Hostname: page-component-8448b6f56d-m8qmq Total loading time: 0 Render date: 2024-04-23T17:56:13.923Z Has data issue: false hasContentIssue false

Multimodal validation of facial expression detection software for real-time monitoring of affect in patients with suicidal intent

Published online by Cambridge University Press:  23 March 2020

F. Amico*
Affiliation:
Newcastle Hospital, Psychiatry, Newcastle, Ireland
G. Healy
Affiliation:
Dublin City University, The Insight Centre for Data Analytics, Dublin, Ireland
M. Arvaneh
Affiliation:
The University of Sheffield, Department of Automatic Control and Systems Engineering, Sheffield, United Kingdom
D. Kearney
Affiliation:
University of Maynooth, Biomedical Engineering Research Group, Maynooth, Ireland
E. Mohedano
Affiliation:
Dublin City University, The Insight Centre for Data Analytics, Dublin, Ireland
D. Roddy
Affiliation:
Newcastle Hospital, Psychiatry, Newcastle, Ireland
J. Yek
Affiliation:
Newcastle Hospital, Psychiatry, Newcastle, Ireland
A. Smeaton
Affiliation:
Dublin City University, The Insight Centre for Data Analytics, Dublin, Ireland
J. Brophy
Affiliation:
Newcastle Hospital, Psychiatry, Newcastle, Ireland
*
*Corresponding author.

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.

Facial expression is an independent and objective marker of affect. Basic emotions (fear, sadness, joy, anger, disgust and surprise) have been shown to be universal across human cultures. Techniques such as the Facial Action Coding System can capture emotion with good reliability. Such techniques visually process the changes in different assemblies of facial muscles that produce the facial expression of affect.

Recent groundbreaking advances in computing and facial expression analysis software now allow real-time and objective measurement of emotional states. In particular, a recently developed software package and equipment, the Imotion Attention Tool™, allows capturing information on discreet emotional states based on facial expressions while a subject is participating in a behavioural task.

Extending preliminary work by further experimentation and analysis, the present findings suggests a link between facial affect data to already established peripheral arousal measures such as event related potentials (ERP), heart rate variability (HRV) and galvanic skin response (GSR) using disruptively innovative, noninvasive and clinically applicable technology in patients reporting suicidal ideation and intent compared to controls. Our results hold promise for the establishment of a computerized diagnostic battery that can be utilized by clinicians to improve the evaluation of suicide risk.

Disclosure of interest

The authors have not supplied their declaration of competing interest.

Type
EV1240
Copyright
Copyright © European Psychiatric Association 2016
Submit a response

Comments

No Comments have been published for this article.