Software That Can Predict Psychosis From Speech Patterns

 In Naturopathic News

Node Smith, ND

The Sound of Psychosis

A recent report by researchers at Mount Sinai Hospital confirms that a computer-based analysis of speech patterns of teens at risk of psychosis was able to predict which individuals would go on to develop symptoms within 2 years.1 The accuracy of the speech analysis for making these predictions was 83 percent.

Concentration on Organization of Speech

The computer analysis concentrates on the organization of speech, and speech content and complexity. Disorganized thinking is a symptom of psychosis, and is generally assessed using interview-based clinical metrics. The disorganization of psychotic speech is characterized by looseness of associations as well as tangential language and a general reduction in speech complexity. These speech patterns can actually be severe enough to limit effective communication. Commonly these disturbances in language can be seen to a more subtler degree prior to psychosis onset in at risk youth.

Who Develops and Who Does Not?

The current study looked at transcripts from 2 distinct geographical groups of at-risk youth – one in New York City, and one in Los Angeles. The cohorts contained 34 and 59 participants respectively. The onset of psychosis over following 2 years after speech transcripts was known. The transcripts were analyzed by computer using natural language processing functions to predict who would develop psychosis, and who would not.

Incidence of Psychosis Predicted with 83 percent Accuracy

The computer was 83 percent accurate in determining the likelihood of an individual developing psychosis over the following 2 years.

Study Suggests Technology Could ‘Tell us’ When Psychosis Looms

The study suggests that technology such as this could potentially improve the prediction of psychosis and indicate when pre-emptive treatment approaches may be beneficial. If re-mediation and training strategies can be employed earlier, it is possible that cognitive deficits that underlie these language disturbances could be addressed. This also makes the diagnostic future of psychosis likely less subjective.


  1. Corcoran C. Mount Sinai Hospital “Speech Analysis Software Predicts Psychosis in Those At Risk With 83% Accuracy.” NeuroscienceNews. NeuroscienceNews, 23 January 2018. <>.

Image Copyright: <a href=’’>kubko / 123RF Stock Photo</a>

Node Smith, ND, is a naturopathic physician in Portland, OR and associate editor for NDNR. He has been instrumental in maintaining a firm connection to the philosophy and heritage of naturopathic medicine among the next generation of docs. He helped found the first multi-generational experiential retreat, which brings elders, alumni, and students together for a weekend camp-out where naturopathic medicine and medical philosophy are experienced in nature. Four years ago he helped found the non-profit, Association for Naturopathic ReVitalization (ANR), for which he serves as the board chairman. ANR has a mission to inspire health practitioners to embody the naturopathic principles through experiential education. Node also has a firm belief that the next era of naturopathic medicine will see a resurgence of in-patient facilities which use fasting, earthing, hydrotherapy and homeopathy to bring people back from chronic diseases of modern living; he is involved in numerous conversations and projects to bring about this vision.

Recommended Posts

Start typing and press Enter to search