Validation and longitudinal trajectory analysis of an AI-based ECG model for aortic stenosis: from community screening to pre-TAVR risk stratification
Open accessAbstract
Aims: Early aortic stenosis (AS) detection remains challenging, with many patients presenting late when left ventricular dysfunction may be irreversible. We evaluated whether longitudinal AI-enhanced ECG patterns can predict outcomes years before intervention and assessed the community screening potential of the AK-AVS model. Methods and results: We conducted two complementary analyses: (1) community validation of the AK-AVS model in 3632 cardiovascular disease-free ARIC participants, and (2) longitudinal trajectory analysis of 7860 ECGs from 2040 TAVR recipients collected up to 10 years pre-procedure. Unsupervised clustering identified distinct AK-AVS trajectories, with mortality associations assessed using Cox regression and net reclassification improvement. In community screening (n = 16 moderate/severe AS), AK-AVS achieved an AUROC of 0.79, sensitivity 75%, and specificity 75% for moderate/severe AS. At hypothetical screening prevalences of 1–5%, positive predictive values improved to 3.1–14.3%. False-positive predictions identified individuals at 4-fold increased risk for future AS hospitalisation (HR 4.05, P < 0.001) and 52% increased risk for heart failure (HR 1.52, P = 0.02). In the TAVR cohort, trajectory analysis revealed three distinct patterns: Stable Low (19.3%), Accelerated Progression (23.6%), and Persistently High (57.1%). Elevated trajectory groups were older (78.4 and 77.8 vs. 72.6 years, P < 0.001) with higher pacemaker rates (16.4% and 17.3% vs. 10.7%, P = 0.008), despite similar hemodynamic severity. Both elevated patterns independently predicted mortality (Accelerated: HR 1.40, P = 0.03; Persistently High: HR 1.48, P = 0.005) and significantly improved risk reclassification beyond traditional risk scores (NRI 0.069–0.074). Conclusion: Longitudinal AI-ECG trajectory patterns detect disease progression up to 4.5 years before TAVR and enhance mortality prediction beyond traditional risk scores. Community validation shows potential screening utility with ‘false-positives’ identifying future risk.
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?
Valvular and composite SHD AI-ECG models are promising for referral enrichment.
“Valvular and composite SHD models are promising for referral enrichment”
From AI-ECG for Echocardiography Triage in Structural Heart Disease: Evidence, Implementation, and Future Directions (2026) · cites this paper as [23]
The Discussion (page not provided) proposes using an AI-ECG model for aortic stenosis to identify patients for confirmatory echocardiography, supporting the referral-enrichment idea for one valvular condition. It does not evaluate composite structural heart disease (SHD) models or establish the claim for valvular models generally. (LLM, conf=0.84)
Experimental — accuracy not yet measuredValvular AI-ECG has moved beyond proof of concept and shows meaningful referral enrichment, but prospective pathway validation remains limited.
“From a deployment perspective, however, the practical conclusion is narrower: valvular AI-ECG has moved beyond proof of concept and shows meaningful referral enrichment, but prospective pathway validation remains limited.19,23”
From AI-ECG for Echocardiography Triage in Structural Heart Disease: Evidence, Implementation, and Future Directions (2026) · cites this paper as [23]
The Discussion (page unavailable) reports community validation of the aortic-stenosis AI-ECG model and projects that screening higher-risk patients would improve positive predictive value, with positive screens prompting echocardiography. It does not demonstrate referral enrichment in an implemented pathway; that is a proposed application. The Discussion also calls for prospective validation and randomized trials, supporting the qualification that pathway validation remains limited. (LLM, conf=0.86)
Experimental — accuracy not yet measuredIn aortic stenosis, patients with positive AI-ECG results but no moderate-to-severe AS at baseline had a higher long-term risk of subsequently developing moderate-to-severe AS, and recent community validation showed a fourfold higher risk of future AS hospitalization among false-positive screens.
“Analogous findings have been reported in aortic stenosis: patients with positive AI-ECG results but no moderate-to-severe AS at baseline had a higher long-term risk of subsequently developing moderate-to-severe AS, and recent community validation likewise showed a fourfold higher risk of future AS hospitalization among false-positive screens.19,23”
From AI-ECG for Echocardiography Triage in Structural Heart Disease: Evidence, Implementation, and Future Directions (2026) · cites this paper as [23]
Emerging evidence supports longitudinal risk tracking in aortic stenosis and surveillance for treatment-related left ventricular dysfunction in cardio-oncology.
“with emerging evidence supporting longitudinal risk tracking in aortic stenosis23 and surveillance for treatment-related left ventricular dysfunction in cardio-oncology.18”
From AI-ECG for Echocardiography Triage in Structural Heart Disease: Evidence, Implementation, and Future Directions (2026) · cites this paper as [23]
Longitudinal AI-ECG trajectories in aortic stenosis can identify accelerated disease progression years before valve intervention.
“Recent studies have shown that longitudinal AI-ECG trajectories in aortic stenosis can identify accelerated disease progression years before valve intervention,23”
From AI-ECG for Echocardiography Triage in Structural Heart Disease: Evidence, Implementation, and Future Directions (2026) · cites this paper as [23]
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
Generalized Additive Models: An Introduction with R
Wood, S. N. (2017) · doi:10.1201/9781315370279 · Cited by 13,852 · see citing works
Burden of valvular heart diseases: a population-based study
Nkomo, V. T., Gardin, J. M., Skelton, T. N., Gottdiener, J. S., Scott, C. G., & Enriquez-Sarano, M. (2006) · The Lancet · doi:10.1016/s0140-6736(06)69208-8 · Cited by 4,881 · see citing works
THE ATHEROSCLEROSIS RISK IN COMMUNIT (ARIC) STUDY: DESIGN AND OBJECTIVES
THE ARIC INVESTIGATORS (1989) · American Journal of Epidemiology · doi:10.1093/oxfordjournals.aje.a115184 · Cited by 3,491 · see citing works
Evaluating the Yield of Medical Tests
Harrell, F. E. (1982) · JAMA: The Journal of the American Medical Association · doi:10.1001/jama.1982.03320430047030 · Cited by 3,490 · see citing works
Nashef, S. A. M., Roques, F., Sharples, L. D., Nilsson, J., Smith, C., Goldstone, A. R., & Lockowandt, U. (2012) · European Journal of Cardio-Thoracic Surgery · doi:10.1093/ejcts/ezs043 · Cited by 2,971 · see citing works
Group-Based Trajectory Modeling in Clinical Research
Nagin, D. S., & Odgers, C. L. (2010) · Annual Review of Clinical Psychology · doi:10.1146/annurev.clinpsy.121208.131413 · Cited by 2,749 · see citing works
Aortic Stenosis in the Elderly
Osnabrugge, R. L. J., Mylotte, D., Head, S. J., Van Mieghem, N. M., Nkomo, V. T., LeReun, C. M., Bogers, A. J. J. C., Piazza, N., & Kappetein, A. P. (2013) · Journal of the American College of Cardiology · doi:10.1016/j.jacc.2013.05.015 · Cited by 1,378 · see citing works
The Society of Thoracic Surgeons 2008 Cardiac Surgery Risk Models: Part 2—Isolated Valve Surgery
O’Brien, S. M., Shahian, D. M., Filardo, G., Ferraris, V. A., Haan, C. K., Rich, J. B., Normand, S. T., DeLong, E. R., Shewan, C. M., Dokholyan, R. S., et al. (2009) · The Annals of Thoracic Surgery · doi:10.1016/j.athoracsur.2009.05.056 · Cited by 1,259 · see citing works
Genetic Associations with Valvular Calcification and Aortic Stenosis
Thanassoulis, G., Campbell, C. Y., Owens, D. S., Smith, J. G., Smith, A. V., Peloso, G. M., Kerr, K. F., Pechlivanis, S., Budoff, M. J., Harris, T. B., et al. (2013) · New England Journal of Medicine · doi:10.1056/nejmoa1109034 · Cited by 1,008 · 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
Clavel, M.-A., Pibarot, P., Messika-Zeitoun, D., Capoulade, R., Malouf, J., Aggarwal, S. R., Araoz, P. A., Michelena, H. I., Cueff, C., Larose, E., et al. (2014) · Journal of the American College of Cardiology · doi:10.1016/j.jacc.2014.05.066 · Cited by 480 · see citing works
Myocardial Fibrosis and Cardiac Decompensation in Aortic Stenosis
Chin, C., Everett, R. J., Kwieciński, J., Vesey, A. T., Yeung, E., Esson, G. A., Jenkins, W., Koo, M., Mirsadraee, S., White, A. C., et al. (2016) · JACC. Cardiovascular imaging · doi:10.1016/j.jcmg.2016.10.007 · Cited by 424 · see citing works
Association of Trajectory of Cardiovascular Health Score and Incident Cardiovascular Disease
Wu, S., An, S., Li, W., Lichtenstein, A. H., Gao, J., Kris‐Etherton, P. M., Wu, Y., Jin, C., Huang, S., Hu, F. B., et al. (2019) · JAMA Network Open · doi:10.1001/jamanetworkopen.2019.4758 · Cited by 293 · see citing works
Imaging and Impact of Myocardial Fibrosis in Aortic Stenosis
Bing, R., Cavalcante, J. L., Everett, R. J., Clavel, M.-A. A., Newby, D. E., & Dweck, M. R. (2019) · JACC. Cardiovascular imaging · doi:10.1016/j.jcmg.2018.11.026 · Cited by 278 · see citing works
Electrocardiogram screening for aortic valve stenosis using artificial intelligence
Cohen-Shelly, M., Attia, Z. I., Friedman, P. A., Ito, S., Essayagh, B. A., Ko, W.-Y., Murphree, D. H., Michelena, H. I., Enriquez-Sarano, M., Carter, R. E., et al. (2021) · European Heart Journal · doi:10.1093/eurheartj/ehab153 · Cited by 252 · see citing works
Deep Learning–Based Algorithm for Detecting Aortic Stenosis Using Electrocardiography
Kwon, J., Lee, S. Y., Jeon, K., Lee, Y., Kim, K., Park, J., Oh, B., & Lee, M. (2020) · Journal of the American Heart Association · doi:10.1161/jaha.119.014717 · Cited by 224 · see citing works
10-Year Risk Equations for Incident Heart Failure in the General Population
Khan, S. S., Ning, H., Shah, S. J., Yancy, C. W., Carnethon, M. R., Berry, J. D., Mentz, R. J., O'Brien, E. C., Correa, A., Suthahar, N., et al. (2019) · Journal of the American College of Cardiology · doi:10.1016/j.jacc.2019.02.057 · Cited by 199 · see citing works
Jacobs, J. P., Edwards, F. H., Shahian, D. M., Haan, C. K., Puskas, J. D., Morales, D. L. S., Gammie, J. S., Sánchez, J. A., Brennan, J. M., O’Brien, S. M., et al. (2010) · The Annals of Thoracic Surgery · doi:10.1016/j.athoracsur.2010.05.042 · Cited by 160 · see citing works
Artificial intelligence in cardiovascular diseases: diagnostic and therapeutic perspectives
Sun, X., Yin, Y., Yang, Q., & Huo, T. (2023) · European journal of medical research · doi:10.1186/s40001-023-01065-y · Cited by 152 · see citing works
Lindman, B. R., Breyley, J. G., Schilling, J. D., Vatterott, A. M., Zajarias, A., Maniar, H. S., Damiano, R. J., Moon, M. R., Lawton, J. S., Gage, B. F., et al. (2015) · Heart · doi:10.1136/heartjnl-2015-307742 · Cited by 114 · see citing works
Thoenes, M., Bramlage, P., Zamorano, P., Messika–Zeitoun, D., Wendt, D., Kasel, M., Kurucova, J., & Steeds, R. P. (2018) · Journal of Thoracic Disease · doi:10.21037/jtd.2018.09.02 · Cited by 61 · see citing works
Transcatheter Aortic Valve Replacement in Intermediate‐ and Low‐Risk Patients
Rogers, T., Thourani, V. H., & Waksman, R. (2018) · Journal of the American Heart Association · doi:10.1161/jaha.117.007147 · Cited by 30 · see citing works
Gjertsson, P., Caidahl, K., Odén, A., & Bech‐Hanssen, O. (2006) · Scandinavian Cardiovascular Journal · doi:10.1080/14017430601115935 · Cited by 21 · see citing works
Tseng, A. S., Shelly-Cohen, M., Attia, I., Noseworthy, P., Friedman, P., Oh, J. K., & Lopez-Jimenez, F. (2021) · European Heart Journal - Digital Health · doi:10.1093/ehjdh/ztab061 · Cited by 21 · see citing works
Ito, S., Cohen, M. S., Attia, Z. I., Lee, E., Friedman, P. A., Nkomo, V. T., Michelena, H. I., Noseworthy, P. A., López-Jiménez, F. A., & Oh, J. K. (2023) · European Heart Journal - Digital Health · doi:10.1093/ehjdh/ztad009 · Cited by 17 · see citing works
Tanaka, T., Yahagi, K., Asami, M., Ninomiya, K., Kikushima, H., Okuno, T., Horiuchi, Y., Yuzawa, H., Komiyama, K., Tanaka, J., et al. (2021) · Journal of Cardiology · doi:10.1016/j.jjcc.2020.12.017 · Cited by 15 · see citing works
Nchimi, A., Dibato, J. E., Davin, L., Schoysman, L., Oury, C., & Lancellotti, P. (2018) · Frontiers in Cardiovascular Medicine · doi:10.3389/fcvm.2018.00112 · Cited by 14 · see citing works
Artificial Intelligence in the Screening, Diagnosis, and Management of Aortic Stenosis
Zhang, Y., Wang, M., Zhang, E., & Wu, Y. (2024) · Reviews in Cardiovascular Medicine · doi:10.31083/j.rcm2501031 · Cited by 13 · see citing works
Popat, A., Saini, B., Patel, M., Seby, N., Patel, S., Harikrishnan, S., Shah, H. N. H., Pathak, P., Dekhne, A., Sen, U., et al. (2024) · Clinical Medicine & Research · doi:10.3121/cmr.2024.1934 · Cited by 12 · see citing works
Sager, P., Rusch, A., Weber, L., Breuss, A., Appert, S., Brenner, R., Buser, M., Ammann, P., Rickli, H., & Maeder, M. T. (2023) · Clinical Cardiology · doi:10.1002/clc.24155 · Cited by 9 · see citing works
Cost-effectiveness of population screening for aortic stenosis
Motazedian, P., Prosperi‐Porta, G., Hibbert, B. M., Jalal, H. J., Labinaz, M. X., Burwash, I. G., Abdel‐Razek, O., Santo, P. D., Simard, T., Wells, G. A., et al. (2024) · European Heart Journal - Quality of Care and Clinical Outcomes · doi:10.1093/ehjqcco/qcae043 · Cited by 8 · see citing works
Living in disadvantaged neighborhoods linked to less intervention for severe aortic stenosis
Ram, C., Yousef, S., Ma, W., Vallabhajosyula, I., Singh, S., Agarwal, R., Milewski, R. K., Assi, R., Patel, P. A., Williams, M. L., et al. (2024) · Scientific Reports · doi:10.1038/s41598-024-52660-w · Cited by 7 · see citing works
Prognostic implications of left ventricular ejection fraction trajectory changes in heart failure
Ding, Z., Si, J., Zhang, X., Hu, Y., Zhang, X., Zhang, Y., & Liu, Y. (2023) · Frontiers in Cardiovascular Medicine · doi:10.3389/fcvm.2023.1232404 · Cited by 7 · see citing works
A call to consider an aortic stenosis screening program
Bae, J. Y., Fallahi, A., Miller, W. L., Leon, M. B., Abraham, T. P., Bangalore, S., & Hsi, D. H. (2023) · Trends in Cardiovascular Medicine · doi:10.1016/j.tcm.2023.04.003 · Cited by 6 · see citing works
Management of Asymptomatic Severe Aortic Stenosis: Current Evidence and Future Directions
Laterra, G., Agnello, F. G., Strazzieri, O., Reddavid, C., Scalia, L., Ingala, S., Guarino, S., Barbera, C., Russo, M. D., Costa, G., et al. (2025) · Journal of Clinical Medicine · doi:10.3390/jcm14217549 · Cited by 5 · see citing works
Balčiūnaitė, G., Rudinskaitė, I., Palionis, D., Besusparis, J., Žurauskas, E., Valevičienė, N., Janušauskas, V., Zorinas, A., Ručinskas, K., Søgaard, P., et al. (2023) · Journal of Clinical Medicine · doi:10.3390/jcm12175588 · Cited by 3 · see citing works
Flagged first, then by citations
Research works printed but not linked: 1
- [6]Martinez-Selles M, Marina-Breysse M. Current and future use of artificial intelligence in electrocardiography. J Cardiovasc Dev Dis 2023; 10: 175. 37103054 PMC10145690
Cited by
Sorted by citations
Tang, Q., Deng, K., Cui, Y., Liu, H., & Qian, B. (2026) · International Journal of General Medicine · doi:10.2147/ijgm.s610298
“19,23 that ECG-derived risk signals may reflect subclinical chamber remodelling and future progression risk, although this evidence is less mature than that for low LVEF and aortic stenosis.”
InfluentialHart, T., Gilani, N., Denis, R., Alli, O. O., Ibebuogu, U., Rier, J. D., Fergus, I. V., Kwaku, K. F., McCullough, C., Peschin, S., et al. (2026) · Current Cardiovascular Risk Reports · doi:10.1007/s12170-026-00785-0
- Authors
- Segar, M. W., Lambeth, K. D., Postalian, A., Coulter, S., Gilge, J., Razvi, N., Saeed, M., Paisley, R. D., Pandey, A., & Razavi, M.
- Affiliations
- Department of Cardiology, Texas Heart Institute , 6770 Bertner Ave, Houston, TX 77030, USA
- Department of Cardiac Electrophysiology , Ascension St. Vincent, Indianapolis, IN, USA
- Ipswich Hospital (AU)
- The University of Texas Southwestern Medical Center (US)
- Baylor College of Medicine (US)
- Corresponding author
- Segar, Matthew W
- ORCID
- Venue
- European Heart Journal - Digital Health
- Publisher
- Oxford University Press (OUP)
- Published
- 2026-01-27
- Volume
- 7
- Issue
- 2
- Pages
- ztag018-ztag018
- ISSN
- 2634-3916 (ISSN-L)
- PMC
- PMC12912914
- OpenAlex
- W7127344322
- Cited by
- 2
- References
- 36
- Citations by year
- 2026: 2
- FWCI
- 9.99
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- European Heart Journal - Digital Health (publishedVersion, cc-by)
- PubMed (publishedVersion)
- PubMed Central (publishedVersion, cc-by)
- Digital Commons-TMC (Texas Medical Center) (submittedVersion)
- Funders
- Eli Lilly and Company
- Pfizer
- Gilead Sciences
- Cytokinetics
- Novo Nordisk
- Idorsia Pharmaceuticals
- Topics
- Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › Cardiac Valve Diseases and Treatments
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › ECG Monitoring and Analysis
- Keywords
- aortic stenosis, community-based screening, disease progression trajectories, mortality prediction, heart failure risk, pacemaker rate, ARIC cohort, unsupervised clustering, risk reclassification, false-positive screening results, left ventricular dysfunction
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
