Machine Learning Predicts Early Onset of Sepsis from Continuous Physiological Data of Critically Ill Adults

Ronet Swaminathan, Aditya Singh, Akram Mohammed, Rishikesan Kamaleswaran1

  • 1University of Tennessee Health Science Center

Details

12:15 - 14:15 | Wed 20 November | Upper Foyer Balcony | A1P-E.9

Session: [A1P-E] Poster Session - Early Detection of Disease or Toxicity 1

Category: Poster Session
Theme: Early Detection of Disease or Toxicity

Full Text

Abstract

Sepsis is a severe dysregulation of the immune system due to infection, that often results in multi-organ failure. Predicting early onset of sepsis from physiological data streams and clinical variables using machine learning techniques could help in designing effective treatment strategies. Our study demonstrates the viability of using machine learning to predict sepsis among hospitalized adults.