Artificial intelligence might help scientists identify the patients who are suffering from schizophrenia. A machine learning algorithm was used for the first time by Bo Cao, who is a psychiatry researcher in the U of A’s Faculty.
The machine learning algorithm managed to measure the connections of the superior temporal cortex to other regions of the brain. By doing this, patients with schizophrenia were identified with 78 percent accuracy.
“This is the first step, but ultimately we hope to find reliable biomarkers that can predict schizophrenia before the symptoms show up,” explained Cao. This is an important step forward as the algorithm also managed to predict whether a patient would respond positively to a certain treatment.
Improvements to come
While the algorithm is able to predict schizophrenia, Cao wants to improve it. “We also want to use machine learning to optimize a patient’s treatment plan. It wouldn’t replace the doctor, however, in the future, with the help of machine learning, if the doctor can select the best medicine or procedure for a specific patient at the first visit, it would be a good step forward.”
Even more improvements will become available in the future, as Cao’s team of scientists aims to study other mental illnesses as well. This could mean that artificial intelligence will be able to diagnose a wide range of illnesses, and then provide the correct treatment as well.
“It will be a joint effort of the patients, psychiatrists, neuroscientists, computer scientists and researchers in other disciplines to build better tools for precise mental health,” he said. “We have a Computational Psychiatry group at U of A with a team of excellent clinicians and scientists to work collaboratively on this challenging problem,” finally concluded Bo Cao.