Non-invasive localization of the ventricular excitation origin without patient-specific geometries using deep learning
Source check: Source checked. Not independent scientific confirmation.
Finding: Two CNNs trained on more than one million simulated body-surface-potential maps were evaluated on clinical ECG/BSPM data to localize ventricular excitation origin. The arXiv v1 reported median localization error of 32 mm and up to 82% transmural-position detection; this is a proof of principle, not clinical deployment or outcome benefit.
Technology: Two CNNs trained on simulated ECG/body-surface-potential maps localize ventricular excitation origin.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Two CNNs trained on simulated ECG/body-surface-potential maps localize ventricular excitation origin.
- Test and result
- Preprint Results: clinical localization median error 32 mm, up to 82% transmural-position detection; ranked top-3 results improved localization. This is a proof of principle, with substantial residual error.
- Limitation / still unknown
- Methods/Results use simulated test data plus a separate clinical dataset; the article reports clinical test error and classification performance but no clinical deployment or patient outcomes. Narrow technical clinical-reference validation only.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://europepmc.org/article/MED/37673581 · https://arxiv.org/abs/2209.08095 · https://arxiv.org/pdf/2209.08095 · https://www.sciencedirect.com/science/article/pii/S0933365723001331 · https://pubmed.ncbi.nlm.nih.gov/37673581/
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..
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 2/5 · Validation 2/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.