AI Science Tracker
EN

Accurate and Low-Cost Cardiac Disorder Detection from Wearable Phonocardiogram Signals Using Hybrid Feature Selection and Machine Learning.

Department of Electrical and Electronics Engineering, Zonguldak Bülent Ecevit University, Zonguldak 67100, Türkiye · 29 May 2026 · medicine

Discovery

Accurate and Low-Cost Cardiac Disorder Detection from Wearable Phonocardiogram Signals Using Hybrid Feature Selection and Machine Learning.

Source check: Source checked. Not independent scientific confirmation.

Finding: mRMR/ReliefF/Kruskal-Wallis feature selection with k-NN/SVM/Bagged Tree; PSO/ACO optimize selected subsets. Results reports 99.80% accuracy and 99.50% F1 for Kruskal-Wallis+k-NN; validation is benchmark-dataset evaluation as stated in paper.

Technology: mRMR/ReliefF/Kruskal-Wallis feature selection with k-NN/SVM/Bagged Tree; PSO/ACO optimize selected subsets.

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

AI contribution
mRMR/ReliefF/Kruskal-Wallis feature selection with k-NN/SVM/Bagged Tree; PSO/ACO optimize selected subsets.
Test and result
Benchmark-dataset evaluation reported 99.80% accuracy and 99.50% F1 for Kruskal–Wallis feature selection with k-nearest neighbors; the result is limited to the reported dataset.
Limitation / still unknown
External replication and real-world or clinical benefit were not established by the reviewed study
Evidence sources and annotation context

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

Evidence sources: https://europepmc.org/articles/PMC13297422?pdf=render · https://pubmed.ncbi.nlm.nih.gov/42345866/

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 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 in the full catalog for filters, charts and related discoveries. Browse medicine discoveries.