A deep learning-based approach to diagnose mild traumatic brain injury using audio classification
Source check: Source checked. Not independent scientific confirmation.
Finding: A particle-swarm-optimized Bi-LSTM-A classified speech features from a pilot rugby-athlete dataset, reporting AUROC 0.904, sensitivity 94.7% and specificity 86.2% for mild traumatic brain injury. The small study dataset limits generalization and does not establish clinical utility.
Technology: A particle-swarm-optimized bidirectional LSTM with attention classifies speech MFCC features for mild traumatic brain injury.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- A particle-swarm-optimized bidirectional LSTM with attention classifies speech MFCC features for mild traumatic brain injury.
- Test and result
- A particle-swarm-optimized Bi-LSTM-A classified speech MFCC features for mild traumatic brain injury, reporting AUROC 0.904, sensitivity 94.7% and specificity 86.2%.
- Limitation / still unknown
- The pilot dataset is small; generalization and clinical utility were not established.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://doi.org/10.1371/journal.pone.0274395 · https://europepmc.org/article/MED/36170287 · https://europepmc.org/articles/PMC9518857 · https://www.ncbi.nlm.nih.gov/research/bionlp/RESTful/pmcoa.cgi/BioC_json/PMC9518857/unicode · https://pubmed.ncbi.nlm.nih.gov/36170287/
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 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.