SYDNEY, Australia: Scientists in Australia have developed an “explainable” artificial intelligence (AI) tool that could help doctors diagnose schizophrenia by analysing brainwave patterns, reported Xinhua.
Researchers from Australia’s James Cook University (JCU) found machine learning models can distinguish between healthy individuals and those with schizophrenia, even under conditions of acute stress, according to a JCU statement released on Tuesday.
The team tested new machine learning algorithms on the electroencephalography (EEG) brainwave patterns of healthy, stressed and schizophrenic patients, and found the brain responds differently in people with schizophrenia than in healthy people when they are stressed.
Schizophrenia affects about 1 per cent of the global population and is linked to high mortality. Making improved diagnosis and early detection is critical for effective management, said the study published in the journal ’Biomedical Signal Processing and Control’.
The team used open-access EEG datasets and developed algorithms capable of accounting for the impact of stress on EEG brainwaves, producing patterns consistent with established medical knowledge.
Researchers said AI is designed to support doctors, not replace them, and explainable AI could help improve access to timely care in remote areas. – BERNAMA-XINHUA
