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: Jul 9, 2026

Measuring Frailty in HIV-infected Individuals. Identification of Frail Patients is the First Step to Amelioration and Reversal of Frailty
05:53

Measuring Frailty in HIV-infected Individuals. Identification of Frail Patients is the First Step to Amelioration and Reversal of Frailty

Published on: July 24, 2013

Interpretable machine learning framework for frailty risk prediction using NHANES 2007-2018: A cross-sectional study.

Xinyan Liu1,2, Zihe Feng3,4, Zipeng Wu5

  • 1Medical School of Chinese PLA, Beijing, China.

Medicine
|July 7, 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

Top Electrode-Free Electrochromic Device with Ultra-Flexibility and Wide Color Gamut Based on Porous Resonant Cavity.

Small (Weinheim an der Bergstrasse, Germany)·2025
Same author

Van der Waals Ferroelectric CuCrP<sub>2</sub>S<sub>6</sub>-Enabled Hysteresis-Free Negative Capacitance Field-Effect Transistors.

Advanced materials (Deerfield Beach, Fla.)·2025
Same author

Astragaloside IV Attenuates Angiotensin II-Induced Inflammatory Responses in Endothelial Cells: Involvement of Mitochondria.

Journal of inflammation research·2025
Same author

Comparative analysis of physicochemical properties, antioxidant activities, and metabolomic profiles in daylily-supplemented craft beer fermented with different <i>Saccharomyces</i> strains.

Food chemistry: X·2025
Same author

Platform of Oxidative Transformation of α-Methyl Secondary Enaminones toward Tetrahydropyridines.

The Journal of organic chemistry·2025
Same author

A PheWAS approach to identify associations of GBA1 variants with comprehensive phenotypes beyond neurological diseases.

NPJ Parkinson's disease·2025

This study developed an interpretable machine learning framework for frailty risk prediction. The Automatic Piecewise Linear Regression (APLR) model achieved high accuracy and interpretability, outperforming other methods in identifying frailty risk factors.

Area of Science:

  • Gerontology
  • Biostatistics
  • Machine Learning

Background:

  • Frailty is a clinical syndrome linked to adverse health outcomes.
  • Current prediction models often lack interpretability, hindering clinical application.
  • Developing accurate and transparent frailty prediction tools is crucial.

Purpose of the Study:

  • To develop and validate an interpretable machine learning framework for frailty risk prediction.
  • To compare the performance of the interpretable framework against traditional models.
  • To identify key predictors of frailty in a diverse adult population.

Main Methods:

  • Cross-sectional analysis of 3817 adults from the National Health and Nutrition Examination Survey (NHANES, 2007-2018).
  • Frailty defined using a deficit accumulation Frailty Index (FI ≥ 0.21).
Keywords:
anchor explanationsautomated piecewise linear regressionfrailty predictioninflammatory biomarkersmachine learningmetabolic biomarkers

More Related Videos

Frailty Assessment in an Aging Mouse Model
06:58

Frailty Assessment in an Aging Mouse Model

Published on: September 23, 2025

Related Experiment Videos

Last Updated: Jul 9, 2026

Measuring Frailty in HIV-infected Individuals. Identification of Frail Patients is the First Step to Amelioration and Reversal of Frailty
05:53

Measuring Frailty in HIV-infected Individuals. Identification of Frail Patients is the First Step to Amelioration and Reversal of Frailty

Published on: July 24, 2013

Frailty Assessment in an Aging Mouse Model
06:58

Frailty Assessment in an Aging Mouse Model

Published on: September 23, 2025

  • Developed a 3-tier interpretable framework using Automatic Piecewise Linear Regression (APLR) and compared it with XGBoost and logistic regression (LR) using 10-fold cross-validation.

    • Main Results:

    • APLR achieved the highest Area Under the Receiver Operating Characteristic Curve (AUC) of 0.801 ± 0.018, outperforming XGBoost and LR.
    • Top predictors in the full sample included body mass index (BMI), poverty-income ratio (PIR), and age.
    • In adults aged 60+, APLR maintained superior AUC (0.799 ± 0.022), with blood urea nitrogen (BUN) emerging as a key predictor.

    Conclusions:

    • The APLR-based interpretable framework offers a promising approach for frailty risk stratification, balancing accuracy and clinical transparency.
    • The framework is particularly relevant for older adults, highlighting the importance of renal function.
    • Further external and longitudinal validation is recommended before clinical deployment.