Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Podocyte mPGES-2 Determines Renal Aging and Contributes to Senile Osteoporosis.

Aging cell·2026
Same author

Effects of individualized positive end-expiratory pressure combined with recruitment maneuver on intraoperative ventilation during abdominal surgery: a systematic review and network meta-analysis of randomized controlled trials.

Journal of anesthesia·2021
Same author

Urinary albumin creatinine ratio associated with postoperative delirium in elderly patients undergoing elective non-cardiac surgery: A prospective observational study.

CNS neuroscience & therapeutics·2021
Same author

Bioinspired mineral hydrogels as nanocomposite scaffolds for the promotion of osteogenic marker expression and the induction of bone regeneration in osteoporosis.

Acta biomaterialia·2020
Same author

Determinants of gefitinib pharmacokinetics in healthy Chinese male subjects: A pharmacogenomic study of cytochrome p450 enzymes and transporters.

Journal of clinical pharmacy and therapeutics·2020
Same author

Photoassisted degradation of 2,2',4,4'-tetrabrominated diphenyl ether in simulated soil washing system containing Triton X series surfactants.

Environmental pollution (Barking, Essex : 1987)·2020

Related Experiment Video

Updated: Oct 13, 2025

An Experimental Paradigm for the Prediction of Post-Operative Pain PPOP
14:56

An Experimental Paradigm for the Prediction of Post-Operative Pain PPOP

Published on: January 27, 2010

21.5K

Automated machine learning-based model predicts postoperative delirium using readily extractable perioperative

Xiao-Yi Hu1,2, He Liu3, Xue Zhao1

  • 1Department of Anesthesiology, The Affiliated Hospital of Xuzhou Medical University, Jiangsu Province, Xuzhou City, China.

CNS Neuroscience & Therapeutics
|November 18, 2021
PubMed
Summary

A machine learning model accurately predicts postoperative delirium (POD) risk using patient data. This algorithm helps identify at-risk surgical patients for timely intervention and improved outcomes.

Keywords:
deliriummachine learningmodel predictionnomogrampostoperative

More Related Videos

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
07:31

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

7.3K
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.7K

Related Experiment Videos

Last Updated: Oct 13, 2025

An Experimental Paradigm for the Prediction of Post-Operative Pain PPOP
14:56

An Experimental Paradigm for the Prediction of Post-Operative Pain PPOP

Published on: January 27, 2010

21.5K
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
07:31

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

7.3K
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.7K

Area of Science:

  • Anesthesiology and Perioperative Medicine
  • Medical Informatics
  • Geriatric Medicine

Background:

  • Postoperative delirium (POD) is a frequent complication impacting patient outcomes.
  • Rapid identification of patients at high risk for POD is crucial for effective management.
  • Automated prediction models offer a potential solution for timely POD risk assessment.

Purpose of the Study:

  • To develop and validate a machine learning algorithm for predicting postoperative delirium.
  • To identify key clinical and laboratory features associated with POD risk.
  • To create a tool for rapid perioperative risk stratification of surgical patients.

Main Methods:

  • Secondary analysis of an observational study involving 531 surgical patients.
  • Utilized the Least Absolute Shrinkage and Selection Operator (LASSO) for feature selection.
  • Developed and compared four machine learning models (logistic regression, random forest, XGBoost, SVM) for POD prediction.

Main Results:

  • A logistic regression model achieved the highest predictive performance (AUC 80.44%) in the testing set.
  • Key independent risk factors for POD identified: age, extubation time, ICU admission, MMSE, CCI, and postoperative NLR.
  • The model demonstrated robust performance in identifying patients at risk for POD.

Conclusions:

  • A validated, high-performing algorithm can predict POD risk during the perioperative period.
  • This tool aids in making rational therapeutic choices for at-risk patients.
  • The developed model supports proactive management strategies to mitigate POD incidence and impact.