External Validation of a Hip-Worn Accelerometry-Based Machine Learning Model for Physical Behavior Classification in Free-Living Conditions

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62690094%3A18470%2F25%3A50023032" target="_blank" >RIV/62690094:18470/25:50023032 - isvavai.cz</a>

Result on the web

<a href="https://journals.humankinetics.com/view/journals/jmpb/8/1/article-jmpb.2025-0030.xml" target="_blank" >https://journals.humankinetics.com/view/journals/jmpb/8/1/article-jmpb.2025-0030.xml</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1123/jmpb.2025-0030" target="_blank" >10.1123/jmpb.2025-0030</a>

Result language

angličtina

Original language name

External Validation of a Hip-Worn Accelerometry-Based Machine Learning Model for Physical Behavior Classification in Free-Living Conditions

Original language description

Background: Accurate classification of physical behavior from accelerometer data is crucial for health and behavioral research. While machine learning models often perform well within the populations they are trained on, they are rarely validated on independent populations, and their generalizability remains poorly understood. Therefore, we aimed to externally validate a widely used random forest model for physical behavior classification, and to assess whether its performance varied by participants’ age, sex, or body mass index. Methods: We validated the random forest classifier, trained by Ellis et al., which achieved a balanced accuracy of 79% for classifying sitting, standing, and walking/running from hip-worn accelerometer data in the original training population. For the external validation, we obtained ActiGraph recordings for 610 participants from four European countries from the WEALTH (WEarable sensor Assessment of physicaL and eaTing beHaviors) project, which were labeled with the corresponding free-living behavior using ecological momentary assessment. Classifier performance was assessed using confusion matrices, precision, recall, F-score, and balanced accuracy. Results: In the WEALTH population, the random forest classifier achieved a balanced accuracy of 40% and an average F-score of 0.33. Precision and recall were highest for sitting, followed by walking/running and standing. Performance was consistent across subpopulations defined by age, sex, and body mass index. Conclusion: The substantial reduction in accuracy demonstrates the limited generalizability of the existing random forest classifier. Our findings underscore the need for external validation and more diverse training data to ensure robust application of machine learning models in physical behavior research. © 2025 Human Kinetics, Inc.

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

R - Projekt Ramcoveho programu EK

Publication year

2025

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Journal for the Measurement of Physical Behaviour

ISSN

2575-6605

e-ISSN

2575-6613

Volume of the periodical

8

Issue of the periodical within the volume

1

Country of publishing house

US - UNITED STATES

Number of pages

9

Pages from-to

"Article Number: 20250030"

UT code for WoS article

001678562800007

EID of the result in the Scopus database

2-s2.0-105027529261