Automated assessment of psychiatric disorders using speech: A systematic review

Abstract

Objective There are many barriers to accessing mental health assessments including cost and stigma. Even when individuals receive professional care, assessments are intermittent and may be limited partly due to the episodic nature of psychiatric symptoms. Therefore, machine‐learning technology using speech samples obtained in the clinic or remotely could one day be a biomarker to improve diagnosis and treatment. To date, reviews have only focused on using acoustic features from speech to detect depression and schizophrenia. Here, we present the first systematic review of studies using speech for automated assessments across a broader range of psychiatric disorders. Methods We followed the Preferred Reporting Items for Systematic Reviews and Meta‐Analysis (PRISMA) guidelines. We included studies from the last 10 years using speech to identify the presence or severity of disorders within the Diagnostic and Statistical Manual of Mental Disorders (DSM‐5). For each study, we describe sample size, clinical evaluation method, speech‐eliciting tasks, machine learning methodology, performance, and other relevant findings. Results 1395 studies were screened of which 127 studies met the inclusion criteria. The majority of studies were on depression, schizophrenia, and bipolar disorder, and the remaining on post‐traumatic stress disorder, anxiety disorders, and eating disorders. 63% of studies built machine learning predictive models, and the remaining 37% performed null‐hypothesis testing only. We provide an online database with our search results and synthesize how acoustic features appear in each disorder. Conclusion Speech processing technology could aid mental health assessments, but there are many obstacles to overcome, especially the need for comprehensive transdiagnostic and longitudinal studies. Given the diverse types of data sets, feature extraction, computational methodologies, and evaluation criteria, we provide guidelines for both acquiring data and building machine learning models with a focus on testing hypotheses, open science, reproducibility, and generalizability. Level of Evidence 3a

Improving Mental Health Services: A 50-Year Journey from Randomized Experiments to Artificial Intelligence and Precision Mental Health

“…This suggests that we need more studies on diagnosis and AI. A very informative synthesis and review are provided by Low et al ( 2020 ). They screened 1395 studies and reviewed the 127 that met the inclusion criterion: studies from the last 10 years using speech to identify the presence or severity of disorders through ML methods.…”

“…A comprehensive and in-depth review of 127 studies that have used speech to assess psychiatric disorders is provided by Low et al ( 2020 ). They conclude that speech processing technology could assist in mental health assessments but believe that there are many obstacles to this use, including the need for longitudinal studies.…”

Automatic Detection of Depression in Speech Using Ensemble Convolutional Neural Networks

“…However, presently, there is a growth interest in developing this kind of application for real-world scenarios where, at least, the data acquisition is done through microphone-enabled smart devices and/or other wearable technologies that what would allow the remote monitoring of patients [ 20 , 49 ]. According to [ 50 ], apart from the consent forms, two main strategies for strengthening privacy can be considered. The first approach consists of the extraction of acoustic features from which it is not possible to reconstruct the raw speech signal.…”

Voice perturbations under the stress overload in young individuals: phenotyping and suboptimal health as predictors for cascading pathologies

“…Hundreds of muscles, innervated by a different network of the cranial and spinal nerve, subcortical, and cortical parts of the brain are involved in the production and processing of voice [ 1 ]. Contextually, the human voice is a complex phenomenon reflecting both—the mental and physical health of an individual [ 2 ]. According to the American Academy of Otolaryngology-Head and Neck Surgery Foundation, voice perturbations are defined as any abnormalities in the vocal quality, pitch, loudness, and vocal effort that influence communication or generate a negative effect on the voice-related quality of life [ 3 , 4 ].…”