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 Experiment Videos

Development and Validation of a Prediction Model for Postoperative Delirium.

Laixi Li1, Ningning Qiao2, Xiaojuan Yang3

  • 1Department of Anesthesiology, 541 General Hospital, Yuncheng, Shanxi Province, People's Republic of China.

Neuropsychiatric Disease and Treatment
|June 15, 2026
PubMed
Summary

Related Concept Videos

Data Validation01:03

Data Validation

Data validation is an essential part of a comprehensive assessment. Validation is confirming or verifying and opening the door to gathering more assessment data as it clarifies vague or unclear data. The process of checking and verifying the collected information is called data validation. The primary purpose of data validation is to ensure data is as free from error, bias, and misinterpretation as possible.
Nursing assessment guides are generally based on holistic models rather than medical...

You might also read

Related Articles

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

Sort by
Same author

Mechanistic regulation of multielectron iodine chemistry in aqueous zinc-iodine batteries.

Chemical communications (Cambridge, England)·2026
Same author

Lactylation of PD-L1 by a lactyltransferase HAT1 dictates its protein stability and tumor immune evasion.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

Fabrication of a high-performance MXene-ATP composite membrane: enhancing flux and retention for dye wastewater treatment.

Environmental research·2026
Same author

CA125 Outperforms HE4 and CA19-9 as a Serum Biomarker for Preoperative Diagnosis of Ovarian Endometriomas: A Retrospective Cohort Study.

Reproductive sciences (Thousand Oaks, Calif.)·2026
Same author

Nanocarriers engineering for efficient NSUN2 silencing and immune responsive therapy in metastatic colorectal cancer.

Materials today. Bio·2026
Same author

RETRACTED: Clinical effects of acupuncture for the treatment of pressure ulcers: A comprehensive systematic review and meta-analysis.

International wound journal·2026

A machine learning model accurately predicts postoperative delirium (POD) risk. Key predictors include cognitive status, nutrition, and demographics, enabling early intervention for surgical patients.

Area of Science:

  • Medical Informatics
  • Machine Learning in Healthcare
  • Surgical Outcomes Research

Background:

  • Postoperative delirium (POD) is a frequent and severe complication following surgery.
  • Early identification of patients at high risk for POD is crucial for implementing timely interventions.

Purpose of the Study:

  • To develop and validate a machine learning (ML) model for predicting POD.
  • To compare the performance of eight different ML algorithms for POD prediction.

Main Methods:

  • A multicenter retrospective cohort of 3000 surgical patients was analyzed.
  • Eight ML algorithms were evaluated, with Random Forest selected as the optimal model based on AUC.
  • SHapley Additive exPlanations (SHAP) were used for model interpretability.
Keywords:
Chinese mini mental statusSHapley additive exPlanationsmachine learningpostoperative deliriumprognostic nutritional index

Related Experiment Videos

Main Results:

  • The Random Forest model achieved high predictive accuracy (AUC: 0.823 in external validation).
  • Key predictors identified include Chinese Mini Mental Status (CMMS) score, Prognostic Nutritional Index, ASA classification, age, dementia, and ICU admission.
  • The model demonstrated good calibration and discrimination.

Conclusions:

  • A validated, interpretable ML framework for POD risk stratification is presented.
  • The findings highlight the importance of nutritional status as a modifiable target for perioperative interventions to reduce POD.