Copyright: ©Author(s) 2026. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial (CC BY-NC 4.0) license. No commercial re-use. See permissions. Published by Baishideng Publishing Group Inc.
World J Cardiol. Mar 26, 2026; 18(3): 116217
Published online Mar 26, 2026. doi: 10.4330/wjc.v18.i3.116217
Published online Mar 26, 2026. doi: 10.4330/wjc.v18.i3.116217
Machine learning-based detection of diabetes mellitus from single-lead electrocardiography: A phenotype-stratified approach
Anna Dmitrievna Karbovskaya, State Budgetary Healthcare Institution of the Tver Region, Konakovskaya Central District Hospital, Moscow 11953, Russia
Basheer Abdullah Marzoog, Anastasia Stroeva, Alexander Suvorov, Peter Chomakhidze, Daria Gognieva, Natalia Kuznetsova, Philipp Kopylov, Institute of Personalized Cardiology of the Center “Digital Biodesign and Personalized Healthcare” of Biomedical Science and Technology Park, Sechenov First Moscow State Medical University, Moscow 119991, Russia
Abromavich Syrkin, Department of Cardiology, Functional and Ultrasound Diagnostics, Sechenov First Moscow State Medical University, Moscow 119991, Russia
Valentin V Fadeev, Sevindzh M Ismailova, Irina V Poluboyarinova, Sechenov First Moscow State Medical University, Moscow 119991, Russia
Co-first authors: Anna Dmitrievna Karbovskaya and Basheer Abdullah Marzoog.
Author contributions: Karbovskaya AD contributed to data acquisition; Marzoog BA contributed to write the original draft and review; Karbovskaya AD and Marzoog BA contributed equally to this manuscript as co-first authors; Stroeva A contributed to biostatistical analysis of the sample; Suvorov A, Chomakhidze P, Gognieva D, Kuznetsova N, Syrkin A, Fadeev VV, Ismailova SM, and Poluboyarinova IV contributed to data collection; Chomakhidze P, Fadeev VV, Syrkin A, and Kopylov P contributed to concept development; Kopylov P contributed to project supervision. All authors have read and approved the final version of the manuscript.
Supported by the Government Assignment Application of Mass Spectrometry and Exhaled Air Emission Spectrometry for Cardiovascular Risk Stratification, No. 1023022600020-6; and the Priority 2030 Program of the Ministry of Science and Higher Education of Russia, No. 03.000.B.163 and No. 03.000. B. 166.
Institutional review board statement: This study was conducted at the I.M. Sechenov First Moscow State Medical University (Sechenov University), Moscow, Russia. The study protocol was approved by the Local Ethical Committee of Sechenov University (approval No. 19-23). Study registered at clinicaltrails.gov (ID: NCT04788342).
Informed consent statement: All study participants, or their legal guardian, provided informed written consent prior to study enrollment.
Conflict-of-interest statement: All the authors report no relevant conflicts of interest for this article.
STROBE statement: The authors have read the STROBE Statement-checklist of items, and the manuscript was prepared and revised according to the STROBE Statement-checklist of items.
Data sharing statement: Applicable on reasonable request.
Corresponding author: Basheer Abdullah Marzoog, MD, PhD, Researcher, Institute of Personalized Cardiology of The Center “Digital Biodesign and Personalized Healthcare” of Biomedical Science and Technology Park, Sechenov First Moscow State Medical University, 8-2 Trubetskaya Street, Moscow 119991, Russia. marzug@mail.ru
Received: November 5, 2025
Revised: November 19, 2025
Accepted: January 12, 2026
Published online: March 26, 2026
Processing time: 138 Days and 9.5 Hours
Revised: November 19, 2025
Accepted: January 12, 2026
Published online: March 26, 2026
Processing time: 138 Days and 9.5 Hours
Core Tip
Core Tip: This study introduces a crucial paradigm shift for non-invasive diabetes detection using electrocardiography. Instead of a one-size-fits-all model, we employed phenotypic clustering to disentangle the confounding effects of cardiovascular disease. We identified a specific patient profile (cluster 4: High diabetes prevalence with significant but non-severe comorbidities) where a machine learning model, analyzing single-lead electrocardiography features like T-wave morphology and atrial conduction, achieves optimal and clinically viable performance (area under the curve: 0.88). This proves that diabetes-specific cardiac “whispers” are detectable, but only with a precision medicine approach that tailors diagnostics to distinct clinical phenotypes.