcare. In aircraft flight operations, the ability to precisely predict landing and turnaround times, which includes the complex coordination of ground support equipment and supplies, is critical. In the military, these predictions are critical to life-and-death battlefield coordination. In commercial flight operations, these predictions are critical to the economic well-being of the airline, as well as adherence to FAA-regulated schedules.

These predictive algorithms in aircraft operations utilize the data collected about the inbound flights— aircraft type, runway and gate assignment, speed, distance, weather conditions, fuel levels, maintenance problems reported in-flight, flight crew names, etc.—and compare that data profile against a historical database of similar profiles along with the actual turnaround times of those historical flights.

Catalyst’s highly proprietary Patient Flight Plan Predictor is based upon the exact same concept. Catalyst profiles inbound patients with as much data as is available, adding data that is collected during admission (or encounter) and then comparing that patient’s specific data against historical patient data of similar profiles and those patients’ historical outcomes. With this comparative approach, Catalyst can precisely predict readmission probability and patient satisfaction.

If additional patient outcomes data is available, such as functional status, in the client’s ecosystem of data, Catalyst’s methodology can easily accommodate this additional data content to augment Patient Flight Plan Predictor. Catalyst’s approach to predictive analytics does not rely on the more popular, very complicated, and less accurate techniques that rely on a priori weighted multivariate modeling. Instead, Catalyst retrospectively calculates the weighted impact of the various data variables in the system, and thus enables very targeted interventions (prescriptive analytics) at the inbound patient level, when needed. Available 2014.

Join our growing community of healthcare leaders

Stay informed by getting the latest news and exclusive updates from Health Catalyst.

This site uses cookies

We take pride in providing you with relevant, useful content. May we use cookies to track what you read? We take your privacy very seriously. Please see our privacy policy for details and any questions.