Citation

BibTex format

@article{Pastika:2026:ehjdh/ztag118,
author = {Pastika, L and Patlatzoglou, K and Sieliwonczyk, E and Barker, J and Zeidaabadi, B and McGurk, KA and Barreto, SM and Camelo, L and Khan, S and Scott, WR and ORegan, DP and Duncan, BB and Schmidt, MI and Ware, JS and Misra, S and Kramer, DB and Waks, JW and Peters, NS and Ribeiro, ALP and Sau, A and Ng, FS},
doi = {ehjdh/ztag118},
journal = {European Heart Journal - Digital Health},
title = {Artificial Intelligence-Enhanced Electrocardiography for the Prediction of Future Type 2 Diabetes Mellitus: a model-development and multicentre validation study},
url = {http://dx.doi.org/10.1093/ehjdh/ztag118},
year = {2026}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - <jats:title>Abstract</jats:title>                  <jats:sec>                    <jats:title>Background</jats:title>                    <jats:p>A significant proportion of type 2 diabetes cases remain undiagnosed despite screening advances, carrying substantial cardiometabolic risk. Artificial intelligence-enhanced electrocardiography (AI-ECG) detects subtle ECG changes in subclinical disease, potentially enabling opportunistic screening.</jats:p>                  </jats:sec>                  <jats:sec>                    <jats:title>Methods</jats:title>                    <jats:p>We developed AIRE-DM, a convolutional neural network with discrete-time survival loss, for diagnosis of prevalent and prediction of incident type 2 diabetes. It was trained on 1,163,401 ECGs from 189,537 individuals from Beth Israel Deaconess Medical Center (BIDMC) and externally validated in UK Biobank (N = 65,606) and ELSA-Brasil (N = 13,739).</jats:p>                  </jats:sec>                  <jats:sec>                    <jats:title>Results</jats:title>                    <jats:p>AIRE-DM demonstrated moderate discrimination for prevalent type 2 diabetes (AUC: BIDMC 0.724, UK Biobank 0.733, ELSA-Brasil 0.706) and incident type 2 diabetes (C-index: BIDMC 0.667, UKB 0.688, ELSA-Brasil 0.625). The highest AIRE-DM risk quartile had elevated incident diabetes risk versus the lowest (HR: BIDMC 4.75, UKB 7.52, ELSA-Brasil 3.96). AIRE-DM was non-inferior to the ADA Diabetes Risk Test in BIDMC, with improved predictive accuracy when combined. In normoglycaemic patients, AIRE-DM was superior to HbA1c for predicting incident diabetes in BIDMC and non-inferior in ELSA-Brasil. The highest risk quartile reached 5% cumulative T2DM incidence 5.4 years (BIDMC) and 4.8 years (ELSA-Brasil) earlier than the lowest risk quartile, after adjusting for HbA1c, age and sex.
AU  - Pastika,L
AU  - Patlatzoglou,K
AU  - Sieliwonczyk,E
AU  - Barker,J
AU  - Zeidaabadi,B
AU  - McGurk,KA
AU  - Barreto,SM
AU  - Camelo,L
AU  - Khan,S
AU  - Scott,WR
AU  - ORegan,DP
AU  - Duncan,BB
AU  - Schmidt,MI
AU  - Ware,JS
AU  - Misra,S
AU  - Kramer,DB
AU  - Waks,JW
AU  - Peters,NS
AU  - Ribeiro,ALP
AU  - Sau,A
AU  - Ng,FS
DO  - ehjdh/ztag118
PY  - 2026///
TI  - Artificial Intelligence-Enhanced Electrocardiography for the Prediction of Future Type 2 Diabetes Mellitus: a model-development and multicentre validation study
T2  - European Heart Journal - Digital Health
UR  - http://dx.doi.org/10.1093/ehjdh/ztag118
UR  - https://doi.org/10.1093/ehjdh/ztag118
ER  -
Download