EUVIMEDEUVIMED entdecken
Crossref

Prediction of Skeletal Muscle Mass Measured by Bioelectrical Impedance Analysis in Older Adults Using Anthropometric Data

Jun-Hee Kim iD

Australasian Journal on Ageing · 2026-06 · 45 (2)

DOI: 10.1111/ajag.70167 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Australasian Journal on Ageing, online erschienen am 22.04.2026. Verfasst von Jun-Hee Kim. Beteiligte Einrichtung: Department of Physical Therapy, College of Software and Digital Healthcare Convergence, Yonsei University, Wonju, South Korea. Hauptthemen laut MEDLINE: Electric Impedance, Muscle, Skeletal, Sarcopenia, Anthropometry. Die Arbeit nennt 37 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

Accurate estimation of skeletal muscle mass is a key component in the screening for sarcopenia. Anthropometric parameters provide a non‐invasive, cost‐effective alternative, yet their predictive capability can be enhanced with machine learning. This study aimed to develop and evaluate machine learning models to predict skeletal muscle mass measured by bioelectrical impedance analysis (BIA) in individuals aged 70 years and older using anthropometric measurements and demographic data.

Methods

Anthropometric data from 984 older adults aged 70 years and older were obtained from the 8th Size Korea Human Body Measurement Survey. Data preprocessing included removing missing values, applying Min‐Max scaling and selecting relevant features. Machine learning models were developed, optimised using a tuning framework and evaluated through error metrics, residual analysis and feature importance interpretation.

Results

Among the machine learning models, XGBoost achieved the highest predictive accuracy (RMSE = 1.29, R 2 = 0.92) while using the fewest predictors (18), demonstrating efficiency and effectiveness. Key features included calf circumference, gender, weight, height and waist circumference. SHapley Additive exPlanations analysis emphasised the dominant role of calf circumference, reinforcing its predictive capability for skeletal muscle mass.

Conclusions

This study highlights the potential of machine learning for predicting skeletal muscle mass using non‐invasive anthropometric measurements. These findings support the proposed model as a scalable and cost‐effective tool for estimating skeletal muscle mass, which is a key quantitative component of sarcopenia screening.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Electric ImpedanceMuscle, SkeletalSarcopeniaAnthropometryBody CompositionAgingMachine LearningHumansAgedFemaleMalePredictive Value of TestsPredictive Learning ModelsAge FactorsAged, 80 and overBoosting Machine Learning AlgorithmsReproducibility of ResultsRepublic of KoreaGeriatric AssessmentWaist Circumference

Stichwörter der Autor:innen

ageinganthropometrymachine learningsarcopeniaskeletal muscle

Autor:innen und Institutionen

  • Department of Physical Therapy, College of Software and Digital Healthcare Convergence, Yonsei University, Wonju, South Korea.

ORCID-Profile: Jun-Hee Kim

Zitieren

APA

Kim, J. H. (2026). Prediction of Skeletal Muscle Mass Measured by Bioelectrical Impedance Analysis in Older Adults Using Anthropometric Data. Australasian Journal on Ageing, 45(2). https://doi.org/10.1111/ajag.70167

Vancouver

Kim JH. Prediction of Skeletal Muscle Mass Measured by Bioelectrical Impedance Analysis in Older Adults Using Anthropometric Data. Australasian Journal on Ageing. 2026;45(2). doi:10.1111/ajag.70167

BibTeX
@article{Kim2026,
  author = {Kim, Jun-Hee},
  title = {Prediction of Skeletal Muscle Mass Measured by Bioelectrical Impedance Analysis in Older Adults Using Anthropometric Data},
  journal = {Australasian Journal on Ageing},
  year = {2026},
  volume = {45},
  number = {2},
  doi = {10.1111/ajag.70167}
}
Kostenlos starten →