Key result
AI-ECG AK-AVS model identifies screening false positives at ~4-fold higher risk for AS hospitalization.
Why the study?
Early aortic stenosis detection remains challenging, with many patients presenting late when left ventricular dysfunction may be irreversible.
Does the AK-AVS AI-based ECG model accurately detect moderate/severe aortic stenosis in the community and predict long-term mortality in pre-TAVR patients?
Observational (n=5,672)
Does the AK-AVS AI-based ECG model accurately detect moderate/severe aortic stenosis in the community and predict long-term mortality in pre-TAVR patients?
Hazard Ratio: 1.48
p-value: p=0.005
An AI-enhanced ECG model can detect moderate/severe aortic stenosis in community screening and identify distinct longitudinal trajectories that independently predict mortality in TAVR recipients beyond traditional risk scores.
No takes yet. Share an insight, caveat, or question.
May aid community AS screening with AI-ECG; leaves open prospective validation before clinical adoption.
Background 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 community screening potential of the AK-AVS model. Methods We conducted two complementary analyses: (1) community validation of the AK-AVS model in 3,632 cardiovascular disease-free ARIC participants, and (2) longitudinal trajectory analysis of 7,860 ECGs from 2,040 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. Results In community screening (n=16 moderate/severe AS), AK-AVS achieved an AUROC 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 hospitalization (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). Conclusions 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.
Segar et al. (2026) conducted an observational in Aortic stenosis (n=5,672). AK-AVS AI-enhanced ECG model vs. Stable Low trajectory was evaluated on Mortality (HR 1.48, p=0.005). Longitudinal AI-ECG trajectory patterns independently predicted mortality in TAVR recipients (Persistently High pattern: HR 1.48, p=0.005) and improved risk reclassification beyond traditional scores.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: