Sad Eyes Are Real: Your Smartphone May Soon Recognize Depression in Your Face
Monday. October 7, 2024.
Nearly 300 million people face depression every day. Early detection can make all the difference.
But imagine if your smartphone could help you identify the signs of depression just by analyzing your face.
Thanks to innovative research from Stevens Institute of Technology, this may soon become a reality.
Led by Professor Sang Won Bae and doctoral candidate Rahul Islam, two groundbreaking apps have been developed to revolutionize how we detect mental health issues.
These AI-powered tools could transform your smartphone into a personal mental health checker, giving you insight into your emotional well-being by analyzing subtle changes in your eyes and facial expressions.
PupilSense: A Window Into Your Eyes
The first app, PupilSense, is designed to analyze your eye movements. For decades, researchers have found that pupillary responses are linked to depressive episodes. But now, this knowledge has been distilled into a tool that could soon be at your fingertips.
When you're using your smartphone, PupilSense quietly takes snapshots of your eyes during 10-second intervals. The app measures the size of your pupils relative to your irises.
In a four-week study involving 25 volunteers, the app analyzed an impressive 16,000 interactions.
The results? PupilSense was 76% accurate in identifying depressive episodes — a significant improvement over existing smartphone-based mental health detection systems.
This innovation could offer a convenient, non-invasive way to track mental health by leveraging a device we all use daily.
FacePsy: Your Mood in Focus
But the team didn’t stop with just your eyes. They’ve developed another app called FacePsy that looks at facial expressions to detect shifts in mood.
“A growing body of psychological studies suggests that depression is characterized by nonverbal signals such as facial muscle movements and head gestures,” explains Bae.
FacePsy runs in the background of your phone, analyzing facial movements and expressions during regular use.
Don’t worry about privacy—once the system processes the image, it is deleted almost immediately. What’s fascinating about the findings is that even smiling could indicate depression.
Surprising? Bae explains that putting on a “brave face” is often a coping mechanism for those experiencing emotional distress.
Other indicators included fewer facial movements in the morning and specific head movements. For instance, yawing head motions in the early hours seemed to correlate with increased depressive symptoms.
Why Smartphones? Accessibility is Key
So why focus on smartphones? It’s simple: nearly everyone uses them. Smartphones offer unparalleled accessibility, making them an ideal tool for detecting early signs of depression.
“Since most people in the world today use smartphones daily, this could be a useful detection tool that’s already built and ready to be used,” notes Bae.
Unlike other AI-based depression detection systems that may require wearing special devices, these smartphone apps are far less intrusive. They provide a simple, readily available method for keeping track of mental health — without the need for expensive gadgets.
The Road Ahead
While these apps show great promise, they are still in the early stages of development.
The team has made PupilSense available open-source on GitHub to encourage other developers and researchers to build upon their work.
Meanwhile, FacePsy has been presented as an exciting first step toward creating a compact, cost-effective, and easy-to-use diagnostic tool for mental health.
These developments mark an exciting shift in how we approach mental health care, offering the possibility of early detection and intervention using everyday technology.
As this research progresses, the potential impact on global mental health could be profound.
In the future, the apps on your phone may be more than just tools for socializing or getting work done. They could become powerful allies in protecting your mental health.
By monitoring subtle changes in your eyes and face, these innovations may soon offer a convenient, accessible, and effective way to detect the early warning signs of depression — empowering depressed folks to seek help sooner and potentially changing lives.
Be Well, Stay Kind, and Godspeed.
RESEARCH:
Bae, S. W., & Islam, R. (2024). PupilSense: AI-powered smartphone app for detecting depressive episodes. ACM International Conference on Mobile Human-Computer Interaction (MobileHCI).
Bae, S. W., & Islam, R. (2024). FacePsy: AI-powered app to monitor facial expressions for mental health analysis. ACM International Conference on Mobile Human-Computer Interaction (MobileHCI).
World Health Organization. (2024). Depression: Key facts. https://www.who.int/news-room/fact-sheets/detail/depression