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 and 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. Additionally, machine-derived EE classifications and observer-rated EE classifications had simiar relationships with youth mood symptoms, parental distress, and family conflict. 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.

The implementation of evidence-based psychotherapies often requires significant commitments of time and expense from mental health providers. Psychotherapy protocols with rapid and efficient training and supervision requirements may have higher levels of uptake in publicly funded clinics. Family-focused therapy (FFT) is a 4-month, 12-session treatment for bipolar and psychosis patients consisting of psychoeducation, communication training, and problem-solving skills training. In a pilot randomized trial, we compared two methods of training community clinicians in FFT: (a) high intensity (n = 24), consisting of a 6-hour in-person didactic workshop followed by telephone supervision for every session with training cases; or (b) low-intensity training (n = 23), consisting of a 4-hour online workshop covering the same material as the in-person workshop followed by telephone supervision after every third session with training cases. Of 47 clinician participants, 18 (11 randomly assigned to high intensity, 7 to low) enrolled 34 patients with mood or psychotic disorders (mean age 16.5 ± 2.0 years; 44.1% female) in an FFT implementation phase. Expert supervisors rated clinicians' fidelity to the FFT manual based on taped family sessions. We detected no differences in fidelity scores between clinicians in the two training conditions, nor did patients treated by clinicians in high- versus low-intensity training differ in end-of-treatment depression or mania symptoms. Levels of parent/offspring conflict improved in both conditions. Although based on a pilot study, the results suggest that low-intensity training of community clinicians in FFT is feasible and can result in rapid achievement of fidelity benchmarks without apparent loss of treatment efficacy.

Background

We examined whether digital phenotyping of spontaneous speech, such as the use of specific word categories during speech samples, was associated with depressive symptoms in youth who were at familial and clinical risk for mood disorders.

Methods

Participants (ages 13-19) had active mood symptoms, mood instability, and at least one parent with bipolar or major depressive disorder. During a randomized trial of family-focused therapy, participants were instructed to make weekly calls to a central voice server and leave speech samples in response to automated prompts. We coded youths' speech samples with the Linguistic Inquiry and Word Count system and used machine learning to identify the combination of speech features that were most closely associated with the course of depressive symptoms over 18 weeks.

Results

A total of 253 speech samples were collected from 44 adolescents (mean age = 15.8 years; SD = 1.6) over 18 weeks. Speech containing affective processes, social processes, drives toward risk or reward, nonfluencies, and time orientation words were correlated with depressive symptoms at concurrent time periods (ps < 0.01). Machine learning analyses revealed that affective processes, nonfluencies, drives and risk words combined to most strongly predict changes in depressive symptoms over 18 weeks of treatment.

Limitations

Study results were limited by the small sample and the exclusion of paralinguistic or contextual variables in analyzing speech samples.

Conclusions

In youth at high risk for mood disorders, knowledge of speech patterns may inform prognoses during outpatient psychosocial treatment.

Objectives

Family-focused therapy (FFT) is associated with reduced rates of mood episodes among youth at high risk for bipolar disorder (BD). In a randomized trial of FFT compared to a psychoeducation-only treatment (enhanced care, EC), we sought to determine if changes in psychosocial functioning mediate mood improvements among high-risk youth.

Method

119 youths with active mood symptoms and a family history of BD were randomized to either 4 months of FFT or EC. Participants were rated on mood symptom severity and provided self-ratings of psychosocial functioning across domains of family, social-emotional, and school functioning. Repeated measures mixed modeling and bootstrapped mediational analyses evaluated the effects of treatment conditions and psychosocial functioning on mood improvements immediately posttreatment and over 2 years of follow-up.

Results

Youths in FFT reported greater improvements in family functioning over 24 months compared to those in EC, F(5, 76.8) = 3.1, p < .05. Improvements in family functioning partially mediated participants' improvements in depressive symptoms, B = -0.22, p < .01; 95% CI [-0.55, -0.02]. The effects of FFT versus EC on family functioning were stronger among youth with comorbid anxiety and externalizing disorders than among youth without these comorbid disorders.

Conclusions

The findings suggest a temporal link between changes in youths' perceptions of family functioning and improvements in depressive symptoms among high-risk youth in FFT. Family conflict and cohesion are important treatment targets for youth who present with early signs of BD. Future studies should examine whether changes in observational measures of family interaction precede improvements in mood among high-risk youth. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

Aim

Integrating psychosocial interventions with mobile apps may increase treatment engagement among adolescents. We examined the user experience, uptake, and clinical effects of a mobile-enhanced family-focused therapy (FFT) among adolescents at risk for mood disorders.

Method

We created a mobile app containing 12 lesson plans corresponding to content of weekly FFT sessions, with modules concerning mood management, family communication and problem-solving. We pilot tested the app in an open trial of FFT (12 sessions in 18 weeks) for adolescents who had active depressive or hypomanic symptoms, a parent with mood disorder, and at least one parent who expressed high levels of criticism. Teens and parents made daily and weekly ratings of youths' moods, amount of parent/offspring criticism, and practice of FFT psychoeducational, communication or problem-solving skills. Independent evaluators interviewed adolescents at baseline and every 9 weeks over 27 weeks to measure symptom trajectories.

Results

Participants were adolescents (n=22; mean age 15.4 ± 1.8 years; 45.5% female) and their 34 parents. Completion of requested app assessment and skill practices averaged 46%-65% among adolescents and parents over 18 weeks of treatment. Adolescents showed significant improvement in clinician-rated depression scores over 27 weeks (Cohen's d=1.58, 95% CI, 0.83 to 2.32) and reported reductions in the amount of perceived criticism expressed by parents.

Limitations

The uncontrolled design limits inferences about whether the mobile app augmented the effects of FFT on moods or family relationships.

Conclusions

Mobile applications may enhance users' responses to family therapy and provide clinicians with information regarding clinical status. Clinicaltrials.gov NCT03913013.