AI Science Tracker
EN

School of Electronic and Information Engineering (SEIE)

1 discovery from 2022

Discoveries

Inter-Patient Congestive Heart Failure Detection Using ECG-Convolution-Vision Transformer Network.

Source check: Source checked. Not independent scientific confirmation.

Finding: ECVT-Net distinguished CHF from normal ECG beats under a patient-separated evaluation, reporting 98.88% accuracy. The result is limited to the two named databases and does not establish clinical deployment or disease-specific generalization across acquisition sources.

Technology: A convolutional/vision-transformer network operates on ECG heartbeat segments; Methods §§2–3 describe MIT-BIH normal and BIDMC CHF databases and patient-grouped splits.

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

AI contribution
A convolutional/vision-transformer network operates on ECG heartbeat segments; Methods §§2–3 describe MIT-BIH normal and BIDMC CHF databases and patient-grouped splits.
Test and result
Inter-patient Results §3 reports 98.88% accuracy (98.94% average sensitivity; CHF sensitivity 99.79%) on held-out patients.
Limitation / still unknown
Patient-separated test scheme is reported, but normal and CHF classes come from different databases, so database/acquisition differences may confound apparent disease discrimination.
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/35590972 · https://pmc.ncbi.nlm.nih.gov/articles/PMC9104351/?report=xml · https://pubmed.ncbi.nlm.nih.gov/35590972/

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 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 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.