Clinical state tracking in serious mental illness through computational analysis of speech

Autor: Victor R. Martinez, Kenneth B. Wells, David J. Miklowitz, Shrikanth S. Narayanan, Armen C. Arevian, Daniel Bone, Nikolaos Malandrakis
Jazyk: angličtina
Rok vydání: 2020
Předmět:
Male
Bipolar Disorder
Support Vector Machine
Emotions
Social Sciences
Pilot Projects
0302 clinical medicine
Residence Characteristics
Medicine and Health Sciences
Psychology
Depression (differential diagnoses)
Language
Multidisciplinary
Depression
Physics
Mental Disorders
Middle Aged
3. Good health
Semantics
Schizophrenia
Physical Sciences
Medicine
Major depressive disorder
Female
Clinical psychology
Research Article
Science
Schizoaffective disorder
03 medical and health sciences
Mental Health and Psychiatry
medicine
Speech
Humans
Bipolar disorder
Disease burden
business.industry
Mood Disorders
Cognitive Psychology
Biology and Life Sciences
Computational Biology
Linguistics
Acoustics
medicine.disease
Mental illness
Mental health
030227 psychiatry
Cognitive Science
business
030217 neurology & neurosurgery
Neuroscience
Zdroj: PLoS ONE
PLoS ONE, Vol 15, Iss 1, p e0225695 (2020)
ISSN: 1932-6203
Popis: Individuals with serious mental illness experience changes in their clinical states over time that are difficult to assess and that result in increased disease burden and care utilization. It is not known if features derived from speech can serve as a transdiagnostic marker of these clinical states. This study evaluates the feasibility of collecting speech samples from people with serious mental illness and explores the potential utility for tracking changes in clinical state over time. Patients (n = 47) were recruited from a community-based mental health clinic with diagnoses of bipolar disorder, major depressive disorder, schizophrenia or schizoaffective disorder. Patients used an interactive voice response system for at least 4 months to provide speech samples. Clinic providers (n = 13) reviewed responses and provided global assessment ratings. We computed features of speech and used machine learning to create models of outcome measures trained using either population data or an individual's own data over time. The system was feasible to use, recording 1101 phone calls and 117 hours of speech. Most (92%) of the patients agreed that it was easy to use. The individually-trained models demonstrated the highest correlation with provider ratings (rho = 0.78, p
Databáze: OpenAIRE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje