Over the last few years, Artificial Intelligence has been playing a key role in the healthcare industry. AI machines like IBM’s Watson is now widely used in diagnoses of critical diseases such as cancer. The accuracy with which these machines are performing is astonishing, sometimes even outperforming their human counterparts. Thanks to the latest developments in the field AI is now beginning to leave its marks in the field of psychiatry.

No Blood Test for Mind

A team of scientists from the Institute of Cognitive Science at the University of Colorado at Boulder is now working on an AI-based app that can analyze the patient’s mental health. “We are not in any way trying to replace clinicians,” says Peter Foltz a research professor at the Institute of and co-author of a new paper in Schizophrenia Bulletin. The paper talks about the promises and potential pitfalls of adopting AI in psychiatry. “But we do believe we can create tools that will allow them to better monitor their patients.”

Nearly one in five Americans suffer from some kind of mental illness and many of them live in remote areas where they don’t have access to a psychologist. Even for people who have the access they might not have time and money for regular visits. For those who can afford and access regular visits diagnostics, especially early diagnostics, might not be easy as doctors have to largely depend on patient’s speech for diagnostic. “Humans are not perfect. They can get distracted and sometimes miss out on subtle speech cues and warning signs,” notes paper co-author Brita Elvevåg, a cognitive neuroscientist at the University of Tromsø, Norway. “Unfortunately, there is no objective blood test for mental health.”

Language Maybe The Key

The app, Installed in the patient’s phone can keep track of the patient’s mental health by a 5-10 daily conversation with the patient. The app will ask the patient to carry out simple tasks such as tell a story or ask them about their emotional state. The app also gives them touch and gestures based tasks to check their motor skills. The app then will look for patterns that might be a potential warning. For example, a low voice tone might be a symptom of depression or lack of logical clarity in sentences may be an early symptom of schizophrenia. If the app notices any worrisome changes it can notify the assigned psychiatrist.”Language is a critical pathway to detecting patient mental states,” says Foltz. “Using mobile devices and AI, we are able to track patients daily and monitor these subtle changes.”

The paper also calls for a rigorous framework to evaluate effects AI making in the field and thus nurture trustworthiness.