January 3, 2022BMC Anesthesiology92 citationsOpen Access

Postoperative delirium prediction using machine learning models and preoperative electronic health record data

ABAndrew BisharaUniversity of California, San Francisco CCCatherine ChiuUniversity of California, San Francisco EWElizabeth L. WhitlockGeneral Cardiology

Structured PICO

Do machine learning models using preoperative EHR data predict postoperative delirium in surgical patients?

Population

Broad perioperative population (surgical patients at risk for postoperative delirium)

Intervention

Two machine learning models using preoperative electronic health record (EHR) data

Outcome

Postoperative delirium (POD) prediction/discrimination

Machine learning models using preoperative EHR data can provide automated, real-time risk stratification for postoperative delirium.

Abstract

Using pragmatically collected EHR data, two ML models predicted POD in a broad perioperative population with high discrimination. Optimal application of the models would provide automated, real-time delirium risk stratification to improve perioperative management of surgical patients at risk for POD.

Ask AI

Helpful

Bookmark

View Full Paper