Artificial intelligence predicts delirium following cardiac surgery: A case study

Delirium is a highly relevant complication of surgical interventions. Current research indicates that despite increased awareness for delirium, it is often overlooked. We implemented an AI-based tool to monitor delirium in cardiac surgery patients in our specialist clinic. This appears to be a promi...

Full description

Saved in:
Bibliographic Details
Published inJournal of clinical anesthesia Vol. 75; p. 110473
Main Authors Fliegenschmidt, Janis, Hulde, Nikolai, Preising, Maria G., Ruggeri, Silvia, Szymanowski, Ralph, Meesseman, Laurent, Sun, Hong, von Dossow, Vera
Format Journal Article
LanguageEnglish
Published United States Elsevier Inc 01.12.2021
Elsevier Limited
Subjects
Artificial Intelligence
Cardiac surgery
Cardiac Surgical Procedures - adverse effects
Delirium
Delirium - diagnosis
Delirium - etiology
Electronic health records
Frailty
Heart surgery
Hospitals
Humans
Intensive care
Mass Screening
Patients
Risk Factors
Risk stratification
Delirium
Frailty
Cardiac surgery
Artificial intelligence
Risk stratification
Online AccessGet full text

Cover

More Information
Summary:Delirium is a highly relevant complication of surgical interventions. Current research indicates that despite increased awareness for delirium, it is often overlooked. We implemented an AI-based tool to monitor delirium in cardiac surgery patients in our specialist clinic. This appears to be a promising approach to improve detection of delirium, especially for underrecognized forms and in peripheral wards without intensive screening. We present a case in which the AI identified delirium, confirmed by our routine screening and specialist evaluation. •Artificial intelligence can continuously evaluate all EHR information.•Automatic screening can beneficially direct clinician attention.•Artificial intelligence improves delirium screening in peripheral wards.•Using AI to predict events in real time provides clinical applicability.
Bibliography:ObjectType-Case Study-2
SourceType-Scholarly Journals-1
ObjectType-Feature-4
content type line 23
ObjectType-Report-1
ObjectType-Article-3
ISSN:0952-8180
1873-4529
DOI:10.1016/j.jclinane.2021.110473