Page 109 - AIH-2-4

Artificial Intelligence in Health

ORIGINAL RESEARCH ARTICLE
Stratifying autonomic nervous system regulation

patterns in healthy men: A machine learning
approach

Wollner Materko *
1,2
1 Department of Health, Faculty of of Health Sciences, Federal University of Amapá, Macapá,
Amapá, Brazil
2 Department of Education, Faculty of Physical Education, Federal University of Amapá, Macapá,
Amapá, Brazil

Abstract

Heart rate variability (HRV) is a critical non-invasive marker of autonomic nervous
system regulation and plays an essential role in cardiovascular health. Individual
differences in autonomic function necessitate the development of personalized
health strategies. This study aimed to develop and validate a method that integrates
principal component analysis (PCA) and K-means clustering to identify distinct
patterns of autonomic regulation in healthy men using HRV data. A total of 80
young, healthy men (22.0 ± 2.8 years old, 65.2 ± 6.9 kg, and 171.0 ± 6.5 cm) were
recruited, and their HRV data were analyzed using time-domain and frequency-
domain parameters. PCA was applied to reduce the dimensionality of the HRV
data, while K-means clustering was employed to identify distinct autonomic
*Corresponding author: profiles. Silhouette index values were 0.397 for one cluster, 0.481 for two clusters,
Wollner Materko and 0.556 for three clusters, indicating that the three-cluster solution provided the
(wollner.materko@gmail.com)
best fit. Three statistically distinct and physiologically meaningful clusters were
Citation: Materko W. Stratifying identified. Cluster 3 (n = 19) demonstrated significantly higher HRV parameters
autonomic nervous system
regulation patterns in healthy than cluster 1 (n = 33) and cluster 2 (n = 28) (p = 0.001). Post hoc analysis further
men: A machine learning approach. confirms that cluster 1 differed significantly from both cluster 2 and cluster 3 (p =
Artif Intell Health. 2025;2(4):103-113. 0.001). Based on HRV characteristics, the clusters were characterized as “high vagal
doi: 10.36922/AIH025050006 tone,” “intermediate vagal tone,” and “low vagal tone.” The “high vagal tone” cluster
Received: January 29, 2025 exhibited the strongest parasympathetic activity, while the “low vagal tone” cluster
Revised: June 24, 2025 showed evidence of sympathetic predominance. This study demonstrates a robust
approach for stratifying autonomic profiles, highlighting the potential of machine
Accepted: June 30, 2025 learning in advancing personalized cardiovascular health assessment.
Published online: July 28, 2025
Copyright: © 2025 Author(s). Keywords: Heart rate variability; Autonomic nervous system; Machine learning; Principal
This is an Open-Access article
distributed under the terms of the component analysis; K-means clustering
Creative Commons Attribution
License, permitting distribution,
and reproduction in any medium,
provided the original work is
properly cited. 1. Introduction
Publisher’s Note: AccScience Cardiovascular diseases (CVDs) represent a significant global health burden,
Publishing remains neutral with accounting for an estimated 17.9 million deaths annually, according to the World Health
regard to jurisdictional claims in 1
published maps and institutional Organization. Heart rate monitoring serves as an effective method for detecting cardiac
affiliations. irregularities, such as arrhythmias. Continuous heart rate analysis facilitates early

Volume 2 Issue 4 (2025) 103 doi: 10.36922/AIH025050006