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

Noise performance of InAs/GaSb/AlSb/GaSb SWIR FPA.

Optics express·2026
Same author

SIRT7 Prevents Intervertebral Disc Degeneration by Inhibiting the NF-κB Pathway.

Frontiers in bioscience (Landmark edition)·2026
Same author

Association between preoperative COVID-19 and major postoperative pulmonary complications: a multicentre observational cohort study in China.

BMJ open·2026
Same author

Effects of noise isolation using noise-canceling headphones during lymphedema liposuction on postoperative pain in patients undergoing general anesthesia: a protocol for a randomized controlled trial.

Trials·2026
Same author

CYP2D6 gene polymorphisms influence postoperative pain sensitivity and drug response in lung cancer surgery.

International journal of clinical and experimental pathology·2026
Same author

Effect of individualized PEEP guided by EIT vs. conventional fixed PEEP on postoperative pulmonary complications in adult patients with preoperative cardiopulmonary dysfunction undergoing CRS/HIPEC: a randomized clinical trial.

BMC anesthesiology·2026

Related Experiment Video

Updated: Jul 4, 2025

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

7.5K

Random forest algorithm for predicting postoperative delirium in older patients.

Weixuan Sheng1, Xianshi Tang2, Xiaoyun Hu1

  • 1Department of Anesthesiology, Beijing Shijitan Hospital, Capital Medical University, Beijing, China.

Frontiers in Neurology
|January 26, 2024
PubMed
Summary

Machine learning accurately predicts postoperative delirium (POD) in older adults. Key risk factors identified include serum creatinine (CREA) and postoperative pain scores (VAS-Move-Max), enabling better risk assessment.

Keywords:
confusion matrixolder patientpartial dependence graphpostoperative deliriumrandom forest

More Related Videos

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

21.4K
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

7.1K

Related Experiment Videos

Last Updated: Jul 4, 2025

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

7.5K
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

21.4K
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

7.1K

Area of Science:

  • Geriatric Medicine
  • Medical Informatics
  • Computational Biology

Background:

  • Postoperative delirium (POD) is a common complication in older patients, associated with adverse outcomes.
  • Accurate prediction of POD is crucial for timely intervention and improved patient management.

Purpose of the Study:

  • To identify significant predictors of POD in elderly patients using machine learning algorithms.
  • To develop and validate a high-performance predictive model for POD occurrence.

Main Methods:

  • Secondary analysis of a randomized controlled trial dataset.
  • Utilized Boruta function for variable screening and four machine learning models: Logistic Regression (LR), K-Nearest Neighbor (KNN), Classification and Regression Tree (CART), and Random Forest (RF).
  • Employed techniques including repeated cross-validation, hyper-parameter optimization, and Synthetic minority over-sampling technique (Smote), with performance evaluated using confusion matrix, ROC, and PRC curves.

Main Results:

  • Identified key predictive variables including preoperative MMSE, CHARLSON score, serum creatinine (CREA), and postoperative pain scores (VAS-Move-Max).
  • The Random Forest (RF) model demonstrated superior performance with an accuracy of 0.9878 and AUC-ROC/AUC-PRC of 1.0.
  • CREA and VAS-Move-Max were identified as the major risk factors for POD development.

Conclusions:

  • A high-performance machine learning algorithm was successfully developed and validated for predicting POD risk in perioperative elderly patients.
  • The study highlights the utility of machine learning in identifying critical risk factors and improving POD prediction accuracy.
  • Findings provide a valuable tool for clinicians to assess and manage POD risk in the elderly population.