Research Spotlight: Predicting health crises from early warning signs in patient medical records

Sebastián Gallo Bernal, MD, a postdoctoral fellow in the Department of Radiology, is co-lead author of a recent study in Nature Scientific Reports, Predicting Health Crises From Early Warning Signs in Patient Medical Records.

Oleg S. Pianykh, PhD, an investigator in the Department of Radiology and Assistant Professor of Radiology at Harvard Medical School is the senior author.

What Question Were You Investigating?

In this study, we aimed to investigate whether changes in routine population health metrics may serve as early warnings of future crises.

What Was Your Approach?

Our team collected data from the emergency department of a large academic hospital in the northeastern United States from 01/01/2019 to 08/07/2021. A total of 377,694 patient records and 303 features were included for analysis.

Using a multivariate artificial intelligence (AI) model initially developed to predict the risk of high-flow oxygen therapy or mechanical ventilation requirement during the COVID-19 pandemic, our team sought to characterize the temporal trends of several population health indicators before and during the pandemic—and determine their potential roles as early warning signs of a future health crisis.

What Are the Clinical Implications?

Our work demonstrates how the time-windowed aggregation of individual patient metrics, routinely collected in hospital emergency departments, can lead to robust markers of approaching health crises.

This finding, confirmed by recent blood test research, provides a strong foundation for implementing robust population surveillance systems, detecting abnormal development several weeks in advance.

Response strategies for population-wide outbreaks currently adopt a passive and "a posteriori" approach. With our approach, real-time health surveillance systems that monitor population health deviations offer a much more efficient and proactive alternative.

About the Massachusetts General Hospital

Massachusetts General Hospital, founded in 1811, is the original and largest teaching hospital of Harvard Medical School. The Mass General Research Institute conducts the largest hospital-based research program in the nation, with annual research operations of more than $1 billion and comprises more than 9,500 researchers working across more than 30 institutes, centers and departments. In July 2022, Mass General was named #8 in the U.S. News & World Report list of "America’s Best Hospitals." MGH is a founding member of the Mass General Brigham healthcare system.