A software analysed transcript of interviews with young patients at-risk and predicted that those would have developed forms of psychosis within two years. The results were confirmed up to 83%.

In two independent groups of young participants at risk for psychosis, the same computer software was capable of identifying a disruption in the flow of speech were the patients went ‘off track’ during their speaking, being able to forecast those who were most likely to develop psychosis in the future with 79% accuracy.

In this second study, the computer was able to predict future psychosis while also discriminating speech from individuals with psychosis from healthy individuals with an accuracy of 72 percent.

The two applications of the study, suggest that the new technology could drastically contribute to efficient forecasting of psychosis rising and other kinds of disorders.

The study outlining the process and its results were published online in World Psychiatry on the 22nd of January 2018.

Disorganised thinking, which represents a symptom pointing towards psychosis, is usually assessed by interviewing patients and analysing the transcripts through clinical ratings of speech. Typical symptoms are simpleness of speech, weakness in associations and tangential language. Whilst capable of having a huge impact on the communication, creating strong issues to the patient, language disruption is most likely to represent a cunning and persistent indicator of psychosis development in youths at risk.

The research examined interview transcripts from at-risk youths in two different cohorts - a New York-based one with 34 participants and a Los Angeles-based one with 59 participants - the members of which shown psychosis onset within the next following two years. The transcripts were analyzed by a computer software which exploited automated natural language processing methods to identify differences in speech between those who developed psychosis and those who did not.

“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 disturbance,” explained the study’s first author, Cheryl Corcoran, MD, Associate Professor of Psychiatry, Program Leader in Psychosis Risk, Icahn School of Medicine at Mount Sinai.

“More broadly, language and behavior are the primary sources of data for psychiatrists to diagnose and treat mental disorders,” said Dr. Corcoran. “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.”

Other institutions who took part in the study include the IBM T.J. Watson Research Center; the University of Buenos Aires, Argentina; the University of California, Los Angeles; and the New York State Psychiatric Institute at Columbia University Medical Center.

This research was funded and supported by grants from the U.S. National Institute of Mental Health (R01 MH 107558; R03 MH 108933) the New York State Office of Mental Health, and a NAR-SAD/BBRF Young Investigator Award and Miller Family Term Chair to C.E. Bearden.

Written by: Pietro Paolo Frigenti

Journal Reference: Corcoran, C. M., Carrillo, F., Fernández‐Slezak, D., Bedi, G., Klim, C., Javitt, D. C., Bearden, C. E. , Cecchi, G. A. (2018). Prediction of psychosis across protocols and risk cohorts using automated language analysis. World Psychiatry, 17(1), 67-75.