Search research articles

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

Comparative study of imputation strategies to improve the sarcopenia prediction task.

Digital health·2025

Same author

Machine Learning for Sarcopenia Prediction in the Elderly Using Socioeconomic, Infrastructure, and Quality-of-Life Data.

Healthcare (Basel, Switzerland)·2023

Same author

Machine Learning Applications in Sarcopenia Detection and Management: A Comprehensive Survey.

Healthcare (Basel, Switzerland)·2023

Same author

Underwater Wireless Sensor Networks with RSSI-Based Advanced Efficiency-Driven Localization and Unprecedented Accuracy.

Sensors (Basel, Switzerland)·2023

Same author

A Multimodal IoT-Based Locomotion Classification System Using Features Engineering and Recursive Neural Network.

Sensors (Basel, Switzerland)·2023

Same author

Coalition Formation Game for Cost-Efficient Multiparty Payment Channel in Payment Channel Networks.

Sensors (Basel, Switzerland)·2023

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jul 30, 2025

Segmentation and Linear Measurement for Body Composition Analysis using Slice-O-Matic and Horos

Segmentation and Linear Measurement for Body Composition Analysis using Slice-O-Matic and Horos

Published on: March 21, 2021

Sarcopenia Prediction for Elderly People Using Machine Learning: A Case Study on Physical Activity.

Minje Seok¹, Wooseong Kim¹

¹Computer Engineering Department, Gachon University, Seongnam 13120, Gyeonggi, Republic of Korea.

Healthcare (Basel, Switzerland)

|May 13, 2023

Summary

This summary is machine-generated.

Predicting age-related sarcopenia is improved by machine learning models using physical activity (PA) and obesity data. Deep neural networks achieved up to 90% accuracy, highlighting PA and waist circumference as key predictors.

Keywords:

KNHANES elderly machine learning physical activity sarcopenia

More Related Videos

The Creation of a Rat Model for Osteosarcopenia via Ovariectomy

The Creation of a Rat Model for Osteosarcopenia via Ovariectomy

Published on: February 21, 2025

Improving Strength, Power, Muscle Aerobic Capacity, and Glucose Tolerance through Short-term Progressive Strength Training Among Elderly People

Improving Strength, Power, Muscle Aerobic Capacity, and Glucose Tolerance through Short-term Progressive Strength Training Among Elderly People

Published on: July 5, 2017

Related Experiment Videos

Last Updated: Jul 30, 2025

Segmentation and Linear Measurement for Body Composition Analysis using Slice-O-Matic and Horos

Segmentation and Linear Measurement for Body Composition Analysis using Slice-O-Matic and Horos

Published on: March 21, 2021

The Creation of a Rat Model for Osteosarcopenia via Ovariectomy

The Creation of a Rat Model for Osteosarcopenia via Ovariectomy

Published on: February 21, 2025

Improving Strength, Power, Muscle Aerobic Capacity, and Glucose Tolerance through Short-term Progressive Strength Training Among Elderly People

Improving Strength, Power, Muscle Aerobic Capacity, and Glucose Tolerance through Short-term Progressive Strength Training Among Elderly People

Published on: July 5, 2017

Area of Science:

Gerontology
Biomedical Engineering
Machine Learning

Background:

Sarcopenia, an age-related muscle disorder, is linked to musculoskeletal issues and metabolic syndromes like sarcopenic obesity.
Predictive models for sarcopenia often rely on factors requiring medical equipment.
Physical activity (PA) is a measurable risk factor, accessible via personal devices and lifelogs.

Purpose of the Study:

To explore the impact of daily physical activity and obesity on sarcopenia prediction.
To demonstrate the feasibility of using machine learning for sarcopenia prediction with accessible data.
To compare the performance of various machine learning models in predicting sarcopenia.

Main Methods:

Utilized data from the Korea National Health and Nutrition Examination Survey.
Trained multiple machine learning models: DNN, GBM, XGB, LGB, CAT, Logistic Regression, SVC, KNN, RF.
Evaluated models using PA features, obesity metrics (total fat mass, fat percentage, waist circumference), and SHAP analysis for feature importance.

Main Results:

Deep Neural Network (DNN) achieved 81% accuracy with PA features alone.
Accuracy increased to 90% with the addition of obesity information (fat mass, fat percentage).
DNN achieved 84% accuracy using PA and waist circumference, outperforming other models.
Several models (GBM, XGB, LGB, CAT, RF, DNN) showed significant predictive performance (AUC ~0.85-0.9) with PA and waist circumference.
Key predictors identified: quantified PA, metabolic equivalent score, BMI, and waist circumference.

Conclusions:

Machine learning models, particularly DNNs, can effectively predict sarcopenia using accessible physical activity and obesity data.
Waist circumference serves as a practical and accurate obesity metric for sarcopenia prediction when combined with PA.
Quantified PA and simple obesity measures are crucial features for developing accurate sarcopenia predictive models.