Epilepsy physician and researcher Aaron Struck, MD, won the INFORMS Analytics Society Innovative Applications in Analytics Award (IAAA) for research in how to better predict seizures in patients with critical illness.

Struck, assistant professor of neurology in the University of Wisconsin School of Medicine and Public Health, shared the award with colleagues from Harvard, Duke and Massachusetts General Hospital.

Aaron Struck
Aaron Struck

 Their study, "Transparent Machine Learning Models for Predicting Seizures in ICU Patients from cEEG Signals," is a machine learning model for predicting seizures in ICU patients.  It analyzes subtle signals from continuous electroencephalography (cEEG) to detect abnormal electrical patterns that may predict a coming seizure. The goal is to treat the patients before the seizure occurs. This work is the first serious effort to develop such models for seizures in ICU patients and could have a substantial impact on critical care medicine practice. University Hospital uses cEEG monitoring in its critical care units.

His collaborators were Cynthia Rudin, of Duke University; Berk Ustun, of Harvard; and Brandon Westover of Massachusetts General Hospital. The award cited their “creative and unique application of a combination of analytical techniques in a new area.”