Machine Learning-Based Detection of Parkinson's Disease From Arabic Speech: A Cross-Linguistic Validation Study.
Source check: Source checked. Not independent scientific confirmation.
Finding: A Parkinson-disease speech pipeline combined Whisper-derived audio-to-text and deep voice features with feature selection, dimensionality reduction and twelve classifiers; it was developed on 40 Arabic speakers and checked on an independent Spanish cohort of 100.
Technology: A Parkinson-disease speech pipeline combined Whisper-derived audio-to-text and deep voice features with feature selection, dimensionality reduction and twelve classifiers; it was developed on 40 Arabic speakers and checked on an independent Spanish cohort of 100.
Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.
- AI contribution
- A Parkinson-disease speech pipeline combined Whisper-derived audio-to-text and deep voice features with feature selection, dimensionality reduction and twelve classifiers; it was developed on 40 Arabic speakers and checked on an independent Spanish cohort of 100.
- Test and result
- Linear Discriminant Analysis reached 90% accuracy under leave-one-out validation in the Arabic set and the independent Spanish test reached 83% accuracy; small cohorts limit clinical generalization.
- Limitation / still unknown
- The reviewed source does not establish prospective benefit, broad external validity, or replication beyond the reported study.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC13145026/
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 3/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.