VoxNeuro: Leakage-Safe Parkinson Screening Support via Multi-View Grassmannian Speech Analysis
- 1Voxneuro
Abstract
Parkinsons disease (PD) affects speech production, motivating classification from repeated voice measurements. Record-wise evaluation can place recordings from the same participant in both training and test sets. We propose VoxNeuro, a novel subject-level framework combining Grassmann representations of repeated recordings with Euclidean mean-dispersion summaries through a provably positive-semidefinite kernel for support vector classification. Features undergo training-fold Gaussian rank normalization, and a supervised partial least squares subspace ensemble is activated when the feature count exceeds the number of training recordings. Two public cohorts were evaluated, UCI-489 (80 subjects) and PD-252 (252 subjects), each with three sustained-vowel recordings per subject. At the reference five-fold subject-disjoint partition, balanced accuracy was 87.5% and 81.6%, respectively, exceeding all five standard comparators under identical folds and normalization. PD-252 sensitivity was 89.9% and specificity was 73.4%. Across 20 additional subject partitions, PD-252 balanced accuracy averaged 78.4%, with a mean paired advantage of 3.2 percentage points over the highest-scoring standard comparator. VoxNeuro exceeded each standard comparator in at least 19 partitions for both balanced accuracy and macro-F1. Ablations favored rank normalization and the unaugmented supervised-subspace configuration on PD-252. VoxNeuro thus offers an effective and reproducible framework for subject-level analysis of repeated speech measurements in PD screening research.
Related
- A leakage-aware and interpretable machine learning framework for ovarian cancer prediction using the PLCO screening dataset
- Extracting smoking history from clinical notes for lung cancer screening decision support: comparing a structured-judgment model with general-purpose large language models
- Comprehensive genetic screening of the South African Parkinson's disease study collection using the NeuroBooster array.
- Energy and spectral indicators support screening for soil structure interaction sensitivity in steel moment frames
- MemTrax as a scalable digital triage tool for mild cognitive impairment screening: primary validation in Alzheimer’s disease and exploratory analysis in Parkinson’s disease
BibTeX
@misc{khan2026voxneuro,
title = {{VoxNeuro: Leakage-Safe Parkinson Screening Support via Multi-View Grassmannian Speech Analysis}},
author = {L. Khan and M. Waghe},
howpublished = {medRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.27.26364114},
url = {https://www.medrxiv.org/content/10.64898/2026.09.27.26364114v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - VoxNeuro: Leakage-Safe Parkinson Screening Support via Multi-View Grassmannian Speech Analysis
AU - L. Khan
AU - M. Waghe
PY - 2026
DA - 2026/09/27
PB - medRxiv
DO - 10.64898/2026.09.27.26364114
UR - https://www.medrxiv.org/content/10.64898/2026.09.27.26364114v1
AB - Parkinsons disease (PD) affects speech production, motivating classification from repeated voice measurements. Record-wise evaluation can place recordings from the same participant in both training and test sets. We propose VoxNeuro, a novel subject-level framework combining Grassmann representations of repeated recordings with Euclidean mean-dispersion summaries through a provably positive-semidefinite kernel for support vector classification. Features undergo training-fold Gaussian rank normalization, and a supervised partial least squares subspace ensemble is activated when the feature count exceeds the number of training recordings. Two public cohorts were evaluated, UCI-489 (80 subjects) and PD-252 (252 subjects), each with three sustained-vowel recordings per subject. At the reference five-fold subject-disjoint partition, balanced accuracy was 87.5% and 81.6%, respectively, exceeding all five standard comparators under identical folds and normalization. PD-252 sensitivity was 89.9% and specificity was 73.4%. Across 20 additional subject partitions, PD-252 balanced accuracy averaged 78.4%, with a mean paired advantage of 3.2 percentage points over the highest-scoring standard comparator. VoxNeuro exceeded each standard comparator in at least 19 partitions for both balanced accuracy and macro-F1. Ablations favored rank normalization and the unaugmented supervised-subspace configuration on PD-252. VoxNeuro thus offers an effective and reproducible framework for subject-level analysis of repeated speech measurements in PD screening research.
ER -