The IBM Research Group on Computational Psychiatry and Neuroimaging is working to use computer training to predict the risk of developing psychosis, and he has just published a second study in which AI can prove to be a valuable tool when it comes to assessing mental health.
Also Read:
1. Thinking Machine Can beat all Modern Copyright Laws!
2. Scientists Create Clones of Monkeys-Are Humans Next?
Working with the publication in 2015, the team used AI to analyze the speech patterns of 59 people who participated in a separate study. The transcripts of the interview, in which the participants took part, were broken up into parts of the speech and were calculated how consistent the sentences were.
Then the model of machine learning was determined on the basis of these speech models, who had a risk of developing psychosis and who did not. Of these participants, 19 developed a psychotic disorder for two years, and 40 did not, and the model was able to predict this with 83 percent accuracy.
He also was able to differentiate speech patterns of patients who had recently developed psychosis in patients with healthy patients with a 72 percent accuracy. The program found that those who are at risk of psychosis used fewer possessive pronouns when pronouncing and constructing less concerted sentences.
Although the work is still ongoing, it shows that AI can be an effective tool and can be especially useful when mental health professionals are in short supply or inaccessible. "We believe this is an important step towards developing a tool for mental health professionals, carers and patients with a tool that can expand and increase the coverage of neuropsychiatric evaluation outside the clinic," the study's author Guillermo Cecchi said in a blog post.
In the video above, he says that the ability to predict the risk of developing psychosis in a few years can help health professionals and mental health professionals better distribute their resources and provide better care for those who are at risk.
Cecchi points out that one of the areas where this can have an impact is the homeless, who probably do not have the resources to seek medical care. "Given that I feel that we can do something, we must," he says.
Also Read:
1. Smart Technology- Clothes Turned into Power Generators
2. Neuralink -Connecting the Human Brain to Computers!
The study was recently published in World Psychiatry, and Cecchi says that the team will share additional work with other mental health conditions, including depression, Alzheimer's disease, Parkinson's disease and chronic pain.