Speech and Language Markers as Longitudinal Predictors of Youth Mental Health: A Systematic Review.

INTRODUCTION

Severe mental disorders in young people (< 25 years) are often preceded by subtle changes in communication and thinking, detectable in speech. Speech and language markers are promising for early detection; however, no systematic review has evaluated their prospective utility in predicting mental disorders in youth. We comprehensively reviewed longitudinal studies assessing speech/language markers as predictors of major mental disorder onset or symptom progression in youth.

METHODS

We searched for longitudinal studies using recorded speech samples from youth or family members to predict diagnostic changes or symptom severity in major depressive disorder (MDD), psychosis, ADHD, substance use disorder, bipolar disorder, OCD and eating disorders. Risk of bias was assessed using the Newcastle-Ottawa Scale. Our protocol was pre-registered (CRD42024579798).

RESULTS

Of 2260 articles, 11 studies met inclusion criteria, covering MDD (n = 3), psychosis (n = 5) and ADHD (n = 3). No eligible studies were found for OCD, substance use, bipolar or eating disorders. Both manual and computational speech analyses were used, with speech samples from parents and youth. Predictive speech/language markers included parental expressed emotion (MDD, ADHD), formal thought disorder (psychosis) and acoustic/linguistic features (psychosis, ADHD). Study quality was moderate to good (mean score: 5.45/8).

CONCLUSIONS

Externally validated longitudinal studies on the predictive value of speech/language markers of youth-onset mental disorders are scarce, restricted to a few target disorders and do not allow for variations due to the developmental stage of the samples. Nonetheless, existing studies highlight the potential of applying Natural Language Processing methods to speech samples from both youth and parents for early identification.