AI Science Tracker
EN

Leviev Cardiovascular Institute, Sheba Medical Center, Ramat Gan, Israel

1 discovery from 2026

Discoveries

Deep learning analysis of sinus-rhythm echocardiography for the identification of patients with atrial fibrillation

Source check: Source checked. Not independent scientific confirmation.

Finding: In 85,686 retrospective TTE studies, the model achieved AUC 0.85 on an independent test set and model-positive classification among patients without prior AF was associated with subsequent documented AF (adjusted HR 1.64) and adverse outcomes (adjusted HR 1.24). Independent 20% patient-level holdout test and longitudinal outcomes; single tertiary-center retrospective cohort, routine documentation may miss AF, and authors call for external/prospective validation. No exact matching result in frozen active or archived catalogs.

Technology: A deep neural network analyzes apical four-chamber and parasternal long-axis echocardiography videos acquired in sinus rhythm to identify AF-associated imaging signals.

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
A deep neural network analyzes apical four-chamber and parasternal long-axis echocardiography videos acquired in sinus rhythm to identify AF-associated imaging signals.
Test and result
In 85,686 retrospective TTE studies, the model achieved AUC 0.85 on an independent test set and model-positive classification among patients without prior AF was associated with subsequent documented AF (adjusted HR 1.64) and adverse outcomes (adjusted HR 1.24).
Limitation / still unknown
Independent 20% patient-level holdout test and longitudinal outcomes; single tertiary-center retrospective cohort, routine documentation may miss AF, and authors call for external/prospective validation. No exact matching result in frozen active or archived catalogs.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://academic.oup.com/ehjdh/article/7/9/ztag168/8957476

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: Primary source full text Methods and Results; version/date checked against bibliographic record..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open the interactive profile for the timeline, or browse all organizations and model families.