A multimodal Bayesian Network for symptom-level depression and anxiety prediction from voice and speech data
Authors:
Preprint
Abstract
During psychiatric assessment, clinicians observe not only what patients report, but important nonverbal signs such as tone, speech rate, fluency, responsiveness, and body language. Weighing and integrating these different information sources is a challenging task and a good candidate for support by intelligence-driven tools - however this is yet to be realized in the clinic. Here, we argue that several important barriers to adoption can be addressed using Bayesian network modelling. To demonstrate this, we evaluate a model for depression and anxiety symptom prediction from voice and speech features in large-scale datasets (30,135 unique speakers). Alongside performance for conditions and symptoms (for depression, anxiety ROC-AUC=0.842,0.831 ECE=0.018,0.015; core individual symptom ROC-AUC>0.74), we assess demographic fairness and investigate integration across and redundancy between different input modality types. Clinical usefulness metrics and acceptability to mental health service users are explored. When provided with sufficiently rich and large-scale multimodal data streams and specified to represent common mental conditions at the symptom rather than disorder level, such models are a principled approach for building robust assessment support tools: providing clinically-relevant outputs in a transparent and explainable format that is directly amenable to expert clinical supervision.Keywords
All Related Versions
This publication has 54 references indexed in Scilit:
- Ethical Dimensions of Digital Phenotyping Within the Context of Mental HealthcareJournal of Technology in Behavioral Science, 2024
- Interpreting area under the receiver operating characteristic curveThe Lancet Digital Health, 2022
- The network of stress-related states and depression and anxiety symptoms during the COVID-19 lockdownJournal of Affective Disorders, 2021
- The Mental Health Quality of Life Questionnaire (MHQoL): development and first psychometric evaluation of a new measure to assess quality of life in people with mental health problemsQuality of Life Research, 2021
- A comprehensive scoping review of Bayesian networks in healthcare: Past, present and futureArtificial Intelligence in Medicine, 2021
- Unraveling the comorbidity of depression and anxiety in a large inpatient sample: Network analysis to examine bridge symptomsDepression and Anxiety, 2021
- What do clinicians treat: Diagnoses or symptoms? The incremental validity of a symptom-based, dimensional characterization of emotional disorders in predicting medication prescription patternsComprehensive Psychiatry, 2017
- Tracking Responses to Items in Measures as a Means of Increasing Therapeutic Engagement in Clients: A Complementary Clinical Approach to Tracking OutcomesClinical Psychology & Psychotherapy, 2014
- The PHQ-8 as a measure of current depression in the general populationJournal of Affective Disorders, 2009
- A Brief Measure for Assessing Generalized Anxiety DisorderArchives of internal medicine (1960), 2006