Proof-of-Concept Study: a Mobile Application to Derive Clinical Outcome Measures from Expression and Speech for Mental Health Status Evaluation

Francesco Luke Siena,David Crundall,Michael Vernon,Paul Watts,Bill Byrom,Philip Breedon

doi:10.1007/s10916-020-01671-x

Francesco Luke Siena, David Crundall + Show 4 more

Open Access

https://doi.org/10.1007/s10916-020-01671-x

Copy DOI

Abstract

This proof-of-concept study aimed to assess the ability of a mobile application and cloud analytics software solution to extract facial expression information from participant selfie videos. This is one component of a solution aimed at extracting possible health outcome measures based on expression, voice acoustics and speech sentiment from video diary data provided by patients. Forty healthy volunteers viewed 21 validated images from the International Affective Picture System database through a mobile app which simultaneously captured video footage of their face using the selfie camera. Images were intended to be associated with the following emotional responses: anger, disgust, sadness, contempt, fear, surprise and happiness. Both valence and arousal scores estimated from the video footage associated with each image were adequate predictors of the IAPS image scores (p < 0.001 and p = 0.04 respectively). 12.2% of images were categorised as containing a positive expression response in line with the target expression; with happiness and sadness responses providing the greatest frequency of responders: 41.0% and 21.4% respectively. 71.2% of images were associated with no change in expression. This proof-of-concept study provides early encouraging findings that changes in facial expression can be detected when they exist. Combined with voice acoustical measures and speech sentiment analysis, this may lead to novel measures of health status in patients using a video diary in indications including depression, schizophrenia, autism spectrum disorder and PTSD amongst other conditions.

Highlights

Mental health disorders are among the most common health conditions affecting the adult population [1]
Good correspondence of the International Affective Picture System (IAPS)-designated target emotion with the self-ratings of participants provides some confidence that the images used to target emotional responses in these participants were appropriate despite known concerns regarding self-report measures noted above
Inspection of the video footage showed that in these cases facial expression following exposure to an image did not change throughout the subsequent 5-s interval

Summary

Introduction

Mental health disorders are among the most common health conditions affecting the adult population [1]. Anxiety and depressive disorders are estimated to affect over 322 million and 264 million people worldwide respectively [2]. Over 50% of the general population in middle- and high-income countries are estimated to suffer from at least one mental health disorder in their lifetimes [4]. In the EU, it is estimated that each year almost 40% of the population suffer from some form of mental health condition [5], with anxiety disorders affecting around 14% of the population, and insomnia and major depressive disorders the highest affecting 7% and 6.9% respectively [5]. Spending in health and social care related to mental health in England is estimated to account for around 12% of the National Health Service budget and cost approximately US$28 billion a year [6]

Methods

Results

Conclusion