Scientists in England have developed a new, AI-based language tool that could help diagnose and assess psychiatric conditions including Schizophrenia.
The research team from University College London Queen Square Institute for Neurology (UCL) , in partnership with Oxford University aims to understand how the automated analysis of language could help doctors and scientists diagnose and monitor several psychiatric conditions.
Currently, the psychiatric diagnosis process is based predominantly on talking with patients and those around them, with minimal tests such as blood tests and brain scans.
A statement from UCL explains “…this lack of precision prevents a richer understanding of the causes of mental illness, and the monitoring of treatment.”
The researchers asked 26 participants with schizophrenia and 26 control participants to complete two verbal fluency tasks, in which they were given 5 minutes to name as many words as possible, belonging categories: “animals” or starting with the letter “p”.
The team then used an AI language model that had been trained on vast amounts of internet text to represent the meaning of words in a similar way to humans, to analyze the answers and data collected. They specifically tested whether the words the groups spontaneously recalled could be predicted by the AI model, and whether this predictability was reduced in patients with schizophrenia.
Results showed that the answers given by the control participants were more predictable by the AI model than those given by the participants with schizophrenia. This difference was most significant in patients with more severe symptoms.
Scientists believe that this difference could be explained by the brain’s method of learning relationships between memories and ideas; stored mental layouts known as “cognitive maps”.
The team at UCL supported this theory in a following part of the study whereby brain scanning was used to measure brain activity in areas responsible for learning and storing in ‘cognitive maps’.
Lead author, Dr Matthew Nour (UCL Queen Square Institute of Neurology and University of Oxford), said: “Until very recently, the automatic analysis of language has been out of reach of doctors and scientists. However, with the advent of artificial intelligence (AI) language models such as ChatGPT, this situation is changing. This work shows the potential of applying AI language models to psychiatry – a medical field intimately related to language and meaning.”
The team from UCL and Oxford plan to use this technology in a larger sample of patients, with more diverse variables to decide if it could be useful in clinical diagnosis.
“We are entering a very exciting time in neuroscience and mental health research. By combining state-of-the-art AI language models and brain scanning technology, we are beginning to uncover how meaning is constructed in the brain, and how this might go awry in psychiatric disorders. There is enormous interest in using AI language models in medicine. If these tools prove safe and robust, I expect they will begin to be deployed in the clinic within the next decade.” Dr Nour added.
