High Predictive Accuracy of Negative Schizotypy With Acoustic Measures

Abstract

Negative schizotypal traits potentially can be digitally phenotyped using objective vocal analysis. Prior attempts have shown mixed success in this regard, potentially because acoustic analysis has relied on small, constrained feature sets. We employed machine learning to (a) optimize and cross-validate predictive models of self-reported negative schizotypy using a large acoustic feature set, (b) evaluate model performance as a function of sex and speaking task, (c) understand potential mechanisms underlying negative schizotypal traits by evaluating the key acoustic features within these models, and (d) examine model performance in its convergence with clinical symptoms and cognitive functioning. Accuracy was good (> 80%) and was improved by considering speaking task and sex. However, the features identified as most predictive of negative schizotypal traits were generally not considered critical to their conceptual definitions. Implications for validating and implementing digital phenotyping to understand and quantify negative schizotypy are discussed.

Automated analysis of speech as a marker of sub-clinical psychotic experiences

“…Also, within the context of subclinical psychosis, studies using schizotypy as a framework have provided valuable insights [to the deeper understanding of schizotypy concept, the authors suggest reading the work of (61)(62)(63)]. High level of schizotypy has been associated with alterations in speech production, speech variability, and speech content (64)(65)(66). Furthermore, studies have demonstrated that individuals with high schizotypy exhibit alterations in acoustic features of speech like reduced speech variability, expressiveness and atypical pitch patterns compared to those with lower schizotypy scores (20,67).…”

Exploring the relationship between frequent cannabis use, vocal changes and language use

“…In mental health research, speech changes are analysed in terms of language use and vocal parameters, usually after sampling a few minutes of speech elicited with standardized prompts and applying computerized, automated techniques to extract different features of speech. Vocal or paralinguistic analysis evaluates the physical aspects of spoken language after representing sound as waveforms and extract temporal, prosodic or frequency features regarding formants, pitch, frequency, duration, pauses and volume (Agurto et al, Jul 2020b;Albuquerque et al, 2021;Coelho et al, 2021;Cohen et al, 2022;Olah et al, 2023). The modern analysis of language use leverages Natural Language Processing, applied on speech transcripts.…”