Quantifying Articulatory Coordination as a Biomarker for Schizophrenia
This work addresses the need for interpretable biomarkers in clinical psychiatry to assess schizophrenia symptom severity, though it is incremental in applying existing speech analysis methods to this domain.
The researchers tackled the problem of limited interpretability in AI-based diagnostic tools for schizophrenia by developing a framework that quantifies vocal tract coordination from speech features, achieving reliable separation of coordination patterns and correlations with symptom severity scores like BPRS.
Advances in artificial intelligence (AI) and deep learning have improved diagnostic capabilities in healthcare, yet limited interpretability continues to hinder clinical adoption. Schizophrenia, a complex disorder with diverse symptoms including disorganized speech and social withdrawal, demands tools that capture symptom severity and provide clinically meaningful insights beyond binary diagnosis. Here, we present an interpretable framework that leverages articulatory speech features through eigenspectra difference plots and a weighted sum with exponential decay (WSED) to quantify vocal tract coordination. Eigenspectra plots effectively distinguished complex from simpler coordination patterns, and WSED scores reliably separated these groups, with ambiguity confined to a narrow range near zero. Importantly, WSED scores correlated not only with overall BPRS severity but also with the balance between positive and negative symptoms, reflecting more complex coordination in subjects with pronounced positive symptoms and the opposite trend for stronger negative symptoms. This approach offers a transparent, severity-sensitive biomarker for schizophrenia, advancing the potential for clinically interpretable speech-based assessment tools.