Dynamic Predictions of Postoperative Complications from Explainable, Uncertainty-Aware, and Multi-Task Deep Neural Networks

no code implementations • 27 Apr 2020 • Benjamin Shickel, Tyler J. Loftus, Matthew Ruppert, Gilbert R. Upchurch, Tezcan Ozrazgat-Baslanti, Parisa Rashidi, Azra Bihorac

In a longitudinal cohort study of 56, 242 patients undergoing 67, 481 inpatient surgical procedures at a university medical center, we compared deep learning models with random forests for predicting nine common postoperative complications using preoperative, intraoperative, and perioperative patient data.

Decision Making Multi-Task Learning +2

The Intelligent ICU Pilot Study: Using Artificial Intelligence Technology for Autonomous Patient Monitoring

no code implementations • 25 Apr 2018 • Anis Davoudi, Kumar Rohit Malhotra, Benjamin Shickel, Scott Siegel, Seth Williams, Matthew Ruppert, Emel Bihorac, Tezcan Ozrazgat-Baslanti, Patrick J. Tighe, Azra Bihorac, Parisa Rashidi

In this pilot study, we examined the feasibility of using pervasive sensing technology and artificial intelligence for autonomous and granular monitoring of critically ill patients and their environment in the Intensive Care Unit (ICU).

Action Unit Detection Face Detection +4