Can Speech Analysis Aid in the Prediction and Diagnosis of Metal Health Disorders?

What’s New in Psychology?

Can Speech Analysis Aid in the Prediction and Diagnosis of Metal Health Disorders?  

Jim Windell


           Mental health disorders in the U.S. affect 25% of adults, 18% of adolescents and 13% of children. Current approaches to the assessment and monitoring of psychiatric conditions rely primarily on intermittent reports from affected individuals or their caregivers. These reports are often subjective and include patients' retrospective recall biases, cognitive limitations, and social stigma. However, there is an urgency to objectively diagnose, monitor over time, and provide evidence‐based interventions for individuals with mental illnesses, particularly those who are unable to access traditional psychological or psychiatric services due to geographical, financial, or practical barriers. A systematic and objective assessment would facilitate remote assessments and better personalization of care and thereby improve clinical services across the medical practice.

           In recent years, a number of technologies have been explored to try to provide opportunities for better assessment of mental health, but objective measurement of psychiatric disorder has long proved challenging. Yet, there is ample evidence that analysis of speech patterns can accurately diagnose depression and psychosis, measure their severity, and predict their onset. This was shown recently in a literature review published in the Harvard Review of Psychiatry

            The review examined current published literature related to the use of speech pattern analysis to manage psychiatric disorders and identified four key areas of application: diagnostic classification, severity assessment, onset prediction, as well as prognosis and treatment outcomes. These models that bring together multiple speech features can distinguish speakers with psychiatric disorders from healthy controls with high accuracy, write Rudolf Uher, Ph.D., M.D., at Dalhousie University Department of Psychiatry and Nova Scotia Health, and his colleagues.

            Noting that automated analysis is more promising than subjective measures like interviews or questionnaires, the authors pointed out that features of mental illness are often presented through speech and language, and psychiatric clinical assessment often considers patterns in a patient’s speech. Such patterns include speed, coherence and content of speech. It was found though that advances in natural language processing, speech recognition and computer science have underscored the fact that using speech analysis as an objective, clinical measurement of mental illness is possible.  

           Uher and his team reviewed hundreds of articles, papers and reports of individuals with a mental disorder that discussed aspects of their speech. Case studies and studies of patients with neurological disorders were excluded from the review. Many of the included articles analyzed transcriptions of participants’ speech.

           Most studies included in the review discussing the use of speech analysis in diagnosis concerned patients with major depression, whose speech is often slow, full of pauses, negative in content, and lacking energy. Diagnostic accuracy in such studies was high – over 80% in one study.

           It was also found that automated analysis is also effective in predicting the onset of mental illness, particularly in high-risk populations. Multiple studies that looked at speech semantics, including coherence and complexity, predicted the onset of psychosis in two to two and a half years with as much as 100% accuracy. However, literature on the impact of speech analysis on prognosis and treatment outcomes is limited and more research is needed. Also of significance, it has been found that using speech-pattern analysis in assessing suicide risk appears to have great potential. One recent study showed that measuring variables such as erratic frequency, hesitations, and jitters identified patients with suicide ideation against healthy patients 73% of the time.

          Among the drawbacks noted by the authors in using speech pattern analysis for prediction and diagnosis are medication effects and demographic and cultural attributes –such as language, gender, and sex, among others – that can cause variance in speaking patterns and make an objective assessment.

          To read the original article, find it with this reference:

Dikaios, K., Rempel, S., Dumpala, S., Oore, S., Kiefte, M. & Uher, R. (2023). Applications of Speech Analysis in Psychiatry. Harvard Review of Psychiatry 31(1), 1-13. DOI: 10.1097/HRP.0000000000000356

Share this post:

Comments on "Can Speech Analysis Aid in the Prediction and Diagnosis of Metal Health Disorders?"

Comments 0-5 of 0

Please login to comment