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.
Machine learning-based detection of diabetes mellitus from single-lead electrocardiography: A phenotype-stratified approach
Anna Dmitrievna Karbovskaya, Basheer Abdullah Marzoog, Anastasia Stroeva, Alexander Suvorov, Peter Chomakhidze, Daria Gognieva, Natalia Kuznetsova, Abromavich Syrkin, Valentin V Fadeev, Sevindzh M Ismailova, Irina V Poluboyarinova, Philipp Kopylov
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 4.1 Hours
BACKGROUND
Diabetes mellitus (DM) and the related sequalae remains one of the most frequently reported cause of morbidity and mortality in our era. This returns to the non-sufficient screening methods for DM at early stages.
AIM
To assess the diagnostic capabilities of the parameters of single lead electrocardiography (ECG) in the diagnosis of DM utilizing machine learning model.
METHODS
A single center study involved 629 participants with vs without DM. All the study participants passed transthoracic echocardiography, fasting blood glucose measurement, standard 12-lead ECG recording, and single lead ECG registration using the Cardio-Qvark® device. A gradient boosting machine model, specifically the XGBoost implementation, was developed using R v4.2 and Python v3.10. The model was trained and validated using a novel cluster-stratified approach - training on three phenotypic clusters and testing on the fourth - to isolate DM-specific ECG signatures from confounding cardiovascular disease.
RESULTS
The cluster-stratified analysis revealed that the model performed best in cluster 4 (patients with high DM prevalence and significant comorbidities), achieving a sensitivity of 75%, specificity of 83%, and an area under the curve of 88%.
CONCLUSION
This study demonstrates that a phenotype-stratified approach is crucial for effective ECG-based DM screening. By identifying a specific clinical profile (cluster 4: High comorbidity burden with preserved cardiac function), we developed a model that accurately detects DM from a single-lead ECG. This phenotype-specific strategy overcomes the confounding effect of cardiovascular disease, moving beyond one-size-fits-all algorithms towards a precise and clinically viable tool for non-invasive DM detection in high-risk populations.
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.
