Artificial Intelligence-Enabled Electrocardiography Contributes to Hyperthyroidism Detection and Outcome Prediction
Open accessAbstract
Background: Hyperthyroidism is frequently under-recognized and leads to heart failure and mortality. Timely identification of high-risk patients is a prerequisite to effective antithyroid therapy. Since the heart is very sensitive to hyperthyroidism and its electrical signature can be demonstrated by electrocardiography, we developed an artificial intelligence model to detect hyperthyroidism by electrocardiography and examined its potential for outcome prediction. Methods: The deep learning model was trained using a large dataset of 47,245 electrocardiograms from 33,246 patients at an academic medical center. Patients were included if electrocardiograms and measurements of serum thyroid-stimulating hormone were available that had been obtained within a three day period. Serum thyroid-stimulating hormone and free thyroxine were used to define overt and subclinical hyperthyroidism. We tested the model internally using 14,420 patients and externally using two additional test sets comprising 11,498 and 596 patients, respectively. Results: The performance of the deep learning model achieves areas under the receiver operating characteristic curves (AUCs) of 0.725–0.761 for hyperthyroidism detection, AUCs of 0.867–0.876 for overt hyperthyroidism, and AUC of 0.631–0.701 for subclinical hyperthyroidism, superior to a traditional features-based machine learning model. Patients identified as hyperthyroidism-positive by the deep learning model have a significantly higher risk (1.97–2.94 fold) of all-cause mortality and new-onset heart failure compared to hyperthyroidism-negative patients. This cardiovascular disease stratification is particularly pronounced in subclinical hyperthyroidism, surpassing that observed in overt hyperthyroidism. Conclusions: An innovative algorithm effectively identifies overt and subclinical hyperthyroidism and contributes to cardiovascular risk assessment.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
AI-ECG detection of hyperthyroidism was associated with increased risk of mortality and new-onset heart failure.
“A later study also found that AI-ECG detection of hyperthyroidism was associated with increased risk of mortality and new-onset heart failure [39].”
From Deep Learning Applied to 12-Lead ECGs for Detection of Structural, Metabolic and Systemic Disease (2026) · cites this paper as [39]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126 · see citing works
Ross, D. S., Burch, H. B., Cooper, D. S., Greenlee, M. C., Laurberg, P., Maia, A. L., Rivkees, S. A., Samuels, M., Sosa, J. A., Stan, M. N., et al. (2016) · Thyroid® · doi:10.1089/thy.2016.0229 · Cited by 2,938 · see citing works
Thyroid hormone and the cardiovascular system.
Klein, I., & Ojamaa, K. (2001) · New England Journal of Medicine · doi:10.1056/nejm200102153440707 · Cited by 2,300 · see citing works
Attia, Z. I., Kapa, S., Lopez-Jimenez, F., McKie, P. M., Ladewig, D. J., Satam, G., Pellikka, P. A., Enriquez-Sarano, M., Noseworthy, P. A., Munger, T. M., et al. (2019) · Nature Medicine · doi:10.1038/s41591-018-0240-2 · Cited by 1,389 · see citing works
Artificial intelligence-enhanced electrocardiography in cardiovascular disease management
Siontis, K. C., Noseworthy, P. A., Attia, Z. I., & Friedman, P. A. (2021) · Nature Reviews Cardiology · doi:10.1038/s41569-020-00503-2 · Cited by 914 · see citing works
De Leo, S., Lee, S. Y., & Braverman, L. E. (2016) · The Lancet · doi:10.1016/s0140-6736(16)00278-6 · Cited by 883 · see citing works
Managing Incidental Findings on Abdominal CT: White Paper of the ACR Incidental Findings Committee
Berland, L. L., Silverman, S. G., Gore, R. M., Mayo-Smith, W. W., Megibow, A. J., Yee, J., Brink, J. A., Baker, M. E., Federle, M. P., Foley, W. D., et al. (2010) · Journal of the American College of Radiology · doi:10.1016/j.jacr.2010.06.013 · Cited by 869 · see citing works
Bluemke, D. A., Moy, L., Bredella, M. A., Ertl-Wagner, B. B., Fowler, K. J., Goh, V. J., Halpern, E. F., Hess, C. P., Schiebler, M. L., & Weiss, C. R. (2020) · Radiology · doi:10.1148/radiol.2019192515 · Cited by 343 · see citing works
Application of artificial intelligence to the electrocardiogram
Attia, Z. I., Harmon, D., Behr, E. R., & Friedman, P. A. (2021) · European Heart Journal · doi:10.1093/eurheartj/ehab649 · Cited by 313 · see citing works
Cascades of Care After Incidental Findings in a US National Survey of Physicians
Ganguli, I., Simpkin, A. L., Lupo, C., Weissman, A., Mainor, A. J., Orav, E. J., Rosenthal, M. B., Colla, C. H., & Sequist, T. D. (2019) · JAMA Network Open · doi:10.1001/jamanetworkopen.2019.13325 · Cited by 187 · see citing works
Screening for Thyroid Dysfunction: U.S. Preventive Services Task Force Recommendation Statement
LeFevre, M. L., & on behalf of the U.S. Preventive Services Task Force* (2015) · Annals of Internal Medicine · doi:10.7326/m15-0483 · Cited by 176 · see citing works
Haentjens, P., Van Meerhaeghe, A., Poppe, K., & Velkeniers, B. (2008) · European Journal of Endocrinology · doi:10.1530/eje-08-0110 · Cited by 174 · see citing works
Opportunistic Screening: Radiology Scientific Expert Panel
Pickhardt, P. J., Summers, R. M., Garrett, J. W., Krishnaraj, A., Agarwal, S., Dreyer, K. J., & Nicola, G. N. (2023) · Radiology · doi:10.1148/radiol.222044 · Cited by 134 · see citing works
Okosieme, O. E., Taylor, P. N., Evans, C., Thayer, D. S., Chai, A., Khan, I. N., Draman, M. S., Tennant, B. P., Geen, J., Sayers, A. E., et al. (2019) · The Lancet Diabetes & Endocrinology · doi:10.1016/s2213-8587(19)30059-2 · Cited by 133 · see citing works
Conditions not primarily affecting the heart
Slovis, C. M., & Jenkins, R. (2002) · BMJ · doi:10.1136/bmj.324.7349.1320 · Cited by 105 · see citing works
Both Hypothyroidism and Hyperthyroidism Increase Atrial Fibrillation Inducibility in Rats
Zhang, Y., Dedkov, E. I., Teplitsky, D., Weltman, N. Y., Pol, C. J., Rajagopalan, V., Lee, B., & Gerdes, A. M. (2013) · Circulation Arrhythmia and Electrophysiology · doi:10.1161/circep.113.000502 · Cited by 104 · see citing works
Cappola, A. R., Desai, A. S., Medici, M., Cooper, L. S., Egan, D., Sopko, G. S., Fishman, G. I., Goldman, S., Cooper, D. S., Mora, S., et al. (2019) · Thyroid · doi:10.1089/thy.2018.0416 · Cited by 95 · see citing works
Thyroid hormones and cardiac arrhythmias
Tribulová, N., Knezl, V., Shainberg, A., Seki, S., & Soukup, T. (2009) · Vascular Pharmacology · doi:10.1016/j.vph.2009.10.001 · Cited by 82 · see citing works
External validation of a deep learning electrocardiogram algorithm to detect ventricular dysfunction
Attia, I. Z., Tseng, A. S., Benavente, E. D., Medina‐Inojosa, J. R., Clark, T. G., Malyutina, S. K., Kapa, S., Schirmer, H., Kudryavtsev, A. V., Noseworthy, P. A., et al. (2021) · International Journal of Cardiology · doi:10.1016/j.ijcard.2020.12.065 · Cited by 82 · see citing works
Lin, C., Chau, T., Lin, C.-S., Shang, H.-S., Fang, W.-H., Lee, D.-J., Lee, C.-C., Tsai, S.-H., Wang, C.-H., & Lin, S.-H. (2022) · npj Digital Medicine · doi:10.1038/s41746-021-00550-0 · Cited by 62 · see citing works
Self-citationChen, H., Lin, C., Fang, W., Lou, Y.-S., Cheng, C., Cheng, C., & Lee, C. (2022) · Journal of Personalized Medicine · doi:10.3390/jpm12030455 · Cited by 54 · see citing works
Self-citationHyperthyroidism is associated with lengthening of ventricular repolarization
Colzani, R., Emdin, M., Conforti, F., Passino, C., Scarlattini, M., & Iervasi, G. (2001) · Clinical Endocrinology · doi:10.1046/j.1365-2265.2001.01295.x · Cited by 50 · see citing works
Atrial fibrillation and hyperthyroidism.
Jayaprasad, N., & Francis, J. (2005) · PubMed · Cited by 49 · see citing works
Liu, W.-T., Lin, C., Tsao, T., Cheng, C., Chen, J., Chen, J., Tsai, C.-S., Lin, C. S., & Lin, C. S. (2021) · Canadian Journal of Cardiology · doi:10.1016/j.cjca.2021.09.028 · Cited by 45 · see citing works
Self-citationSalden, F., Kutyifa, V., Stockburger, M. A., Prinzen, F. W., & Vernooy, K. (2017) · EP Europace · doi:10.1093/europace/eux207 · Cited by 45 · see citing works
Tayal, B., Graff, C., Selmer, C., Kragholm, K. H., Kihlstrom, M., Nielsen, J. B., Olsen, A. S., Pietersen, A. H., Holst, A. G., Søgaard, P., et al. (2019) · BMJ Open · doi:10.1136/bmjopen-2018-023854 · Cited by 38 · see citing works
Detecting Digoxin Toxicity by Artificial Intelligence-Assisted Electrocardiography
Chang, D., Lin, C., Tsao, T., Lee, C.-C., Chen, J., Tsai, C., Lin, W.-S., & Lin, W. (2021) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph18073839 · Cited by 38 · see citing works
Self-citationLou, Y.-S., Lin, C., Fang, W., Lee, C.-C., Ho, C., Wang, C., & Lin, C. S. (2022) · Journal of Personalized Medicine · doi:10.3390/jpm12020315 · Cited by 23 · see citing works
Self-citationA deep learning-based system capable of detecting pneumothorax via electrocardiogram
Lee, C., Lin, C., Tsai, C., Tsao, T., Cheng, C., Liou, J., Lin, W., Lee, C., Chen, J., & Lin, C. S. (2022) · European Journal of Trauma and Emergency Surgery · doi:10.1007/s00068-022-01904-3 · Cited by 21 · see citing works
Self-citationChen, H., Lin, C., Fang, W., Lee, C., Ho, C., Wang, C., & Lin, C. S. (2022) · Frontiers in Medicine · doi:10.3389/fmed.2022.870523 · Cited by 19 · see citing works
Self-citationLearning and teaching electrocardiography in the 21st century: A neglected art
Shenasa, M. (2018) · Journal of Electrocardiology · doi:10.1016/j.jelectrocard.2018.02.007 · Cited by 15 · see citing works
Asban, A., Chung, S., Tresler, M. A., Huilgol, P., Xie, R., Kirklin, J., Balentine, C., Lindeman, B., & Chen, H. (2018) · Annals of Surgery · doi:10.1097/sla.0000000000002922 · Cited by 14 · see citing works
Lee, C.-H., Liu, W.-T., Lou, Y.-S., Lin, C., Fang, W., Lee, C.-C., Ho, C., Wang, C. H., & Lin, C. S. (2022) · Digital Health · doi:10.1177/20552076221143249 · Cited by 14 · see citing works
Self-citationHuang, P.-F., Kung, P., Chou, W., & Tsai, W. (2020) · PLoS ONE · doi:10.1371/journal.pone.0243373 · Cited by 12 · see citing works
Electrocardiographic Biomarker Based on Machine Learning for Detecting Overt Hyperthyroidism
Choi, B., Jang, J. H., Son, M., Lee, M. S., Jo, Y. Y., Jeon, J. Y., Jin, U., Soh, M., Park, R. W., & Kwon, J. M. (2022) · European Heart Journal - Digital Health · doi:10.1093/ehjdh/ztac013 · Cited by 12 · see citing works
Artificial Intelligence Application in Graves Disease
Naser, J. A., Attia, Z. I., Pislaru, S. V., Stan, M. N., Pellikka, P. A., Noseworthy, P. A., Friedman, P. A., & Lin, G. R. (2022) · Mayo Clinic Proceedings · doi:10.1016/j.mayocp.2021.08.029 · Cited by 10 · see citing works
Opportunistic Osteoporosis Screening with Cardiac CT: Can We Predict Future Fractures?
Bredella, M. A. (2020) · Radiology · doi:10.1148/radiol.2020202374 · Cited by 10 · see citing works
Metwalley, K. A., Farghaly, H. S., & Abdelhamid, A. (2017) · European Journal of Pediatrics · doi:10.1007/s00431-017-3039-0 · Cited by 5 · see citing works
High triiodothyronine levels induce myocardial hypertrophy via BAFF overexpression
Li, G., Liu, X., Liu, B., Zhong, Y., Gu, Q., Miao, J., Wang, J., Liu, S., & Mao, X. (2022) · Journal of Cellular and Molecular Medicine · doi:10.1111/jcmm.17470 · Cited by 2 · see citing works
Lin, C. S., Kuo, F.-C., Chau, T., Shih, J., Lin, C., Chen, C., Lee, C., & Lin, S. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4376989 · Cited by 2 · see citing works
Self-citation
Flagged first, then by citations
1 of the 41 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Artificial intelligence-enabled electrocardiography from scientific research to clinical application
Lin, C.-S., Liu, W.-T., Chen, Y.-H., Lin, S.-H., & Lin, C. (2025) · EMBO Molecular Medicine · doi:10.1038/s44321-025-00351-y · Cited by 15 · see citing works
Self-citationThyroid dysfunction and cardiovascular disease
Alwan, H., Hysaj, O., Gencer, B., Duntas, L. H., & Rodondi, N. (2026) · European Heart Journal · doi:10.1093/eurheartj/ehag248 · Cited by 14 · see citing works
Fujita, W., Sakamoto, A., Sato, E., KANEKO, T., & Kagiyama, N. (2025) · Juntendō Igaku/Juntendo igaku · doi:10.14789/ejmj.jmj25-0019-r · Cited by 1 · see citing works
Deep Learning Applied to 12-Lead ECGs for Detection of Structural, Metabolic and Systemic Disease
Shaulian, S., Zeltser, R., & Makaryus, A. N. (2026) · Diagnostics · doi:10.3390/diagnostics16172834
Zou, R., Li, A., Chen, D., & Li, M. (2024) · Research Square · doi:10.21203/rs.3.rs-4823408/v1
Zvuloni, E., Gagliardi, G., Ribeiro, A. H., Ribeiro, A. L. P., Vos, M. D., & Behar, J. A. (2025) · Machine Learning Health · doi:10.1088/3049-477x/ae2ac5
Endocrine hypertension in 2025: how AI and multiomics are revolutionizing detection
Fuentes‐Mendoza, J. M., Concepción‐Zavaleta, M. J., Mendoza-Godoy, J. J., Aldave, J. E. Q., Morón-Siguas, J. C., & Paz‐Ibarra, J. (2026) · Expert Review of Cardiovascular Therapy · doi:10.1080/14779072.2026.2634025
- Authors
- Lin, C., Kuo, F.-C., Chau, T., Shih, J.-H., Lin, C.-S., Chen, C.-C., Lee, C.-C., & Lin, S.-H.
- Affiliations
- Tri-Service General Hospital (TW)
- Providence St. Vincent Medical Center (US)
- Corresponding author
- Lin, Shih-Hua
- ORCID
- Venue
- Communications Medicine
- Published
- 2024-03-12
- Volume
- 4
- Issue
- 1
- Pages
- 42-42
- ISSN
- 2730-664X (ISSN-L)
- PMC
- PMC10933352
- OpenAlex
- W4392682835
- Cited by
- 8
- References
- 41
- Citations by year
- 2026: 3 · 2025: 3 · 2024: 2
- FWCI
- 2.63
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- Communications Medicine (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- Funders
- Ministry of Science and Technology, Taiwan (CHNDMC-111-07, MOST110-2314-B016-010-MY3)
- Medical Affairs Bureau (MND-MAB-110-113, MND-MAB-C13-112050)
- Topics
- Health Sciences › Medicine › Endocrinology, Diabetes and Metabolism › Thyroid Disorders and Treatments
- Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › ECG Monitoring and Analysis
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- hyperthyroidism, subclinical hyperthyroidism, electrocardiogram, deep learning, artificial intelligence, outcome prediction, all-cause mortality, heart failure, cardiovascular risk stratification, thyroid-stimulating hormone, free thyroxine
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
