Wearable sensor-based analysis of heart rate variability as a biomarker for ischemic heart disease

Nurdaulet Tasmurzayev (), Bibars Amangeldy (), Imanbek Baglan (), Zhanel Baigarayeva () and Akzhan Konysbekova ()

International Journal of Innovative Research and Scientific Studies, 2025, vol. 8, issue 5, 1909-1925

Abstract: Cardiovascular diseases are the leading global cause of death, with ischemic heart disease (IHD) being the most prevalent and deadly subtype, emphasizing the need for accessible, non-invasive screening tools. Heart rate variability (HRV) is a recognized indicator of autonomic imbalance and a predictor of adverse cardiac events; however, standard diagnosis relies on 24-hour Holter electrocardiography, which limits its widespread application. This study introduces the Zhurek fingertip IoT device, a photoplethysmography (PPG)-based tool for measuring HRV parameters, and evaluates its ability to distinguish between healthy autonomic function and IHD-related dysregulation. A comparative analysis with a three-lead Holter ECG showed clinically acceptable mean deviations: –0.601 bpm for heart rate, +33.1 ms for SDNN, and –4.8 ms for RMSSD. HRV segment data were obtained from patients at the Cardiology Center in Almaty, Kazakhstan, with angiographically confirmed IHD. Eight features were measured, including SDNN, RMSSD, LF, HF, LF/HF ratio, Max HR, BMI, and age. Mann–Whitney U tests revealed significant differences between groups for SDNN, LF, HF, Max HR, BMI, and age (p < 0.05). Principal component analysis indicated that the first two components, accounting for 49.5% of the total variance, effectively separated the cohorts without labels. Feature importance analysis using CatBoost demonstrated that LF power had the greatest discriminative weight (~44%), followed by age (~19%) and HF power, with smaller contributions from maximum heart rate and RMSSD. These findings demonstrate that diagnostically relevant autonomic signatures are preserved in PPG recordings, reducing monitoring time compared to standard Holter studies while maintaining physiological fidelity. The pilot study confirms the suitability of the Zhurek wearable device and healthy-baseline machine learning pipelines for large-scale, ambulatory IHD risk stratification, supporting a shift from reactive intervention to proactive prevention.

Keywords: Cardiovascular diseases; Heart rate variability; IoT device; Ischemic heart disease; Machine learning; Photoplethysmography; Risk stratification. (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://ijirss.com/index.php/ijirss/article/view/9317/2093 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:aac:ijirss:v:8:y:2025:i:5:p:1909-1925:id:9317

Access Statistics for this article

International Journal of Innovative Research and Scientific Studies is currently edited by Natalie Jean

More articles in International Journal of Innovative Research and Scientific Studies from Innovative Research Publishing
Bibliographic data for series maintained by Natalie Jean ().