Advances in AI has allowed for computers to help doctors in diagnosing disease and help monitor patients’ vital signs from any location.
A team of researchers from the University of Colorado Boulder are working to apply machine learning artificial intelligence (AI) in psychiatry, with a speech-based mobile app that can categorise a patient’s mental health status as well as, or better than, a human can.
Peter Foltz, a research professor at the Institute of Cognitive Science and co-author of the paper, said: “We are not in any way trying to replace clinicians, but we do believe we can create tools that will allow them to better monitor their patients.”
Accessing mental health care
Diagnosis of mental health disorders are based on an age-old method that can be subjective and unreliable, notes paper co-author Brita Elvevåg, a cognitive neuroscientist at the University of Tromsø, Norway.
Elvevåg said: “Humans are not perfect. They can get distracted and sometimes miss out on subtle speech cues and warning signs.
“Unfortunately, there is no objective blood test for mental health.”
Elvevåg and Foltz teamed up to develop machine learning technology that is able to more precisely detect day-to-day changes in speech that hint at mental health decline.
For instance, sentences that don’t follow a logical pattern can be a critical symptom in schizophrenia. Shifts in tone or pace can hint at mania or depression, and memory loss can be a sign of both cognitive and mental health problems.
“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.”
AI in psychiatry
The new mobile app asks patients to answer a five to 10 minute series of questions by talking into their phone. Among various other tasks, they’re asked about their emotional state, asked to tell a short story, listen to a story and repeat it and given a series of touch-and-swipe motor skills tests.
The team developed an AI system that assesses the speech samples, compares them to previous samples by the same patient and the broader population, and then rates the patient’s mental state.
The team asked human clinicians to listen to and assess speech samples of 225 participants – half with severe psychiatric issues; half healthy volunteers – in rural Louisiana and Northern Norway. They then compared those results to those of the machine learning system.
If the app detected a worrisome change, it could notify the patient’s doctor to check in.
Foltz said: “We found that the computer’s AI models can be at least as accurate as clinicians.
“Patients often need to be monitored with frequent clinical interviews by trained professionals to avoid costly emergency care and unfortunate events, but there are simply not enough clinicians for that.”
In the paper, the researchers lay out a call for larger studies to prove efficacy and earn public trust before AI technology could be broadly brought into clinical practice for psychiatry.
The paper states: ‘The mystery around AI does not nurture trustworthiness, which is critical when applying medical technology.
‘Rather than looking for machine learning models to become the ultimate decision-maker in medicine, we should leverage the things that machines do well that are distinct from what humans do well.’