AI has helped scientists in discovering a hidden clue in people's language which can correctly predict whether they are probable to develop psychosis in future.

The AI and ML process more accurately measures the semantic richness of people's conversational language, a recognized indicator for psychosis.

According to the research, published in the journal npj Schizophrenia, automated analysis of the two language variables — more common use of words associated with sound and speaking with reduced semantic density, or vagueness — can predict whether an at-risk person will later develop psychosis with 93 percent exactness.

It has been seen that, trained clinicians had not observed how people at risk for psychosis use more words connected with sound than the average, while abnormal auditory insight is a pre-clinical symptom.

"Trying to hear these subtleties in conversations with people is like trying to see microscopic germs with your eyes," said Neguine Rezaii, who performed the research at Emory University in the US.

"The AI automated technique we've developed is a really sensitive tool to detect these hidden patterns. It's like a microscope for warning signs of psychosis," said Rezaii, who is currently at Harvard University in the US.

"It was previously known that subtle features of future psychosis are present in people's language, but we've used AI and ML to actually uncover hidden details about those features," said Phillip Wolff, a professor at Emory University.

The findings show the possibility for using AI and machine learning to detect linguistic abnormalities associated with mental illness, said Elaine Walker, an Emory professor.

The inception of schizophrenia and other psychotic disorders usually occurs in the early 20s, with warning signs — known as prodromal syndrome — starting around age 17.

Around 25 to 30 percent of youth those meet criteria for a prodromal syndrome will develop schizophrenia or another psychotic disorder.

Using prepared interviews and cognitive tests, trained clinicians can guess psychosis with about 80 percent accuracy in those having a prodromal syndrome.

Machine-learning research is among the numerous ongoing efforts to modernize diagnostic methods, discover new variables, and advance the accuracy of predictions. Presently, there is no cure for psychosis.

"If we can identify individuals who are at risk earlier and use preventive interventions, we might be able to reverse the deficits," Walker said.

"There are good data showing that treatments like cognitive-behavioural therapy can delay onset, and perhaps even reduce the occurrence of psychosis," she said.