Abstract
Negative symptoms are a transdiagnostic feature of serious mental illness (SMI) that can be potentially “digitally phenotyped” using objective vocal analysis. In prior studies, vocal measures show low convergence with clinical ratings, potentially because analysis has used small, constrained acoustic feature sets. We sought to evaluate (1) whether clinically rated blunted vocal affect (BvA)/alogia could be accurately modelled using machine learning (ML) with a large feature set from two separate tasks (i.e., a 20-s “picture” and a 60-s “free-recall” task), (2) whether “Predicted” BvA/alogia (computed from the ML model) are associated with demographics, diagnosis, psychiatric symptoms, and cognitive/social functioning, and (3) which key vocal features are central to BvA/Alogia ratings. Accuracy was high (>90%) and was improved when computed separately by speaking task. ML scores were associated with poor cognitive performance and social functioning and were higher in patients with schizophrenia versus depression or mania diagnoses. However, the features identified as most predictive of BvA/Alogia were generally not considered critical to their operational definitions. Implications for validating and implementing digital phenotyping to reduce SMI burden are discussed.
Highlights
Blunted vocal affect (BvA) and alogia, defined in terms of reduced vocal prosody and verbal production, respectively, are diagnostic criteria of schizophrenia[1] and are present in major depressive, posttraumatic, neurocognitive, and neurodegenerative spectrum disorders[2,3,4]
The present study used machine-learning analysis of computerized vocal measures procured from a large sample of patients with serious mental illness (SMI) to redress issues with these prior studies
Our aims were to: (1) evaluate whether clinically rated blunted vocal affect (BvA) and alogia can be accurately modeled from acoustic features extracted from the natural speech of two distinct speaking tasks, (2) evaluate if model accuracy changes as a function of these separate speaking tasks, (3) evaluate the convergence/divergence of BvA/alogia measured using machine learning versus clinical ratings to demographic characteristics, psychiatric symptoms and cognitive and social functioning, and (4) evaluate the key features from the models
Summary
Blunted vocal affect (BvA) and alogia, defined in terms of reduced vocal prosody and verbal production, respectively, are diagnostic criteria of schizophrenia[1] and are present in major depressive, posttraumatic, neurocognitive, and neurodegenerative spectrum disorders[2,3,4]. Our aims were to: (1) evaluate whether clinically rated BvA and alogia can be accurately modeled from acoustic features extracted from the natural speech of two distinct speaking tasks, (2) evaluate if model accuracy changes as a function of these separate speaking tasks, (3) evaluate the convergence/divergence of BvA/alogia measured using machine learning versus clinical ratings to demographic characteristics, psychiatric symptoms and cognitive and social functioning, and (4) evaluate the key features from the models This final step involved “opening the contents of the black box”, as it were, to provide potential insight into how BvA/alogia is rated by clinicians.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.