Using Machine Learning Analyses of Speech to Classify Levels of Expressed Emotion in Parents of Youth with Mood Disorders

Abstract Expressed emotion (EE), a measure of attitudes among caregivers towards a patient with a psychiatric disorder, is a robust predictor of relapse across mood and psychotic disorders. Because the measurement of EE is time-intensive and costly, its use in clinical settings has been limited. In an effort to automate EE classification, we evaluated whether machine learning (ML) applied to lexical features of speech samples can accurately categorize parents as high or low in EE or in its subtypes (criticism, overinvolvement, and warmth). The sample was 123 parents of youth who had active mood symptoms and a family history of bipolar disorder. Using ML algorithms, we achieved 75.2-81.8% accuracy (sensitivities of ∼0.7 and specificities of ∼0.8) in classifying parents as high or low in EE and EE subtypes. Further, machine-derived EE classifications’ relationships with mood symptoms, parental distress, and family conflict paralleled observer-rated EE classifications’ relationships with the same variables. Of note, criticism related to greater manic severity, parental distress, and family conflict. Study findings indicate that EE classification can be automated through lexical analysis and suggest potential for facilitating larger-scale applications in clinical settings. The results also provide initial indications of the digital phenotypes that underlie EE and its subtypes.