Objective methods for reliable detection of concealed depression

Recent research has shown that it is possible to automatically detect clinical depression from audio-visual recordings. Before considering integration in a clinical pathway, a key question that must be asked is whether such systems can be easily fooled. This work explores the potential of acoustic f...

Full description

Bibliographic Details
Main Authors: Solomon, Cynthia, Valstar, Michel F., Morriss, Richard K., Crowe, John
Format: Article
Published: Frontiers 2015
Subjects:
Online Access:https://eprints.nottingham.ac.uk/31309/
_version_ 1848794173888528384
author Solomon, Cynthia
Valstar, Michel F.
Morriss, Richard K.
Crowe, John
author_facet Solomon, Cynthia
Valstar, Michel F.
Morriss, Richard K.
Crowe, John
author_sort Solomon, Cynthia
building Nottingham Research Data Repository
collection Online Access
description Recent research has shown that it is possible to automatically detect clinical depression from audio-visual recordings. Before considering integration in a clinical pathway, a key question that must be asked is whether such systems can be easily fooled. This work explores the potential of acoustic features to detect clinical depression in adults both when acting normally and when asked to conceal their depression. Nine adults diagnosed with mild to moderate depression as per the Beck Depression Inventory (BDI-II) and Patient Health Questionnaire (PHQ-9) were asked a series of questions and to read a excerpt from a novel aloud under two different experimental conditions. In one, participants were asked to act naturally and in the other, to suppress anything that they felt would be indicative of their depression. Acoustic features were then extracted from this data and analysed using paired t-tests to determine any statistically significant differences between healthy and depressed participants. Most features that were found to be significantly different during normal behaviour remained so during concealed behaviour. In leave-one-subject-out automatic classification studies of the 9 depressed subjects and 8 matched healthy controls, an 88% classification accuracy and 89% sensitivity was achieved. Results remained relatively robust during concealed behaviour, with classifiers trained on only non-concealed data achieving 81% detection accuracy and 75% sensitivity when tested on concealed data. These results indicate there is good potential to build deception-proof automatic depression monitoring systems.
first_indexed 2025-11-14T19:11:59Z
format Article
id nottingham-31309
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T19:11:59Z
publishDate 2015
publisher Frontiers
recordtype eprints
repository_type Digital Repository
spelling nottingham-313092020-05-04T17:06:52Z https://eprints.nottingham.ac.uk/31309/ Objective methods for reliable detection of concealed depression Solomon, Cynthia Valstar, Michel F. Morriss, Richard K. Crowe, John Recent research has shown that it is possible to automatically detect clinical depression from audio-visual recordings. Before considering integration in a clinical pathway, a key question that must be asked is whether such systems can be easily fooled. This work explores the potential of acoustic features to detect clinical depression in adults both when acting normally and when asked to conceal their depression. Nine adults diagnosed with mild to moderate depression as per the Beck Depression Inventory (BDI-II) and Patient Health Questionnaire (PHQ-9) were asked a series of questions and to read a excerpt from a novel aloud under two different experimental conditions. In one, participants were asked to act naturally and in the other, to suppress anything that they felt would be indicative of their depression. Acoustic features were then extracted from this data and analysed using paired t-tests to determine any statistically significant differences between healthy and depressed participants. Most features that were found to be significantly different during normal behaviour remained so during concealed behaviour. In leave-one-subject-out automatic classification studies of the 9 depressed subjects and 8 matched healthy controls, an 88% classification accuracy and 89% sensitivity was achieved. Results remained relatively robust during concealed behaviour, with classifiers trained on only non-concealed data achieving 81% detection accuracy and 75% sensitivity when tested on concealed data. These results indicate there is good potential to build deception-proof automatic depression monitoring systems. Frontiers 2015-04-15 Article PeerReviewed Solomon, Cynthia, Valstar, Michel F., Morriss, Richard K. and Crowe, John (2015) Objective methods for reliable detection of concealed depression. Frontiers in ICT, 2 (5). ISSN 2297-198X behaviomedics depression affective computing social signal processing automatic audio analysis http://journal.frontiersin.org/article/10.3389/fict.2015.00005/abstract doi:10.3389/fict.2015.00005 doi:10.3389/fict.2015.00005
spellingShingle behaviomedics
depression
affective computing
social signal processing
automatic audio analysis
Solomon, Cynthia
Valstar, Michel F.
Morriss, Richard K.
Crowe, John
Objective methods for reliable detection of concealed depression
title Objective methods for reliable detection of concealed depression
title_full Objective methods for reliable detection of concealed depression
title_fullStr Objective methods for reliable detection of concealed depression
title_full_unstemmed Objective methods for reliable detection of concealed depression
title_short Objective methods for reliable detection of concealed depression
title_sort objective methods for reliable detection of concealed depression
topic behaviomedics
depression
affective computing
social signal processing
automatic audio analysis
url https://eprints.nottingham.ac.uk/31309/
https://eprints.nottingham.ac.uk/31309/
https://eprints.nottingham.ac.uk/31309/