Evidence map›Paper›PMID 39799251›Full record

ArticleNPJ digital medicine2025

Unsupervised deep learning of electrocardiograms enables scalable human disease profiling.

Sam F Friedman, Shaan Khurshid, Rachael A Venn, Xin Wang, Nate Diamant, Paolo Di Achille, Lu-Chen Weng, Seung Hoan Choi, Christopher Reeder, James P Pirruccello and 9 more

Abstract read
In one paragraph

Article in NPJ digital medicine, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 10 papers.

0numbers the graph read from it
0cells of the map it votes in
10citing papers in PubMed
–field-weighted citation impact
1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

10 citing papers in PubMed.

  1. Review
  2. Article
  3. Article
  4. Article
  5. Article
  6. Review
  7. Prototype Learning to Create Refined Interpretable Digital Phenotypes from ECGs.Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing · 2026
    Article
  8. Article
  9. Article
  10. Extracting Genetically-Imputed Causal Features From ECG Data.Statistical analysis and data mining · 2025
    Article
4 · The record

Corrections and comments

PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.

5 · Who and what money

Authors and funding

19 authors.

Sam F Friedman *Data Sciences Platform, The Broad Institute of MIT and Harvard, Cambridge, MA, USA.ORCID http://orcid.org/0000-0002-0688-2169
Shaan Khurshid *Cardiovascular Research Center, Massachusetts General Hospital, Boston, MA, USA.ORCID http://orcid.org/0000-0002-2840-4539
Rachael A Venn *Cardiovascular Research Center, Massachusetts General Hospital, Boston, MA, USA.
Xin Wang *Cardiovascular Research Center, Massachusetts General Hospital, Boston, MA, USA.
Nate DiamantData Sciences Platform, The Broad Institute of MIT and Harvard, Cambridge, MA, USA.
Paolo Di AchilleData Sciences Platform, The Broad Institute of MIT and Harvard, Cambridge, MA, USA.ORCID http://orcid.org/0000-0001-9256-0678
Lu-Chen WengCardiovascular Research Center, Massachusetts General Hospital, Boston, MA, USA.ORCID http://orcid.org/0000-0003-1475-4930
Seung Hoan ChoiCardiovascular Disease Initiative, The Broad Institute of MIT and Harvard, Cambridge, MA, USA.ORCID http://orcid.org/0000-0002-2797-3190
Christopher ReederData Sciences Platform, The Broad Institute of MIT and Harvard, Cambridge, MA, USA.ORCID http://orcid.org/0000-0002-3893-2423
James P PirruccelloCardiovascular Disease Initiative, The Broad Institute of MIT and Harvard, Cambridge, MA, USA.ORCID http://orcid.org/0000-0001-6088-4037
Pulkit SinghData Sciences Platform, The Broad Institute of MIT and Harvard, Cambridge, MA, USA.ORCID http://orcid.org/0000-0002-1538-5519
Emily S LauCardiovascular Research Center, Massachusetts General Hospital, Boston, MA, USA.ORCID http://orcid.org/0000-0001-9361-6397
Anthony PhilippakisGoogle Ventures, Cambridge, MA, USA.ORCID http://orcid.org/0000-0001-6953-3794
Christopher D AndersonDepartment of Neurology, Brigham and Women's Hospital, Boston, MA, USA.
Mahnaz MaddahData Sciences Platform, The Broad Institute of MIT and Harvard, Cambridge, MA, USA.ORCID http://orcid.org/0000-0002-9837-6000
Puneet BatraData Sciences Platform, The Broad Institute of MIT and Harvard, Cambridge, MA, USA.
Patrick T EllinorCardiovascular Research Center, Massachusetts General Hospital, Boston, MA, USA.ORCID http://orcid.org/0000-0002-2067-0533
Jennifer E HoCardiovascular Disease Initiative, The Broad Institute of MIT and Harvard, Cambridge, MA, USA.ORCID http://orcid.org/0000-0002-7987-4768
Steven A LubitzCardiovascular Research Center, Massachusetts General Hospital, Boston, MA, USA. slubitz@mgh.harvard.edu.ORCID http://orcid.org/0000-0002-9599-4866

Funding

Ethnic/Racial Variation in Intracerebral Hemorrhage (ERICH)U01NS069763 · NINDS · UNIVERSITY OF CINCINNATI · PI ANDERSON, CHRISTOPHER DAVID, DEMEL, STACIE · 2010 to 2024
$34.2M
Sequencing Annotation and Functional Analysis in Risk of Intracerebral HemorrhageR01NS103924 · NINDS · MASSACHUSETTS GENERAL HOSPITAL · PI ANDERSON, CHRISTOPHER DAVID · 2018 to 2022
$3.4M
Genomics of Cardiac ArrhythmiasR01HL139731 · NHLBI · MASSACHUSETTS GENERAL HOSPITAL · PI ELLINOR, PATRICK THOMAS · 2018 to 2022
$3.3M
Eicosanoid Profiles as Determinants of HFpEFR01HL140224 · NHLBI · MASSACHUSETTS GENERAL HOSPITAL · PI HO, JENNIFER E · 2018 to 2021
$3.1M
The Association of Metabolic Disease and Pulmonary HypertensionR01HL134893 · NHLBI · MASSACHUSETTS GENERAL HOSPITAL · PI HO, JENNIFER E · 2017 to 2021
$2.9M
Long-Term Endothelial Effects of COVID-19 in ObesityR01HL160003 · NHLBI · BETH ISRAEL DEACONESS MEDICAL CENTER · PI HAMBURG, NAOMI MIRIAM, HO, JENNIFER E · 2022 to 2025
$2.8M
Mentoring in Arrhythmia ResearchK24HL105780 · NHLBI · MASSACHUSETTS GENERAL HOSPITAL · PI ELLINOR, PATRICK THOMAS · 2011 to 2020
$1.2M
HFpEF Susceptibility in Women: The Role of InflammationK23HL159243 · NHLBI · MASSACHUSETTS GENERAL HOSPITAL · PI Emily Lau · 2022 to 2026
$1.1M
Electrocardiogram-based deep learning and decision analysis to improve atrial fibrillation risk estimationK23HL169839 · NHLBI · MASSACHUSETTS GENERAL HOSPITAL · PI Shaan Khurshid · 2023 to 2026
$860k
Deep learning to enable the genetic analysis of aortaK08HL159346 · NHLBI · UNIVERSITY OF CALIFORNIA, SAN FRANCISCO · PI PIRRUCCELLO, JAMES · 2021 to 2025
$827k
Mentoring in Patient-Oriented and Translational HFpEF ResearchK24HL153669 · NHLBI · MASSACHUSETTS GENERAL HOSPITAL · PI Jennifer E Ho · 2020 to 2026
$744k
American Heart Association (American Heart Association, Inc.) 18SFRN34110082American Heart Association (American Heart Association, Inc.) 18SFRN34250007American Heart Association (American Heart Association, Inc.) 21SFRN812095American Heart Association (American Heart Association, Inc.) 23CDA1050571American Heart Association (American Heart Association, Inc.) 853922NHLBI NIH HHS K23 HL159243NHLBI NIH HHS K23 HL169839U.S. Department of Health & Human Services | NIH | National Heart, Lung, and Blood Institute (NHLBI) 1R01HL092577U.S. Department of Health & Human Services | NIH | National Heart, Lung, and Blood Institute (NHLBI) 1R01HL139731U.S. Department of Health & Human Services | NIH | National Heart, Lung, and Blood Institute (NHLBI) K08HL159346U.S. Department of Health & Human Services | NIH | National Heart, Lung, and Blood Institute (NHLBI) K23HL159243U.S. Department of Health & Human Services | NIH | National Heart, Lung, and Blood Institute (NHLBI) K23HL169839U.S. Department of Health & Human Services | NIH | National Heart, Lung, and Blood Institute (NHLBI) K24HL105780U.S. Department of Health & Human Services | NIH | National Heart, Lung, and Blood Institute (NHLBI) K24HL153669U.S. Department of Health & Human Services | NIH | National Heart, Lung, and Blood Institute (NHLBI) R01HL134893U.S. Department of Health & Human Services | NIH | National Heart, Lung, and Blood Institute (NHLBI) R01HL139731U.S. Department of Health & Human Services | NIH | National Heart, Lung, and Blood Institute (NHLBI) R01HL140224U.S. Department of Health & Human Services | NIH | National Heart, Lung, and Blood Institute (NHLBI) R01HL160003U.S. Department of Health & Human Services | NIH | National Heart, Lung, and Blood Institute (NHLBI) R01NS103924U.S. Department of Health & Human Services | NIH | National Heart, Lung, and Blood Institute (NHLBI) U01NS069763
6 · The paper itself

Abstract

The 12-lead electrocardiogram (ECG) is inexpensive and widely available. Whether conditions across the human disease landscape can be detected using the ECG is unclear. We developed a deep learning denoising autoencoder and systematically evaluated associations between ECG encodings and ~1,600 Phecode-based diseases in three datasets separate from model development, and meta-analyzed the results. The latent space ECG model identified associations with 645 prevalent and 606 incident Phecodes. Associations were most enriched in the circulatory (n = 140, 82% of category-specific Phecodes), respiratory (n = 53, 62%) and endocrine/metabolic (n = 73, 45%) categories, with additional associations across the phenome. The strongest ECG association was with hypertension (p < 2.2×10

Identifiers

PMID39799251
PMCPMC11724961

What Socratic holds

Textmetadata
LicenceCC BY-NC-ND
Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the Socratic graph.