This article is more than 5 years old. Information may no longer be current.

Psychosis onset may be detectable by automated speech analysis

Automated speech analysis may be able to identify individuals who will progress to psychosis, according to study findings in npj Schizophrenia.

“The capacity of psychiatry to diagnose and treat serious mental illness has been hampered by the absence of objective clinical tests of the type routinely used in other fields of medicine. Although recent years have seen substantial advances in understanding of the neurobiology of mental illness, these developments have yet to yield markers that reliably differentiate psychiatric health from illness at the level of the individual patient,” Gillinder Bedi, DPsych, of Columbia University, and colleagues wrote.

Researchers used automated analysis to evaluate interview transcripts to identify semantic and syntactic features that predicted later psychosis onset among 34 youths at clinical high-risk for psychosis. Study participants, aged 14 to 27 years, were assessed quarterly for up to 2.5 years. Overall, five individuals transitioned to psychosis.

“Speech features were fed into a convex hull classification algorithm with leave-one-subject-out cross-validation to assess their predictive value for psychosis outcome. The canonical correlation between the speech features and prodromal symptom ratings was computed,” the researchers wrote.

Speech features that predicted later psychosis onset included Latent Semantic Analysis measure of semantic coherence and two syntactic markers of speech complexity: maximum phrase length and use of determiners (eg, which). These features predicted later psychosis development with 100% accuracy, according to researchers.

Speech features were significantly associated with prodromal symptoms.

“Using automated approaches, we were able to extract indices of speech-semantic coherence and syntax and use these to accurately predict the subsequent development of psychosis in high-risk youths. Prognostic prediction using this approach outperformed prediction on the basis of standard psychiatric ratings. Computerized analysis of complex human behaviors such as speech may present an opportunity to move psychiatry beyond reliance on self-report and clinical observation toward more objective measures of health and illness in the individual patient,” the researchers concluded. – by Amanda Oldt

Disclosure: The researchers report no relevant financial disclosures.