Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 414 - Risk Modeling and Regression Techniques
Type: Contributed
Date/Time: Thursday, August 12, 2021 : 2:00 PM to 3:50 PM
Sponsor: Biometrics Section
Abstract #318434
Title: Quantifying the Harm Caused by Seizure-like Brain Activity in Critically Ill Patients using MALTS
Author(s): Kentaro Hoffman* and Harsh Parikh and Cynthia Rudin and Haoqi Sun and Brandon Westover
Companies: University of North Carolina-Chapel Hill and Duke University and Duke University and Massachusetts General Hosptial and Massachusetts General Hospital
Keywords: Personalized Medicine; Causal Inference; Matching; Neuroscience

Seizures and seizure-like brain activity patterns (ictal-interictal continuum, IIC) are common in critically ill neuro ICU patients. However, whether IICs directly leads to adverse outcomes is unclear, partially due to a strong feedback loops existing in hospital treatment. Recent advances in causal inference holds promise in estimating a less biased causal effect for IIC burden while providing interpretable results to aid doctors decision making.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2021 program