Detecting Neurodegenerative Diseases using Frame-Level Handwriting Embeddings

TL;DR

This study uses spectrogram representations of handwriting signals combined with CNN models to classify neurodegenerative diseases, achieving high accuracy especially in distinguishing Alzheimer's disease from healthy controls.

Contribution

It introduces a novel approach of using frame-level handwriting spectrograms with CNNs for neurodegenerative disease detection, highlighting the impact of task and spectrogram parameters.

Findings

Highest F1-score of 89.8% for AD vs. controls

CNN outperformed CNN-BLSTM models

Optimal window length varies by disease

Abstract

In this study, we explored the use of spectrograms to represent handwriting signals for assessing neurodegenerative diseases, including 42 healthy controls (CTL), 35 subjects with Parkinson's Disease (PD), 21 with Alzheimer's Disease (AD), and 15 with Parkinson's Disease Mimics (PDM). We applied CNN and CNN-BLSTM models for binary classification using both multi-channel fixed-size and frame-based spectrograms. Our results showed that handwriting tasks and spectrogram channel combinations significantly impacted classification performance. The highest F1-score (89.8%) was achieved for AD vs. CTL, while PD vs. CTL reached 74.5%, and PD vs. PDM scored 77.97%. CNN consistently outperformed CNN-BLSTM. Different sliding window lengths were tested for constructing frame-based spectrograms. A 1-second window worked best for AD, longer windows improved PD classification, and window length had little effect on PD vs. PDM.