Polish scientists unveil rapid AI tool for detecting depression
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, this method boasts an accuracy rate of 70 percent, and researchers believe there is potential to improve it further.
Polish artificial intelligence technology could revolutionize the diagnosis of mental disorders through eye movement analysis. Researchers from three Polish universities have created an AI-based system that enables the rapid detection of these conditions. Their research is detailed in the International Journal of Marketing, Communication and New Media.
The study involved 101 participants, including individuals with depression, people with social anxiety, and a control group of healthy participants. The subjects were asked to watch images of faces expressing various emotions for 10 seconds, while special sensors in eye trackers recorded their eye movements. The data collected 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. We notice a tendency in depressed individuals to focus on negative stimuli," said Dr. Karol Chlasta from Kozminski University, a co-author of the study and an expert in artificial intelligence, in a conversation with PAP.
He added, "People with social anxiety show increased activity in scanning faces due to a psychological phenomenon known as hyperscanning." The co-author also noted that this is manifested by prolonged face scanning paths, indicating these individuals' sensitivity 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, participated in the project. The method achieves 60 to 70 percent accuracy for depression and social anxiety cases, comparable to traditional methods.
This new approach is faster and less burdensome for the patient than traditional methods, making it easier to monitor changes in mental state. The system can be integrated with everyday devices, such as laptops, smartphones, or VR goggles. Dr. Chlasta compares it to smartwatches that monitor sleep rhythms; in this case, it analyzes vision.
Expanding research into voice analysis
Researchers are also exploring AI applications in voice analysis for diagnosing depression and neurological disorders. Dr. Chlasta notes that voice changes can be an early warning sign of depression, dementia, or Alzheimer's disease, allowing for a quicker response and consultation with a doctor.
"In many disorders, our voice changes slightly. It's like an overworked computer running somewhat slower as it switches between tasks. In humans, changes in the speech organs' functioning are often difficult to detect, but a system based on artificial neural networks can identify them immediately, even from short speech excerpts," explains Dr. Chlasta.
The system's creators emphasize that depression and social anxiety are among the most common mental disorders, with the number of affected individuals continuing to rise. According to WHO forecasts, by 2030, depression will be the most frequently diagnosed disease worldwide. In Poland, about 4 million people currently suffer from it, although many cases go unnoticed. Quick analysis of eye movements can provide valuable insights into mental states and serve as an important signal for consultation with a doctor.
Need for further research and systemic changes
Further research is necessary to widely implement the new method. Dr. Chlasta explains that additional data, which is not systematically collected, is needed, and social trust in AI remains low. Without this data, moving beyond laboratory conditions and demonstrating the prototype in operational settings will be difficult. Systemic changes are also needed to enable broader-scale mental health monitoring.
