Researchers have developed AI-based tools that can identify subtle speech patterns in schizophrenia patients. This approach, described in a study in PNAS, aims to enhance the diagnostic precision currently relying mainly on patient conversations. In tests involving verbal fluency tasks, the AI model was less predictable in patients with schizophrenia, especially those with severe symptoms. This unpredictability is believed to be connected to ‘cognitive maps’ in the brain. The team aims to further evaluate this technology’s clinical efficacy in the coming years.