A Machine Learning-Based Algorithm for the Prediction of Intensive Care Unit Delirium (PRIDE): Retrospective Study.

Sujeong Hur Ryoung-Eun Ko Junsang Yoo Juhyung Ha Won Chul Cha Chi Ryang Chung

Published in: JMIR medical informatics (2021)

A machine learning approach based on electronic health record data can be used to predict delirium within 24 hours of ICU admission. RF, XGBoost, DNN, and LR models were used, and they effectively predicted delirium. However, with the potential to advise ICU physicians and prevent ICU delirium, prospective studies are required to verify the algorithm's performance.

Keyphrases

machine learning
intensive care unit
electronic health record
cardiac surgery
mechanical ventilation
hip fracture
big data
artificial intelligence
deep learning
clinical decision support
primary care
emergency department
acute kidney injury
acute respiratory distress syndrome
neural network
human health