Researchers at Columbia University, the New York State Psychiatric Institute, and the IBM T.J. Watson Research center have developed a computer program that can predict the future onset of schizophrenia in young people with 100% accuracy, according to a study published Wednesday in the journal Schizophrenia.
The researchers interviewed 34 at-risk youths, and the automated speech-analysis program monitored their speech for disjointed speech patterns, which point towards disorganized thoughts—symptoms of schizophrenia.
How did they accomplish this?
They did this for two-and-a-half years, and the speech-analysis program was able to correctly identify future psychotic breaks with 100% accuracy. This is a drastic improvement over what doctors can do simply by interviewing people and tracking their speech patterns—at best, doctors can predict schizophrenia with only 79% accuracy.
“In our study, we found that minimal semantic coherence—the flow of meaning from one sentence to the next—was characteristic of those young people at risk who later developed psychosis,” said Guillermo Cecchi, a biometaphorical-computing researcher for IBM Research, told The Atlantic.
“It was not the average. What this means is that over 45 minutes of interviewing, these young people had at least one occasion of a jarring disruption in meaning from one sentence to the next. As an interviewer, if my mind wandered briefly, I might miss it. But a computer would pick it up.”
Using an algorithm to pick out disruptions in what would otherwise be normal speech, the researchers measured sentence coherence as well as the length of sentences and how many clauses they contained.
“When people speak, they can speak in short, simple sentences. Or they can speak in longer, more complex sentences, that have clauses added that further elaborate and describe the main idea,” Cecchi continued. “The measures of complexity and coherence are separate and are not correlated with one another. However, simple syntax and semantic incoherence do tend to aggregate together in schizophrenia.”
So what do these findings mean?
“Better characterizing a behavioral component of schizophrenia may lead to a clearer understanding of the alterations to neural circuitry underlying the development of these symptoms,” said Gillinder Bedi, an assistant professor at Columbia University’s psychology department.
“If speech analyses could identify those people most likely to develop schizophrenia, this could allow for more targeted preventive treatment before the onset of psychosis, potentially delaying onset or reducing the severity of the symptoms which do develop.”
—–
Image credit: Thinkstock
Comments