ECG features improve multimodal deep learning prediction of incident T2DM in a Middle Eastern cohort

Abstract Type 2 Diabetes Mellitus (T2DM) remains a significant global health challenge, underscoring the need for early and accurate risk prediction tools to enable timely interventions. This study introduces ECG-DiaNet, a multimodal deep learning model that integrates electrocardiogram (ECG) featur...

Full description

Saved in:
Bibliographic Details
Main Authors: Farida Mohsen, Ali Safa, Zubair Shah
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-12633-z
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849333398514958336
author Farida Mohsen
Ali Safa
Zubair Shah
author_facet Farida Mohsen
Ali Safa
Zubair Shah
author_sort Farida Mohsen
collection DOAJ
description Abstract Type 2 Diabetes Mellitus (T2DM) remains a significant global health challenge, underscoring the need for early and accurate risk prediction tools to enable timely interventions. This study introduces ECG-DiaNet, a multimodal deep learning model that integrates electrocardiogram (ECG) features with established clinical risk factors (CRFs) to improve the prediction of T2DM onset. Using data from the Qatar Biobank (QBB), we compared ECG-DiaNet against unimodal models based solely on ECG or CRFs. A development cohort (n = 2043) was utilized for model training and internal validation, while a separate longitudinal cohort (n = 395) with a median five-year follow-up served as the test set. ECG-DiaNet demonstrated superior predictive performance, achieving a higher area under the receiver operating characteristic curve (AUROC) compared to the CRF-only model (0.845vs.0.8217), which was statistically significant based on the DeLong test (p < 0.001), thus highlighting the added predictive value of incorporating ECG signals. Reclassification metrics reinforced these improvements, with a significant Net Reclassification Improvement (NRI = 0.0153,p < 0.001) and Integrated Discrimination Improvement (IDI = 0.0482,p = 0.0099), confirming the enhanced risk stratification. Furthermore, stratifying participants into Low-, Medium-, and High-risk categories revealed that ECG-DiaNet achieved a higher positive predictive value (PPV) in the high-risk group compared to CRF-only models. These findings, together with the non-invasive nature and wide accessibility of ECG technology, suggest the potential of ECG-DiaNet for clinical implementation. However, further validation using larger and more diverse datasets is needed to improve generalizability.
format Article
id doaj-art-610e5fd4c5a34bbdac8233c478bb670e
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-610e5fd4c5a34bbdac8233c478bb670e2025-08-20T03:45:52ZengNature PortfolioScientific Reports2045-23222025-07-0115111110.1038/s41598-025-12633-zECG features improve multimodal deep learning prediction of incident T2DM in a Middle Eastern cohortFarida Mohsen0Ali Safa1Zubair Shah2College of Science and Engineering, Hamad Bin Khalifa UniversityCollege of Science and Engineering, Hamad Bin Khalifa UniversityCollege of Science and Engineering, Hamad Bin Khalifa UniversityAbstract Type 2 Diabetes Mellitus (T2DM) remains a significant global health challenge, underscoring the need for early and accurate risk prediction tools to enable timely interventions. This study introduces ECG-DiaNet, a multimodal deep learning model that integrates electrocardiogram (ECG) features with established clinical risk factors (CRFs) to improve the prediction of T2DM onset. Using data from the Qatar Biobank (QBB), we compared ECG-DiaNet against unimodal models based solely on ECG or CRFs. A development cohort (n = 2043) was utilized for model training and internal validation, while a separate longitudinal cohort (n = 395) with a median five-year follow-up served as the test set. ECG-DiaNet demonstrated superior predictive performance, achieving a higher area under the receiver operating characteristic curve (AUROC) compared to the CRF-only model (0.845vs.0.8217), which was statistically significant based on the DeLong test (p < 0.001), thus highlighting the added predictive value of incorporating ECG signals. Reclassification metrics reinforced these improvements, with a significant Net Reclassification Improvement (NRI = 0.0153,p < 0.001) and Integrated Discrimination Improvement (IDI = 0.0482,p = 0.0099), confirming the enhanced risk stratification. Furthermore, stratifying participants into Low-, Medium-, and High-risk categories revealed that ECG-DiaNet achieved a higher positive predictive value (PPV) in the high-risk group compared to CRF-only models. These findings, together with the non-invasive nature and wide accessibility of ECG technology, suggest the potential of ECG-DiaNet for clinical implementation. However, further validation using larger and more diverse datasets is needed to improve generalizability.https://doi.org/10.1038/s41598-025-12633-z
spellingShingle Farida Mohsen
Ali Safa
Zubair Shah
ECG features improve multimodal deep learning prediction of incident T2DM in a Middle Eastern cohort
Scientific Reports
title ECG features improve multimodal deep learning prediction of incident T2DM in a Middle Eastern cohort
title_full ECG features improve multimodal deep learning prediction of incident T2DM in a Middle Eastern cohort
title_fullStr ECG features improve multimodal deep learning prediction of incident T2DM in a Middle Eastern cohort
title_full_unstemmed ECG features improve multimodal deep learning prediction of incident T2DM in a Middle Eastern cohort
title_short ECG features improve multimodal deep learning prediction of incident T2DM in a Middle Eastern cohort
title_sort ecg features improve multimodal deep learning prediction of incident t2dm in a middle eastern cohort
url https://doi.org/10.1038/s41598-025-12633-z
work_keys_str_mv AT faridamohsen ecgfeaturesimprovemultimodaldeeplearningpredictionofincidentt2dminamiddleeasterncohort
AT alisafa ecgfeaturesimprovemultimodaldeeplearningpredictionofincidentt2dminamiddleeasterncohort
AT zubairshah ecgfeaturesimprovemultimodaldeeplearningpredictionofincidentt2dminamiddleeasterncohort