A deep learning digital biomarker to detect hypertension and stratify cardiovascular risk from the electrocardiogram
Abstract Hypertension is a major risk factor for cardiovascular disease (CVD), yet blood pressure is measured intermittently and under suboptimal conditions. We developed a deep learning model to identify hypertension and stratify risk of CVD using 12-lead electrocardiogram waveforms. HTN-AI was tra...
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-025-01491-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849723981474562048 |
|---|---|
| author | Mostafa A. Al-Alusi Samuel F. Friedman Shinwan Kany Joel T. Rämö Daniel Pipilas Pulkit Singh Christopher Reeder Shaan Khurshid James P. Pirruccello Mahnaz Maddah Jennifer E. Ho Patrick T. Ellinor |
| author_facet | Mostafa A. Al-Alusi Samuel F. Friedman Shinwan Kany Joel T. Rämö Daniel Pipilas Pulkit Singh Christopher Reeder Shaan Khurshid James P. Pirruccello Mahnaz Maddah Jennifer E. Ho Patrick T. Ellinor |
| author_sort | Mostafa A. Al-Alusi |
| collection | DOAJ |
| description | Abstract Hypertension is a major risk factor for cardiovascular disease (CVD), yet blood pressure is measured intermittently and under suboptimal conditions. We developed a deep learning model to identify hypertension and stratify risk of CVD using 12-lead electrocardiogram waveforms. HTN-AI was trained to detect hypertension using 752,415 electrocardiograms from 103,405 adults at Massachusetts General Hospital. We externally validated HTN-AI and demonstrated associations between HTN-AI risk and incident CVD in 56,760 adults at Brigham and Women’s Hospital. HTN-AI accurately discriminated hypertension (internal and external validation AUROC 0.803 and 0.771, respectively). In Fine-Gray regression analyses model-predicted probability of hypertension was associated with mortality (hazard ratio per standard deviation: 1.47 [1.36-1.60], p < 0.001), HF (2.26 [1.90-2.69], p < 0.001), MI (1.87 [1.69-2.07], p < 0.001), stroke (1.30 [1.18-1.44], p < 0.001), and aortic dissection or rupture (1.69 [1.22-2.35], p < 0.001) after adjustment for demographics and risk factors. HTN-AI may facilitate diagnosis of hypertension and serve as a digital biomarker of hypertension-associated CVD. |
| format | Article |
| id | doaj-art-e87f993275da4913a4915ae66da0e26f |
| institution | DOAJ |
| issn | 2398-6352 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj-art-e87f993275da4913a4915ae66da0e26f2025-08-20T03:10:52ZengNature Portfolionpj Digital Medicine2398-63522025-02-01811910.1038/s41746-025-01491-8A deep learning digital biomarker to detect hypertension and stratify cardiovascular risk from the electrocardiogramMostafa A. Al-Alusi0Samuel F. Friedman1Shinwan Kany2Joel T. Rämö3Daniel Pipilas4Pulkit Singh5Christopher Reeder6Shaan Khurshid7James P. Pirruccello8Mahnaz Maddah9Jennifer E. Ho10Patrick T. Ellinor11Cardiology Division, Massachusetts General HospitalCardiovascular Disease Initiative, Broad Institute of MIT and HarvardCardiovascular Disease Initiative, Broad Institute of MIT and HarvardCardiovascular Disease Initiative, Broad Institute of MIT and HarvardCardiology Division, Massachusetts General HospitalCardiovascular Disease Initiative, Broad Institute of MIT and HarvardCardiovascular Disease Initiative, Broad Institute of MIT and HarvardCardiology Division, Massachusetts General HospitalCardiovascular Disease Initiative, Broad Institute of MIT and HarvardCardiovascular Disease Initiative, Broad Institute of MIT and HarvardCardiovascular Disease Initiative, Broad Institute of MIT and HarvardCardiology Division, Massachusetts General HospitalAbstract Hypertension is a major risk factor for cardiovascular disease (CVD), yet blood pressure is measured intermittently and under suboptimal conditions. We developed a deep learning model to identify hypertension and stratify risk of CVD using 12-lead electrocardiogram waveforms. HTN-AI was trained to detect hypertension using 752,415 electrocardiograms from 103,405 adults at Massachusetts General Hospital. We externally validated HTN-AI and demonstrated associations between HTN-AI risk and incident CVD in 56,760 adults at Brigham and Women’s Hospital. HTN-AI accurately discriminated hypertension (internal and external validation AUROC 0.803 and 0.771, respectively). In Fine-Gray regression analyses model-predicted probability of hypertension was associated with mortality (hazard ratio per standard deviation: 1.47 [1.36-1.60], p < 0.001), HF (2.26 [1.90-2.69], p < 0.001), MI (1.87 [1.69-2.07], p < 0.001), stroke (1.30 [1.18-1.44], p < 0.001), and aortic dissection or rupture (1.69 [1.22-2.35], p < 0.001) after adjustment for demographics and risk factors. HTN-AI may facilitate diagnosis of hypertension and serve as a digital biomarker of hypertension-associated CVD.https://doi.org/10.1038/s41746-025-01491-8 |
| spellingShingle | Mostafa A. Al-Alusi Samuel F. Friedman Shinwan Kany Joel T. Rämö Daniel Pipilas Pulkit Singh Christopher Reeder Shaan Khurshid James P. Pirruccello Mahnaz Maddah Jennifer E. Ho Patrick T. Ellinor A deep learning digital biomarker to detect hypertension and stratify cardiovascular risk from the electrocardiogram npj Digital Medicine |
| title | A deep learning digital biomarker to detect hypertension and stratify cardiovascular risk from the electrocardiogram |
| title_full | A deep learning digital biomarker to detect hypertension and stratify cardiovascular risk from the electrocardiogram |
| title_fullStr | A deep learning digital biomarker to detect hypertension and stratify cardiovascular risk from the electrocardiogram |
| title_full_unstemmed | A deep learning digital biomarker to detect hypertension and stratify cardiovascular risk from the electrocardiogram |
| title_short | A deep learning digital biomarker to detect hypertension and stratify cardiovascular risk from the electrocardiogram |
| title_sort | deep learning digital biomarker to detect hypertension and stratify cardiovascular risk from the electrocardiogram |
| url | https://doi.org/10.1038/s41746-025-01491-8 |
| work_keys_str_mv | AT mostafaaalalusi adeeplearningdigitalbiomarkertodetecthypertensionandstratifycardiovascularriskfromtheelectrocardiogram AT samuelffriedman adeeplearningdigitalbiomarkertodetecthypertensionandstratifycardiovascularriskfromtheelectrocardiogram AT shinwankany adeeplearningdigitalbiomarkertodetecthypertensionandstratifycardiovascularriskfromtheelectrocardiogram AT joeltramo adeeplearningdigitalbiomarkertodetecthypertensionandstratifycardiovascularriskfromtheelectrocardiogram AT danielpipilas adeeplearningdigitalbiomarkertodetecthypertensionandstratifycardiovascularriskfromtheelectrocardiogram AT pulkitsingh adeeplearningdigitalbiomarkertodetecthypertensionandstratifycardiovascularriskfromtheelectrocardiogram AT christopherreeder adeeplearningdigitalbiomarkertodetecthypertensionandstratifycardiovascularriskfromtheelectrocardiogram AT shaankhurshid adeeplearningdigitalbiomarkertodetecthypertensionandstratifycardiovascularriskfromtheelectrocardiogram AT jamesppirruccello adeeplearningdigitalbiomarkertodetecthypertensionandstratifycardiovascularriskfromtheelectrocardiogram AT mahnazmaddah adeeplearningdigitalbiomarkertodetecthypertensionandstratifycardiovascularriskfromtheelectrocardiogram AT jennifereho adeeplearningdigitalbiomarkertodetecthypertensionandstratifycardiovascularriskfromtheelectrocardiogram AT patricktellinor adeeplearningdigitalbiomarkertodetecthypertensionandstratifycardiovascularriskfromtheelectrocardiogram AT mostafaaalalusi deeplearningdigitalbiomarkertodetecthypertensionandstratifycardiovascularriskfromtheelectrocardiogram AT samuelffriedman deeplearningdigitalbiomarkertodetecthypertensionandstratifycardiovascularriskfromtheelectrocardiogram AT shinwankany deeplearningdigitalbiomarkertodetecthypertensionandstratifycardiovascularriskfromtheelectrocardiogram AT joeltramo deeplearningdigitalbiomarkertodetecthypertensionandstratifycardiovascularriskfromtheelectrocardiogram AT danielpipilas deeplearningdigitalbiomarkertodetecthypertensionandstratifycardiovascularriskfromtheelectrocardiogram AT pulkitsingh deeplearningdigitalbiomarkertodetecthypertensionandstratifycardiovascularriskfromtheelectrocardiogram AT christopherreeder deeplearningdigitalbiomarkertodetecthypertensionandstratifycardiovascularriskfromtheelectrocardiogram AT shaankhurshid deeplearningdigitalbiomarkertodetecthypertensionandstratifycardiovascularriskfromtheelectrocardiogram AT jamesppirruccello deeplearningdigitalbiomarkertodetecthypertensionandstratifycardiovascularriskfromtheelectrocardiogram AT mahnazmaddah deeplearningdigitalbiomarkertodetecthypertensionandstratifycardiovascularriskfromtheelectrocardiogram AT jennifereho deeplearningdigitalbiomarkertodetecthypertensionandstratifycardiovascularriskfromtheelectrocardiogram AT patricktellinor deeplearningdigitalbiomarkertodetecthypertensionandstratifycardiovascularriskfromtheelectrocardiogram |