Scientists making use of artificial intelligence have indeed discovered a hidden clue in people’s language that can also accurately predict whether they are likely to develop psychosis in the future.
The machine-learning method is more precisely quantifies the semantic richness of people’s conversational language, a known indicator for psychosis.
The research indicates that automated analysis of the two language variables― indeed more frequent use of words associated with sound and speaking with low semantic density, or rather vagueness―can predict whether an at-risk person will indeed later develop psychosis with 93 percent accuracy.
Even trained clinicians had not noticed how people at risk for psychosis use more words associated with sound than the average, although abnormal auditory perception is a pre-clinical symptom.
One does try to hear these subtleties in conversations with people which are like trying to see microscopic germs with one’s eyes.
The automated technique that one has developed is a really sensitive tool to detect these hidden patterns. It is like a microscope for warning signs of psychosis.
It was indeed previously known that subtle features of future psychosis are rather present in people’s language, but one has used machine learning to uncover hidden details about those features.
There have been findings that add to the evidence showing the potential for making use of machine learning to identify linguistic abnormalities associated with mental illness.
The onset of schizophrenia as well as other psychotic disorders does typically occur in the early 20s, with warning signs, much referred to as prodromal syndrome beginning around age 17.
About 25 to 30 percent of youth who do meet criteria for a prodromal syndrome that will develop schizophrenia or another psychotic disorder.
Using structured interviews as well as cognitive tests, trained clinicians can indeed predict psychosis with about 80 percent accuracy in those with a prodromal syndrome.
Machine-learning research is indeed among the many ongoing efforts to streamline diagnostic methods, thus identifying new variables, and improve the accuracy of predictions. Currently, there is no cure for psychosis.
In case one can identify individuals who are at risk earlier and also use preventive interventions, one might be able to reverse the deficits.
There are rather good data available that are showing that treatments such as cognitive-behavioral therapy can delay onset, and perhaps even reduce the occurrence of psychosis.
AI language analysis does help clinicians to predict psychosis with 93% accuracy: Machine learning was indeed able not only to detect speech patterns indicative of psychosis but also to be able to identify a new pattern associated with the prodromal phase of psychosis, thus enabling an algorithm to predict the later emergence of psychosis with more than 90 percent accuracy.
Computers can indeed predict schizophrenia much based upon how a person does talks. In fact, several studies of at-risk youths have indeed found that doctors are rather able to guess “jarring disruptions” in otherwise ordinary speech. AI can in indeed predict psychosis risk in everyday language.
