Interpersonal Psychotherapy Versus Cognitive Therapy for Depression: How They Work, How Long, and for Whom—Key Findings From an RCT

Cross-trial prediction of depression remission using problem-solving therapy: A machine learning approach

BACKGROUND

Psychotherapy is a standard depression treatment; however, determining a patient's prognosis with therapy relies on clinical judgment that is subject to trial-and-error and provider variability.

PURPOSE

To develop machine learning (ML) algorithms to predict depression remission for patients undergoing 6 months of problem-solving therapy (PST).

METHOD

Using data from the treatment arm of 2 randomized trials, ML models were trained and validated on ENGAGE-2 (ClinicalTrials.gov, #NCT03841682) and tested on RAINBOW (ClinicalTrials.gov, #NCT02246413) for predictions at baseline and at 2-months. Primary outcome was depression remission using the Depression Symptom Checklist (SCL-20) score < 0.5 at 6 months. Predictor variables included baseline characteristics (sociodemographic, behavioral, clinical, psychosocial) and intervention engagement through 2-months.

RESULTS

Of the 26 candidate variables, 8 for baseline and 11 for 2-months were predictive of depression remission, and used to train the models. The best-performing model predicted remission with an accuracy significantly greater than chance in internal validation using the ENGAGE-2 cohort, at baseline [72.6% (SD = 3.6%), p < 0.0001] and at 2-months [72.3% (5.1%), p < 0.0001], and in external validation with the RAINBOW cohort at baseline [58.3% (0%), p < 0.0001] and at 2-months [62.3% (0%), p < 0.0001]. Model-agnostic explanations highlighted key predictors of depression remission at the cohort and patient levels, including female sex, lower self-reported sleep disturbance, lower sleep-related impairment, and lower negative problem orientation.

CONCLUSIONS

ML models using clinical and patient-reported data can predict depression remission for patients undergoing PST, affording opportunities for prospective identification of likely responders, and for developing personalized early treatment optimization along the patient care trajectory.

Therapist Adherence to Two Treatments for Adolescent Suicide Risk: Association to Outcomes and Role of Therapeutic Alliance

In psychotherapy research, adherence refers to the extent to which therapists deliver a treatment as intended. This study examined whether therapist adherence to two different manualized treatments was associated with improved client outcomes and whether the association was moderated by therapeutic alliance. The study sample included 320 video recordings of therapy sessions from 118 cases in a randomized controlled trial (RCT) comparing attachment-based family therapy (ABFT) with family-enhanced nondirective supportive therapy (FE-NST). Recordings were selected from early, middle, and late stages of treatment. The adherence measure consisted of 24 items representing essential therapist interventions from both treatments. Trained raters coded tapes from both therapies. Adolescent self-report of alliance was measured at session 4. Adherence to ABFT was associated with a significant increase in family cohesion at mid-treatment but not at posttreatment. Adherence to FE-NST was significantly associated with an increase in suicide ideation posttreatment. Using therapeutic alliance as a moderator, adherence to ABFT was significantly associated with a reduction in suicide ideation, family conflict, and higher client satisfaction posttreatment. Alliance did not positively affect the association of FE-NST adherence to outcomes. Findings suggest that adherence to ABFT interventions may be better linked to treatment outcomes when adolescents feel a strong alliance with their therapist. Implications for future research and therapist training are explored.

Editorial: Optimizing Depression Prevention: The Way Forward?

Since the advent of cognitive-behavioral therapy (CBT) and interpersonal therapy in the 1960s and 1970s, the progress on "talking therapies" has been slow. An extensive review of prevention and treatment studies over the past 50 years has shown that, although the therapies are effective, for depression the effect size is moderate, even for treatment, and has not changed in 50 years,¹ with some indication that efficacy may have decreased.² The approaches used in treatment have also been the mainstay of depression prevention approaches,^3,4 with evidence of a small-to-moderate reduction in depressive symptoms but with no convincing evidence of reduction in the incidence of depressive disorder in meta-analyses.^3,4.

Exploring differences in quality of life in clinical populations of depressed outpatients with and without personality disorders

BACKGROUND

Although depression and personality disorders (PDs) often co-occur, less is known about the impact of PDs on health-related quality of life (HRQOL) in patients with depression. This study explores the differences in HRQOL of depressed patients with and without PD.

METHODS

Baseline data of 397 patients with depression from two randomised controlled trials were used for this analysis. HRQOL was measured with the EuroQol-5D (EQ-5D). Differences were examined between three groups: patients with 1) depression-only, 2) depression and comorbid PD and 3) PD and comorbid depression. The EQ-5D scores of the groups were compared with linear regression.

RESULTS

HRQOL scores were lower in the depression-only group than the depression + PD group, even though depression severity was higher in patients with PD. HRQOL in the PD ± depression group did not differ from the other groups. In addition, no associations were found between the type or severity of PD and HRQOL.

DISCUSSION

These findings could indicate that patients with PD are less affected by the impact of depression on HRQOL. In addition, the EQ-5D might not adequately capture the impact of PD on quality of life. Further research is needed to compare the EQ-5D with quality of life instruments that include more life domains.

LIMITATIONS

Two study samples are combined, and therefore not designed to compare the three groups directly. Generalisation of the results should be done with caution.

CONCLUSION

Depressed patients with PD report higher HRQOL than depression-only patients. Although higher HRQOL, patients with PD report more severe depressions than depressed-only patients.

On the Road to Personalized Psychotherapy: A Research Agenda Based on Cognitive Behavior Therapy for Depression

In this conceptual paper, we outline the many challenges on the road to personalized psychotherapy, using the example of cognitive behavior therapy (CBT) for depression. To optimize psychotherapy for the individual patient, we need to find out how therapy works (identification of mechanisms of change) and for whom it works (identification of moderators). To date, psychotherapy research has not resulted in compelling evidence for or against common or specific factors that have been proposed as mechanisms of change. Our central proposition is that we need to combine the "how does it work?"-question with the "for whom does it work?"-question in order to advance the field. We introduce the personalized causal pathway hypothesis that emphasizes the links and distinction between individual patient differences, therapeutic procedures and therapy processes as a paradigm to facilitate und understand the concept of personalized psychotherapy. We review the mechanism of change literature for CBT for depression to see what we have learned so far, and describe preliminary observational evidence supporting the personalized causal pathway hypothesis. We then propose a research agenda to push the ball forward: exploratory studies into the links between individual differences, therapeutic procedures, therapy processes and outcome that constitute a potential causal pathway, making use of experience sampling, network theory, observer ratings of therapy sessions, and moderated mediation analysis; testing and isolation of CBT procedures in experiments; and testing identified causal pathways of change as part of a personalized CBT package against regular CBT, in order to advance the application of personalized psychotherapy.