NIH Reporter #11172540

Personalized Risk Prediction for Prevention and Early Detection of Postoperative Failure to Rescue

This NIH-funded project by University of California Los Angeles aims to develop and test real-time postoperative risk prediction tools using machine learning on multi-modal data to improve surgical outcomes and reduce failure-to-rescue.

Description

The project aims to apply machine learning approaches to multiple data sources including electronic health record data, high-fidelity physiological waveform data, and genomic data that have never been used together in the acute care setting. The goal is to predict postoperative major complications and decrease failure-to-rescue after surgery. The inputs will be used in simulated real-time bedside management to design and evaluate a clinical decision support tool, and its feasibility and acceptability will be assessed in a small-scale prospective, longitudinal pilot evaluation.

View original record