Using Acoustic Speech Patterns From Smartphones to Investigate Mood Disorders: Scoping Review (Preprint)

Show simple item record Flanagan, Olivia Chan, Amy Roop, Partha Sundram, Frederick 2022-05-03T01:29:35Z 2022-05-03T01:29:35Z 2020-09-15
dc.identifier.citation (2020).
dc.description.abstract <sec> <title>BACKGROUND</title> <p>Mood disorders are commonly underrecognized and undertreated, as diagnosis is reliant on self-reporting and clinical assessments that are often not timely. Speech characteristics of those with mood disorders differs from healthy individuals. With the wide use of smartphones, and the emergence of machine learning approaches, smartphones can be used to monitor speech patterns to help the diagnosis and monitoring of mood disorders.</p> </sec> <sec> <title>OBJECTIVE</title> <p>The aim of this review is to synthesize research on using speech patterns from smartphones to diagnose and monitor mood disorders.</p> </sec> <sec> <title>METHODS</title> <p>Literature searches of major databases, Medline, PsycInfo, EMBASE, and CINAHL, initially identified 832 relevant articles using the search terms “mood disorders”, “smartphone”, “voice analysis”, and their variants. Only 13 studies met inclusion criteria: use of a smartphone for capturing voice data, focus on diagnosing or monitoring a mood disorder(s), clinical populations recruited prospectively, and in the English language only. Articles were assessed by 2 reviewers, and data extracted included data type, classifiers used, methods of capture, and study results. Studies were analyzed using a narrative synthesis approach.</p> </sec> <sec> <title>RESULTS</title> <p>Studies showed that voice data alone had reasonable accuracy in predicting mood states and mood fluctuations based on objectively monitored speech patterns. While a fusion of different sensor modalities revealed the highest accuracy (97.4%), nearly 80% of included studies were pilot trials or feasibility studies without control groups and had small sample sizes ranging from 1 to 73 participants. Studies were also carried out over short or varying timeframes and had significant heterogeneity of methods in terms of the types of audio data captured, environmental contexts, classifiers, and measures to control for privacy and ambient noise.</p> </sec> <sec> <title>CONCLUSIONS</title> <p>Approaches that allow smartphone-based monitoring of speech patterns in mood disorders are rapidly growing. The current body of evidence supports the value of speech patterns to monitor, classify, and predict mood states in real time. However, many challenges remain around the robustness, cost-effectiveness, and acceptability of such an approach and further work is required to build on current research and reduce heterogeneity of methodologies as well as clinical evaluation of the benefits and risks of such approaches.</p> </sec>
dc.rights Items in ResearchSpace are protected by copyright, with all rights reserved, unless otherwise indicated. Previously published items are made available in accordance with the copyright policy of the publisher.
dc.subject Patient Safety
dc.subject Brain Disorders
dc.subject Clinical Research
dc.subject Behavioral and Social Science
dc.subject Mental Health
dc.subject 4.2 Evaluation of markers and technologies
dc.subject 4.1 Discovery and preclinical testing of markers and technologies
dc.title Using Acoustic Speech Patterns From Smartphones to Investigate Mood Disorders: Scoping Review (Preprint)
dc.type Journal Article
dc.identifier.doi 10.2196/preprints.24352 2022-04-18T23:06:18Z
dc.rights.holder Copyright: The author en
dc.rights.accessrights en
pubs.elements-id 824116 Engineering Medical and Health Sciences Pharmacy School of Medicine Psychological Medicine Dept Department of Electrical, Computer and Software Engineering
pubs.record-created-at-source-date 2022-04-19

Files in this item

Find Full text

This item appears in the following Collection(s)

Show simple item record


Search ResearchSpace