Written by Alimat Aliyeva
Australian scientists have developed an “explainable” artificial intelligence (AI) tool to help doctors diagnose schizophrenia by analyzing brainwave patterns.
Azel News The report cited foreign media.
Researchers at Australia’s James Cook University (JCU) have found that a machine learning model can distinguish between healthy individuals and patients with schizophrenia, even under conditions of acute stress, according to a university statement released on Tuesday.
The research team tested a new machine learning algorithm based on electroencephalogram (EEG) data collected from healthy participants, stressed individuals, and patients diagnosed with schizophrenia. The results showed that the brains of people with schizophrenia respond differently to stress than people without schizophrenia.
Schizophrenia affects approximately 1% of the world’s population and is associated with an increased risk of mortality, making early detection and accurate diagnosis particularly important for effective treatment and long-term management, according to a study published in the journal Biomedical Signal Processing and Control.
Using open-access EEG datasets, the researchers developed an algorithm that can explain how stress affects brainwave activity, producing results consistent with established neurological findings.
Importantly, the system is described as “explainable AI.” This means not only providing a diagnosis, but also showing the reasoning behind that conclusion. This is an increasingly important feature in medical applications where transparency is important.
The researchers emphasized that AI is intended to support clinicians, not replace them. In particular, explainable AI systems could help improve access to mental health diagnosis in remote and underserved areas, where expert psychiatrists are often unavailable.
An interesting aspect of this development is that it highlights a broader shift in medical AI. The focus is shifting from purely high-precision “black box” systems to models that can justify decisions in terms that humans can understand. If successfully integrated into clinical practice, such tools could not only speed diagnosis but also help physicians better understand the neurological impact of stress-related mental illnesses.
