Speaker: Anoop Mayampurath, PhD | Assistant Professor, Department of Biostatistics and Medical Information, University of Wisconsin – Madison
Date: Monday, October 14th, 2024
Time: 10:00 AM Central Time
Location: WIMR 2409 or Zoom
Title: Using Electronic Health Record Data to Predict Deterioration in Hospitalized Children
Abstract: Children who are admitted to the hospital and subsequently deteriorate have a high risk of mortality. They are also more likely to experience complications in their long-term health. Because timely intervention increases survival, identifying children at risk for deterioration as early as possible is critical. Current early warning scores that predict deterioration are subjectively derived, utilize limited data elements, and have been shown in randomized control trials not to reduce in-hospital mortality.
This talk will focus on our recent efforts to utilize machine learning and electronic health record (EHR) data to revolutionize pediatric early warning scores. Our work has led to a machine learning model called pCART that detects deterioration earlier and more accurately than current standards and that has been shown to improve outcomes in children since deployment. I will also highlight recent efforts within the lab to extend risk prediction to other hospital settings and the use of notes to explain prediction model outputs. Our research facilitates early detection of children at risk for deterioration, thereby creating opportunities for timely intervention that could decrease preventable death and improve long-term outcomes.
Bio: Anoop Mayampurath, PhD, is an Assistant Professor in the Department of Biostatistics and Medical Information at the University of Wisconsin Madison (UW-Madison). He holds a PhD in Informatics and a minor in Statistics from Indiana University. Before joining UW-Madison in 2021, he was a Senior Scientist and Research Assistant Professor at the University of Chicago. Dr. Mayampurath is an NIH-funded clinical informatician and data scientist whose research focuses on using electronic health record data and machine learning to improve the care of hospitalized children. Currently, he co-leads the ICU Data Science Lab at UW-Madison.