ORIGINAL RESEARCH article
Front. Physiol.
Sec. Computational Physiology and Medicine
Volume 16 - 2025 | doi: 10.3389/fphys.2025.1649204
A NOVEL DEEP LEARNING APPROACH TO DETECT DIABETES MELLITUS USING HEART RATE REEHANA SK1 SIDDIQUE IBRAHIM S P2 1,2School of Computer Science and Engineering, VIT AP-University, Amaravati, Andhra Pradesh, India Correspondence author: email: siddique.ibrahim@vitap.ac.in
Provisionally accepted
Reehana Shaik
Siddique Ibrahim S P*- VIT-AP University, Amaravati, India
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
ABSTRACT: Diabetes Mellitus[DM], or diabetes, is an overtime metabolic disorder characterized by increased blood sugar levels. The condition arises because to a deficiency of insulin, a hormone synthesized by the pancreas, or due to the body's resistance to its physiological effects. Diabetes has the potential to give rise to significant complications such as pulmonary infection, renal in-sufficiency, and visual impairment. It can be managed through lifestyle changes, medication, and insulin therapy. The purpose of this research is to develop a computerized system that can categorize people into healthy and diabetic groups using heart rate (HR) data from electrocardiogram (ECG) signals. The theoretical basis for the classification is the Kernel Sparse and Temporal Feature Representation Classifier (KSFTRC) and the Multi-Spectrum Operator (MSO) using a Time Series analysis approach of Heart Rate i.e., ECG signal. Our findings suggest that a small set of parameters can provide the highest diagnostic classification performance. By employing the proposed classifier evaluated on the ten-fold cross-validation, it has shown that the average precision of 97.84%, sensitivity of 95.71%, and specificity of 96.57%. The efficacy of this strategy is also assessed in comparison to other established techniques in order to ascertain the robustness of the proposed model in classifying diabetes based on an HR signal.
Keywords: Diabetes Mellitus, deep learning, classifier, Heart rate monitors, feature extraction
Received: 24 Jun 2025; Accepted: 24 Sep 2025.
Copyright: © 2025 Shaik and S P. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Siddique Ibrahim S P, siddique.ibrahim@vitap.ac.in
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.