Using AI To Spot Psychosis
Using AI To Spot Psychosis
The symptoms of psychosis in speech are pretty subtle, rather than a severe disruption to our ability to communicate, so they can be hard to detect. AI can help.
Join the DZone community and get the full member experience.Join For Free
The most visionary programmers today dream of what a robot could do, just like their counterparts in 1976 dreamed of what personal computers could do. Read more on MistyRobotics.com and enter to win your own Misty.
I've written previously about the growing capability of AI to analyze our voice for everything from speech disorders to PTSD. A recent paper highlights how the technology can also be used to predict psychosis in at-risk youths.
The researchers used AI to analyze audio transcripts of conversations between youths and staff to predict the development of psychosis within two years with an accuracy of 83%. It was able to pick up things such as a disturbance in the flow of meaning when speaking (or going off track to you and I) to make an accurate prediction.
It was also able to accurately distinguish the speech of individuals with psychosis from their healthy peers. The results suggest that it's possible to use technology to better predict and then treat psychosis and other disorders.
Disorganized thought is a well-known symptom of psychosis, and is, therefore, something that assessments specifically look for. It's typically characterized by things such as tangential language, simpler speech, and a looseness of association. The symptoms are pretty subtle, however, rather than a severe disruption to our ability to communicate, so they can be hard to detect. As the symptoms exist from an early stage of psychosis, it can be an important signal to find.
The researchers examined transcripts of a number of young people who had all been predicted to develop psychosis in the next few years. The transcripts were analyzed using natural language processing to determine how their speech differed from healthy peers.
"The results of this study are exciting because this technology has the potential to improve prediction of psychosis and ultimately help us prevent psychosis by helping researchers develop remediation and training strategies that target the cognitive deficits that may underlie language dis-turbance," the authors say.
"More broadly, language and behavior are the primary sources of data for psychiatrists to diagnose and treat mental disorders," they conclude. "There are now novel computerized methods to characterize complex behaviors such as language. Speech is easy to collect and inexpensive to analyze using computer-based analysis. This technology could be applied across psychiatry, and plausibly in other fields of medicine."
Published at DZone with permission of Adi Gaskell , DZone MVB. See the original article here.
Opinions expressed by DZone contributors are their own.