RECA-PD: A Robust Explainable Cross-Attention Method for Speech-based Parkinson's Disease Classification
This addresses the need for explainable AI in clinical settings for early, non-invasive detection of Parkinson's Disease, which affects over 10 million people, but it is incremental as it builds on existing deep-learning models.
The authors tackled the problem of speech-based Parkinson's Disease classification by proposing RECA-PD, a robust and explainable cross-attention method that matches state-of-the-art performance while providing more consistent and clinically meaningful explanations.
Parkinson's Disease (PD) affects over 10 million people globally, with speech impairments often preceding motor symptoms by years, making speech a valuable modality for early, non-invasive detection. While recent deep-learning models achieve high accuracy, they typically lack the explainability required for clinical use. To address this, we propose RECA-PD, a novel, robust, and explainable cross-attention architecture that combines interpretable speech features with self-supervised representations. RECA-PD matches state-of-the-art performance in Speech-based PD detection while providing explanations that are more consistent and more clinically meaningful. Additionally, we demonstrate that performance degradation in certain speech tasks (e.g., monologue) can be mitigated by segmenting long recordings. Our findings indicate that performance and explainability are not necessarily mutually exclusive. Future work will enhance the usability of explanations for non-experts and explore severity estimation to increase the real-world clinical relevance.