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 Video

Updated: Jan 13, 2026

Minimally Invasive Treatment for Thoracolumbar Burst Fracture Using Sagittal Alignment Screws and A Trauma Reduction Device
04:19

Minimally Invasive Treatment for Thoracolumbar Burst Fracture Using Sagittal Alignment Screws and A Trauma Reduction Device

Published on: November 8, 2024

1.1K

An explainable machine learning model predicts 30-day readmission after vertebral augmentation.

Chen Liu1,2, Qingyang Fu1, Wang Qifei3

  • 1Department of Orthopedics, Qilu Hospital, Shandong University, Jinan, Shandong 250000, China.

Iscience
|January 9, 2026
PubMed
Summary

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

[Influence of sampling satisfaction using endometrial sampling device and related factors for pathology diagnostic accordance rate].

Zhonghua fu chan ke za zhi·2014
Same author

Effect of the number of positive lymph nodes and lymph node ratio on prognosis of patients after resection of pancreatic adenocarcinoma.

Hepatobiliary & pancreatic diseases international : HBPD INT·2014
Same author

Mechanisms of human erythrocytic bioactivation of nitrite.

The Journal of biological chemistry·2014
Same author

Simulation research on the natural degradation process of PBDEs in soil polluted by e-waste under increased concentrations of atmospheric O(3).

Chemosphere·2014
Same author

Two-dimensional colloidal crystal assisted formation of conductive porous gold films with flexible structural controllability.

Journal of colloid and interface science·2014
Same author

REDD1 attenuates cardiac hypertrophy via enhancing autophagy.

Biochemical and biophysical research communications·2014

Osteoporotic vertebral compression fracture patients undergoing vertebral augmentation have high readmission risks. An interpretable machine learning model identified key predictors like frailty and comorbidities, enabling targeted interventions.

Area of Science:

  • Orthopedics and Traumatology
  • Medical Informatics
  • Geriatric Medicine

Background:

  • Osteoporotic vertebral compression fractures (OVCF) are common in elderly patients.
  • Vertebral augmentation procedures (VAPs) are frequently performed to treat OVCF.
  • Patients undergoing VAPs have a significant risk of 30-day hospital readmission.

Purpose of the Study:

  • To develop and validate an interpretable machine learning model to predict 30-day readmission risk in OVCF patients post-VAP.
  • To identify key clinical predictors contributing to readmission.
  • To create a tool for real-time risk stratification and personalized intervention.

Main Methods:

  • Utilized electronic health records (EHRs) from 3,947 OVCF patients who underwent VAPs between 2019 and 2024.
Keywords:
Machine learningOrthopedics

More Related Videos

3D Printing Model of a Patient's Specific Lumbar Vertebra
07:30

3D Printing Model of a Patient's Specific Lumbar Vertebra

Published on: April 14, 2023

2.5K

Related Experiment Videos

Last Updated: Jan 13, 2026

Minimally Invasive Treatment for Thoracolumbar Burst Fracture Using Sagittal Alignment Screws and A Trauma Reduction Device
04:19

Minimally Invasive Treatment for Thoracolumbar Burst Fracture Using Sagittal Alignment Screws and A Trauma Reduction Device

Published on: November 8, 2024

1.1K
3D Printing Model of a Patient's Specific Lumbar Vertebra
07:30

3D Printing Model of a Patient's Specific Lumbar Vertebra

Published on: April 14, 2023

2.5K
  • Evaluated eight machine learning algorithms using 10-fold cross-validation, with XGBoost demonstrating superior performance.
  • Employed SHapley Additive exPlanations (SHAPs) for model interpretability and identification of significant predictors.

    • Main Results:

    • The XGBoost model achieved high performance metrics (AUC, sensitivity, specificity, F1 score).
    • Key predictors identified include frailty, history of falls, prolonged hospitalization, specific comorbidities (pulmonary/kidney disease), advanced age, and hypoalbuminemia.
    • A functional clinical web application was developed for real-time risk assessment.

    Conclusions:

    • An interpretable machine learning model effectively predicts readmission risk in OVCF patients post-VAP.
    • Identifying high-risk patients through factors like frailty and comorbidities allows for targeted preventive strategies.
    • The developed tool can aid clinicians in proactive patient management, potentially reducing readmissions and healthcare costs.