AI innovation: Eye movement analysis detects depression rapidly
Polish scientists have developed an innovative system capable of detecting depression and anxiety in just 10 seconds by analyzing eye movement. Thanks to artificial intelligence, the accuracy of this method reaches 70 percent, and researchers are optimistic about further improvements.
In collaboration with three universities, Polish researchers are pioneering a new frontier in diagnosing mental disorders through the study of eye movements. This AI-based system allows for the quick identification of mental health issues. The research was published in the International Journal of Marketing, Communication and New Media.
The trial involved 101 participants, including patients with depression, individuals with social anxiety, and healthy participants as a control group. They were asked to observe images of faces displaying various emotions for 10 seconds while eye trackers recorded their eye movements. This data was used to create gaze paths, which were then analyzed using neural networks.
Eye movement patterns as an indicator of psychological condition
"Eye movement patterns can provide objective data about our psychological condition. Depressed individuals tend to focus on negative stimuli," said Dr. Karol Chlasta from Kozminski University, co-author of the study and expert in artificial intelligence, during a conversation with PAP.
He added, "People with social anxiety display increased scanning activity of faces, a phenomenon in psychology known as hyperscanning." Dr. Chlasta also noted that these prolonged face scanning paths highlight the sensitivity of such individuals to social stimuli.
The method is effective in up to 70 percent of cases
Psychologists and AI experts, including Dr. hab. Krzysztof Krejtz and Dr. hab. Izabela Krejtz from SWPS University, and Dr. Katarzyna Wisiecka from AEH in Warsaw, also contributed to the project. The method achieves 60–70 percent accuracy in detecting depression and social anxiety, which is comparable to traditional methods.
This new approach is faster and less burdensome for patients, allowing for easier monitoring of changes in mental health. The system can be integrated with everyday devices such as laptops, smartphones, or VR goggles. Dr. Chlasta likens it to smartwatches that monitor sleep rhythms; in this case, it analyzes vision.
Expanding research into voice analysis
Researchers are also applying AI to voice analysis for diagnosing depression and neurological disorders. Dr. Chlasta notes that changes in voice can serve as early warning signs of depression, dementia, or Alzheimer's disease, allowing for quicker medical consultations.
"In many disorders, our voice undergoes subtle changes, much like an overworked computer running a bit slower. It must switch between different tasks. In humans, changes in speech organ function often go unnoticed, but a system based on artificial neural networks can identify these changes immediately, even from brief speech samples," explains Dr. Chlasta.
The creators emphasize that depression and social anxiety are among the most common mental disorders, with cases continually increasing. The World Health Organization forecasts that by 2030, depression will be the most frequently diagnosed disease worldwide. In Poland, approximately four million people suffer from it, although many cases remain unreported. Quick analysis of eye movements can provide valuable insights into mental health and encourage medical consultation.
Need for further research and systemic changes
Further research is essential for the widespread implementation of this new method. Dr. Chlasta points out that additional data, which is not systematically collected, is needed, and societal trust in AI remains low. Without further data, it will be challenging to transition from laboratory settings to practical applications. Systemic changes are also required to facilitate broader monitoring of mental health.
