Subject-independent Parkinson's Disease Detection through A Lightweight Spectrotemporal Hybrid Network.
- 1Department of Information Technology, Payame Noor University, Tehran, Iran.
Abstract
Background
Vocal impairment constitutes a prominent prodromal biomarker for Parkinson's disease (PD). However, existing deep learning solutions often rely on computationally intensive architectures or biased validation protocols. This study proposes the lightweight spectrotemporal hybrid network (LST-Net), a resource-efficient framework for robust PD screening.Methods
The model employs a dual-stream architecture that concurrently processes raw one-dimensional waveforms and two-dimensional Mel-spectrograms to capture complementary cues, specifically transient temporal jitters and spectral energy patterns. The proposed architecture was evaluated on the Italian Parkinson's Voice and Speech dataset using a strict subject-independent 5-fold cross-validation protocol to prevent data leakage.Results
The proposed LST-Net achieved a robust segment-level accuracy of 96.69%. By implementing a subject-level majority voting strategy, mimicking clinical diagnosis where patients are assessed over time, the model successfully classified all subjects in the held-out test sets (100% subject-level accuracy). Quantitative Gradient-weighted Class Activation Mapping analysis confirmed the model's focus on clinically relevant low-frequency tremors (mean energy: 61.56% ±27.90%).Conclusions
This framework demonstrates that explicit spectrotemporal fusion yields superior diagnostic performance without heavy computational burdens, offering a verifiable and scalable solution for real-time deployment on edge devices.
Related
- Static and dynamic noise abolish altruistic biases in Parkinson's disease independent of deep brain stimulation
- Personalized stress detection from wearable physiological signals via Digital Twin-inspired subject embeddings and recurrent neural networks
- Impulse Control Disorders Are Independent of Parkinson Disease Motor Subtypes
- A lightweight deep learning model for real-time in-vehicle driver distraction detection with low-latency inference
- Cross-corpus consensus feature selection for language-invariant Parkinson’s disease detection: a dual-stream acoustic and spectrogram-attention framework
BibTeX
@article{masoudi2026subjectindependent,
title = {{Subject-independent Parkinson's Disease Detection through A Lightweight Spectrotemporal Hybrid Network.}},
author = {Babak Masoudi},
journal = {Journal of medical signals and sensors},
year = {2026},
month = oct,
doi = {10.4103/jmss.jmss_137_25},
url = {https://europepmc.org/article/MED/42924316},
note = {CC BY-NC-SA},
}
RIS
TY - JOUR
TI - Subject-independent Parkinson's Disease Detection through A Lightweight Spectrotemporal Hybrid Network.
AU - Babak Masoudi
PY - 2026
DA - 2026/10/01
JO - Journal of medical signals and sensors
DO - 10.4103/jmss.jmss_137_25
UR - https://europepmc.org/article/MED/42924316
AB - Background Vocal impairment constitutes a prominent prodromal biomarker for Parkinson's disease (PD). However, existing deep learning solutions often rely on computationally intensive architectures or biased validation protocols. This study proposes the lightweight spectrotemporal hybrid network (LST-Net), a resource-efficient framework for robust PD screening.Methods The model employs a dual-stream architecture that concurrently processes raw one-dimensional waveforms and two-dimensional Mel-spectrograms to capture complementary cues, specifically transient temporal jitters and spectral energy patterns. The proposed architecture was evaluated on the Italian Parkinson's Voice and Speech dataset using a strict subject-independent 5-fold cross-validation protocol to prevent data leakage.Results The proposed LST-Net achieved a robust segment-level accuracy of 96.69%. By implementing a subject-level majority voting strategy, mimicking clinical diagnosis where patients are assessed over time, the model successfully classified all subjects in the held-out test sets (100% subject-level accuracy). Quantitative Gradient-weighted Class Activation Mapping analysis confirmed the model's focus on clinically relevant low-frequency tremors (mean energy: 61.56% ±27.90%).Conclusions This framework demonstrates that explicit spectrotemporal fusion yields superior diagnostic performance without heavy computational burdens, offering a verifiable and scalable solution for real-time deployment on edge devices.
SN - 2228-7477
ER -