A prognostic index to predict symptom and functional outcomes of a coached, web-based intervention for trauma-exposed veterans.

Researchers at the Department of Veterans Affairs (VA) have studied interventions for posttraumatic stress disorder and co-occurring conditions in both traditional and digital formats. One such empirically supported intervention is web skills training in affective and interpersonal regulation (webSTAIR), a coached, 10-module web program based on STAIR. To understand which patient characteristics were predictive of webSTAIR outcomes in a sample of trauma-exposed veterans (N = 189), we used machine learning (ML) to develop a prognostic index from among 18 baseline characteristics (i.e., demographic, military, trauma history, and clinical) to predict posttreatment posttraumatic stress disorder severity, depression severity, and psychosocial functioning impairment. We compared the ML models to a benchmark of linear regression models in which the only predictor was the baseline severity score of the outcome measure. The ML and "severity-only" models performed similarly, explaining 39%-45% of the variance in outcomes. This suggests that baseline symptom severity and functioning are strong indicators for webSTAIR outcomes in veterans, with higher severity indicating worse prognosis, and that the other variables examined did not contribute significant added predictive signal. Findings also highlight the importance of comparing ML models to an appropriate benchmark. Future research with larger samples could potentially detect smaller patient-level effects as well as effects driven by other types of variables (e.g., therapeutic process variables). As a transdiagnostic, digital intervention, webSTAIR can potentially serve a diverse veteran population with varying trauma histories and may be best conceptualized as a beneficial first step of a stepped care model for those with heightened symptoms or impairment. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Measuring the active elements of cognitive-behavioral therapies.

Understanding how and for whom cognitive-behavioral therapies work is central to the development and improvement of mental health interventions. Suboptimal quantification of the active elements of cognitive-behavioral therapies has hampered progress in elucidating mechanisms of change. To advance process research on cognitive-behavioral therapies, we describe a theoretical measurement framework that focuses on the delivery, receipt, and application of the active elements of these interventions. We then provide recommendations for measuring the active elements of cognitive-behavioral therapies aligned with this framework. Finally, to support measurement harmonization and improve study comparability, we propose the development of a publicly available repository of assessment tools: the Active Elements of Cognitive-Behavioral Therapies Measurement Kit.

The development and internal evaluation of a predictive model to identify for whom Mindfulness-Based Cognitive Therapy (MBCT) offers superior relapse prevention for recurrent depression versus maintenance antidepressant medication.

Depression is highly recurrent, even following successful pharmacological and/or psychological intervention. We aimed to develop clinical prediction models to inform adults with recurrent depression choosing between antidepressant medication (ADM) maintenance or switching to Mindfulness-Based Cognitive Therapy (MBCT). Using data from the PREVENT trial (N=424), we constructed prognostic models using elastic net regression that combined demographic, clinical and psychological factors to predict relapse at 24 months under ADM or MBCT. Only the ADM model (discrimination performance: AUC=.68) predicted relapse better than baseline depression severity (AUC=.54; one-tailed DeLong's test: z=2.8, p=.003). Individuals with the poorest ADM prognoses who switched to MBCT had better outcomes compared to those who maintained ADM (48% vs. 70% relapse, respectively; superior survival times [z=-2.7, p=.008]). For individuals with moderate-to-good ADM prognosis, both treatments resulted in similar likelihood of relapse. If replicated, the results suggest that predictive modeling can inform clinical decision-making around relapse prevention in recurrent depression.

Efficacy and moderators of cognitive therapy versus behavioural activation for adults with depression: study protocol of a systematic review and meta-analysis of individual participant data.

BACKGROUND: Cognitive therapy and behavioural activation are both widely applied and effective psychotherapies for depression, but it is unclear which works best for whom. Individual participant data (IPD) meta-analysis allows for examining moderators at the participant level and can provide more precise effect estimates than conventional meta-analysis, which is based on study-level data. AIMS: This article describes the protocol for a systematic review and IPD meta-analysis that aims to compare the efficacy of cognitive therapy and behavioural activation for adults with depression, and to explore moderators of treatment effect. (PROSPERO: CRD42022341602). METHOD: Systematic literature searches will be conducted in PubMed, PsycINFO, EMBASE and the Cochrane Library, to identify randomised clinical trials comparing cognitive therapy and behavioural activation for adult acute-phase depression. Investigators of these trials will be invited to share their participant-level data. One-stage IPD meta-analyses will be conducted with mixed-effects models to assess treatment effects and to examine various available demographic, clinical and psychological participant characteristics as potential moderators. The primary outcome measure will be depressive symptom level at treatment completion. Secondary outcomes will include post-treatment anxiety, interpersonal functioning and quality of life, as well as follow-up outcomes. CONCLUSIONS: To the best of our knowledge, this will be the first IPD meta-analysis concerning cognitive therapy versus behavioural activation for adult depression. This study has the potential to enhance our knowledge of depression treatment by using state-of-the-art statistical techniques to compare the efficacy of two widely used psychotherapies, and by shedding more light on which of these treatments might work best for whom.

Socioeconomic Indicators of Treatment Prognosis for Adults With Depression: A Systematic Review and Individual Patient Data Meta-analysis.

Importance: Socioeconomic factors are associated with the prevalence of depression, but their associations with prognosis are unknown. Understanding this association would aid in the clinical management of depression. Objective: To determine whether employment status, financial strain, housing status, and educational attainment inform prognosis for adults treated for depression in primary care, independent of treatment and after accounting for clinical prognostic factors. Data Sources: The Embase, International Pharmaceutical Abstracts, MEDLINE, PsycINFO, and Cochrane (CENTRAL) databases were searched from database inception to October 8, 2021. Study Selection: Inclusion criteria were as follows: randomized clinical trials that used the Revised Clinical Interview Schedule (CIS-R; the most common comprehensive screening and diagnostic measure of depressive and anxiety symptoms in primary care randomized clinical trials), measured socioeconomic factors at baseline, and sampled patients with unipolar depression who sought treatment for depression from general physicians/practitioners or who scored 12 or more points on the CIS-R. Exclusion criteria included patients with depression secondary to a personality or psychotic disorder or neurologic condition, studies of bipolar or psychotic depression, studies that included children or adolescents, and feasibility studies. Studies were independently assessed against inclusion and exclusion criteria by 2 reviewers. Data Extraction and Synthesis: Data were extracted and cleaned by data managers for each included study, further cleaned by multiple reviewers, and cross-checked by study chief investigators. Risk of bias and quality were assessed using the Quality in Prognosis Studies (QUIPS) and Grading of Recommendations, Assessment, Development and Evaluation (GRADE) tools, respectively. This study followed the Preferred Reporting Items for Systematic Reviews and Meta-analyses-Individual Participant Data (PRISMA-IPD) reporting guidelines. Main Outcomes and Measures: Depressive symptoms at 3 to 4 months after baseline. Results: This systematic review and individual patient data meta-analysis identified 9 eligible studies that provided individual patient data for 4864 patients (mean [SD] age, 42.5 (14.0) years; 3279 women [67.4%]). The 2-stage random-effects meta-analysis end point depressive symptom scale scores were 28% (95% CI, 20%-36%) higher for unemployed patients than for employed patients and 18% (95% CI, 6%-30%) lower for patients who were homeowners than for patients living with family or friends, in hostels, or homeless, which were equivalent to 4.2 points (95% CI, 3.6-6.2 points) and 2.9 points (95% CI, 1.1-4.9 points) on the Beck Depression Inventory II, respectively. Financial strain and educational attainment were associated with prognosis independent of treatment, but unlike employment and housing status, there was little evidence of associations after adjusting for clinical prognostic factors. Conclusions and Relevance: Results of this systematic review and meta-analysis revealed that unemployment was associated with a poor prognosis whereas home ownership was associated with improved prognosis. These differences were clinically important and independent of the type of treatment received. Interventions that address employment or housing difficulties could improve outcomes for patients with depression.

A Novel Peer-to-Peer Coaching Program to Support Digital Mental Health: Design and Implementation.

Many individuals in need of mental health services do not currently receive care. Scalable programs are needed to reduce the burden of mental illness among those without access to existing providers. Digital interventions present an avenue for increasing the reach of mental health services. These interventions often rely on paraprofessionals, or coaches, to support the treatment. Although existing programs hold immense promise, providers must ensure that treatments are delivered with high fidelity and adherence to the treatment model. In this paper, we first highlight the tension between the scalability and fidelity of mental health services. We then describe the design and implementation of a peer-to-peer coach training program to support a digital mental health intervention for undergraduate students within a university setting. We specifically note strategies for emphasizing fidelity within our scalable framework, including principles of learning theory and competency-based supervision. Finally, we discuss future applications of this work, including the potential adaptability of our model for use within other contexts.

Stratified Care vs Stepped Care for Depression: A Cluster Randomized Clinical Trial.

Importance: Depression is a major cause of disability worldwide. Although empirically supported treatments are available, there is scarce evidence on how to effectively personalize psychological treatment selection. Objective: To compare the clinical effectiveness and cost-effectiveness of 2 treatment selection strategies: stepped care and stratified care. Design, Setting, and Participants: This multisite, cluster randomized clinical trial recruited participants from the English National Health Service from July 5, 2018, to February 1, 2019. Thirty clinicians working across 4 psychological therapy services were randomly assigned to provide stratified (n = 15) or stepped (n = 15) care. In stepped care, patients sequentially access low-intensity guided self-help followed by high-intensity psychotherapy. In stratified care, patients are matched with either low- or high-intensity treatments at initial assessment. Data were analyzed from May 18, 2020, to October 13, 2021, using intention-to-treat principles. Interventions: All clinicians used the same interview schedule to conduct initial assessments with patients seeking psychological treatment for common mental disorders, but those in the stratified care group received a personalized treatment recommendation for each patient generated by a machine learning algorithm. Eligible patients received either stratified or stepped care (ie, treatment as usual). Main Outcomes and Measures: The preregistered outcome was posttreatment reliable and clinically significant improvement (RCSI) of depression symptoms (measured using the 9-item Patient Health Questionnaire). The RCSI outcome was compared between groups using logistic regression adjusted for baseline severity. Cost-effectiveness analyses compared incremental costs and health outcomes of the 2 treatment pathways. Results: A total of 951 patients were included (618 women among 950 with data available [65.1%]; mean [SD] age, 38.27 [14.53] years). The proportion of cases of RCSI was significantly higher in the stratified care arm compared with the stepped care arm (264 of 505 [52.3%] vs 134 of 297 [45.1%]; odds ratio, 1.40 [95% CI, 1.04-1.87]; P = .03). Stratified care was associated with a higher mean additional cost per patient (£104.5 [95% CI, £67.5-£141.6] [$139.83 (95% CI, $90.32-$189.48)]; P < .001) because more patients accessed high-intensity treatments (332 of 583 [56.9%] vs 107 of 368 [29.1%]; χ2 = 70.51; P < .001), but this additional cost resulted in an approximately 7% increase in the probability of RCSI. Conclusions and Relevance: In this cluster randomized clinical trial of adults with common mental disorders, stratified care was efficacious and cost-effective for the treatment of depression symptoms compared with stepped care. Stratified care can improve depression treatment outcomes at a modest additional cost. Trial Registration: isrctn.org Identifier: ISRCTN11106183.

Life events and treatment prognosis for depression: A systematic review and individual patient data meta-analysis.

OBJECTIVE: To investigate associations between major life events and prognosis independent of treatment type: (1) after adjusting for clinical prognostic factors and socio-demographics; (2) amongst patients with depressive episodes at least six-months long; and (3) patients with a first life-time depressive episode. METHODS: Six RCTs of adults seeking treatment for depression in primary care met eligibility criteria, individual patient data (IPD) were collated from all six (n = 2858). Participants were randomized to any treatment and completed the same baseline assessment of life events, demographics and clinical prognostic factors. Two-stage random effects meta-analyses were conducted. RESULTS: Reporting any major life events was associated with poorer prognosis regardless of treatment type. Controlling for baseline clinical factors, socio-demographics and social support resulted in minimal residual evidence of associations between life events and treatment prognosis. However, removing factors that might mediate the relationships between life events and outcomes reporting: arguments/disputes, problem debt, violent crime, losing one's job, and three or more life events were associated with considerably worse prognoses (percentage difference in 3-4 months depressive symptoms compared to no reported life events =30.3%(95%CI: 18.4-43.3)). CONCLUSIONS: Assessing for clinical prognostic factors, social support, and socio-demographics is likely to be more informative for prognosis than assessing self-reported recent major life events. However, clinicians might find it useful to ask about such events, and if they are still affecting the patient, consider interventions to tackle problems related to those events (e.g. employment support, mediation, or debt advice). Further investigations of the efficacy of such interventions will be important.

A Patient Stratification Approach to Identifying the Likelihood of Continued Chronic Depression and Relapse Following Treatment for Depression.

BACKGROUND: Subgrouping methods have the potential to support treatment decision making for patients with depression. Such approaches have not been used to study the continued course of depression or likelihood of relapse following treatment. METHOD: Data from individual participants of seven randomised controlled trials were analysed. Latent profile analysis was used to identify subgroups based on baseline characteristics. Associations between profiles and odds of both continued chronic depression and relapse up to one year post-treatment were explored. Differences in outcomes were investigated within profiles for those treated with antidepressants, psychological therapy, and usual care. RESULTS: Seven profiles were identified; profiles with higher symptom severity and long durations of both anxiety and depression at baseline were at higher risk of relapse and of chronic depression. Members of profile five (likely long durations of depression and anxiety, moderately-severe symptoms, and past antidepressant use) appeared to have better outcomes with psychological therapies: antidepressants vs. psychological therapies (OR (95% CI) for relapse = 2.92 (1.24-6.87), chronic course = 2.27 (1.27-4.06)) and usual care vs. psychological therapies (relapse = 2.51 (1.16-5.40), chronic course = 1.98 (1.16-3.37)). CONCLUSIONS: Profiles at greater risk of poor outcomes could benefit from more intensive treatment and frequent monitoring. Patients in profile five may benefit more from psychological therapies than other treatments.

The Nature, Timing, and Symptom Trajectories of Dropout From Transdiagnostic and Single-Diagnosis Cognitive-Behavioral Therapy for Anxiety Disorders.

Dropout from psychotherapy is common and can have negative effects for patients, providers, and researchers. A better understanding of when and why patients stop treatment early, as well as actionable factors contributing to dropout, has the potential to prevent it. Here, we examined dropout from a large randomized controlled trial of transdiagnostic versus single-diagnosis cognitive-behavioral treatment (CBT) for patients with anxiety disorders (n = 179; Barlow et al., 2017). We aimed to characterize the timing of and reasons for dropout and test whether participants who dropped out had different symptom trajectories than those who completed treatment. Results indicated that overall, the greatest risk of dropout was prior to the first treatment session. In single-diagnosis CBT, dropout risk was particularly elevated before the first session and after other early sessions, whereas in transdiagnostic CBT, dropout risk was low and stable before and during treatment. Participants most often dropped out due to failure to comply with study procedures or dissatisfaction with or desiring alternative treatment. Results from multilevel models showed that trajectories of anxiety symptoms did not significantly differ between dropouts and completers. These findings suggest that there may be specific time windows for targeted and timely interventions to prevent dropout from CBT.

Evaluating the Effectiveness of Personalized Medicine With Software.

We present methodological advances in understanding the effectiveness of personalized medicine models and supply easy-to-use open-source software. Personalized medicine involves the systematic use of individual patient characteristics to determine which treatment option is most likely to result in a better average outcome for the patient. Why is personalized medicine not done more in practice? One of many reasons is because practitioners do not have any easy way to holistically evaluate whether their personalization procedure does better than the standard of care, termed improvement. Our software, "Personalized Treatment Evaluator" (the R package PTE), provides inference for improvement out-of-sample in many clinical scenarios. We also extend current methodology by allowing evaluation of improvement in the case where the endpoint is binary or survival. In the software, the practitioner inputs 1) data from a single-stage randomized trial with one continuous, incidence or survival endpoint and 2) an educated guess of a functional form of a model for the endpoint constructed from domain knowledge. The bootstrap is then employed on data unseen during model fitting to provide confidence intervals for the improvement for the average future patient (assuming future patients are similar to the patients in the trial). One may also test against a null scenario where the hypothesized personalization are not more useful than a standard of care. We demonstrate our method's promise on simulated data as well as on data from a randomized comparative trial investigating two treatments for depression.

A personalized index to inform selection of a trauma-focused or non-trauma-focused treatment for PTSD.

PTSD treatment guidelines recommend several treatments with extensive empirical support, including Prolonged Exposure (PE), a trauma-focused treatment and Present-Centered Therapy (PCT), a non-trauma-focused therapy. Research to inform treatment selection has yielded inconsistent findings with single prognostic variables that are difficult to integrate into clinical decision-making. We examined whether a combination of prognostic factors can predict different benefits in a trauma-focused vs. a non-trauma-focused psychotherapy. We applied a multi-method variable selection procedure and developed a prognostic index (PI) with a sample of 267 female veterans and active-duty service members (mean age 45; SD = 9.37; 53% White) with current PTSD who began treatment in a randomized clinical trial comparing PE and PCT. We conducted linear regressions predicting outcomes (Clinician-Administered PTSD Scale score) with treatment condition, the PI, and the interaction between the PI and treatment condition. The interaction between treatment type and PI moderated treatment response, moderated post-treatment symptom severity, b = 0.30, SEb = 0.15 [95% CI: 0.01, 0.60], p = .049. For the 64% of participants with the best prognoses, PE resulted in better post-treatment outcomes; for the remainder, there was no difference. Use of a PI may lead to optimized patient outcomes and greater confidence when selecting trauma-focused treatments.

The Effect of PTSD Symptom Change on Suicidal Ideation in a Combined Military and Civilian Sample Engaged in Cognitive Processing Therapy.

In light of the well-established relationship between posttraumatic stress disorder (PTSD) and suicidal ideation (SI), there has been a push for treatments that simultaneously improve symptoms of PTSD and decrease SI. Using data from a randomized controlled hybrid implementation-effectiveness trial, the current study investigated the effectiveness of Cognitive Processing Therapy (CPT; Resick, Monson, & Chard, 2016) on PTSD and SI. The patient sample (N = 188) was diverse in military and veteran status, gender, and comorbidity, and 73% of the sample endorsed SI at one or more points during CPT. Participants demonstrated significant improvement in SI over the course of CPT. Multilevel growth curve modeling revealed a significant association between PTSD symptom change and change in SI. Results from cross-lagged multilevel regressions indicated that PTSD symptoms predicted SI in the next session, yet SI in a given session did not predict PTSD symptoms in the next session. Potentially relevant clinical factors (i.e., military status, gender, depression diagnosis, baseline SI, study consultation condition) were not associated with the relationship between PTSD symptoms and SI. These results add to the burgeoning literature suggesting that evidence-based treatments for PTSD, like CPT, reduce suicidality in a range of individuals with PTSD, and that this reduction is predicted by improvements in PTSD symptoms.

The contribution of depressive 'disorder characteristics' to determinations of prognosis for adults with depression: an individual patient data meta-analysis.

BACKGROUND: This study aimed to investigate general factors associated with prognosis regardless of the type of treatment received, for adults with depression in primary care. METHODS: We searched Medline, Embase, PsycINFO and Cochrane Central (inception to 12/01/2020) for RCTs that included the most commonly used comprehensive measure of depressive and anxiety disorder symptoms and diagnoses, in primary care depression RCTs (the Revised Clinical Interview Schedule: CIS-R). Two-stage random-effects meta-analyses were conducted. RESULTS: Twelve (n = 6024) of thirteen eligible studies (n = 6175) provided individual patient data. There was a 31% (95%CI: 25 to 37) difference in depressive symptoms at 3-4 months per standard deviation increase in baseline depressive symptoms. Four additional factors: the duration of anxiety; duration of depression; comorbid panic disorder; and a history of antidepressant treatment were also independently associated with poorer prognosis. There was evidence that the difference in prognosis when these factors were combined could be of clinical importance. Adding these variables improved the amount of variance explained in 3-4 month depressive symptoms from 16% using depressive symptom severity alone to 27%. Risk of bias (assessed with QUIPS) was low in all studies and quality (assessed with GRADE) was high. Sensitivity analyses did not alter our conclusions. CONCLUSIONS: When adults seek treatment for depression clinicians should routinely assess for the duration of anxiety, duration of depression, comorbid panic disorder, and a history of antidepressant treatment alongside depressive symptom severity. This could provide clinicians and patients with useful and desired information to elucidate prognosis and aid the clinical management of depression.

The efficacy of antidepressant medication and interpersonal psychotherapy for adult acute-phase depression: study protocol of a systematic review and meta-analysis of individual participant data.

BACKGROUND: Antidepressant medication and interpersonal psychotherapy (IPT) are both recommended interventions in depression treatment guidelines based on literature reviews and meta-analyses. However, 'conventional' meta-analyses comparing their efficacy are limited by their reliance on reported study-level information and a narrow focus on depression outcome measures assessed at treatment completion. Individual participant data (IPD) meta-analysis, considered the gold standard in evidence synthesis, can improve the quality of the analyses when compared with conventional meta-analysis. AIMS: We describe the protocol for a systematic review and IPD meta-analysis comparing the efficacy of antidepressants and IPT for adult acute-phase depression across a range of outcome measures, including depressive symptom severity as well as functioning and well-being, at both post-treatment and follow-up (PROSPERO: CRD42020219891). METHOD: We will conduct a systematic literature search in PubMed, PsycINFO, Embase and the Cochrane Library to identify randomised clinical trials comparing antidepressants and IPT in the acute-phase treatment of adults with depression. We will invite the authors of these studies to share the participant-level data of their trials. One-stage IPD meta-analyses will be conducted using mixed-effects models to assess treatment effects at post-treatment and follow-up for all outcome measures that are assessed in at least two studies. CONCLUSIONS: This will be the first IPD meta-analysis examining antidepressants versus IPT efficacy. This study has the potential to enhance our knowledge of depression treatment by comparing the short- and long-term effects of two widely used interventions across a range of outcome measures using state-of-the-art statistical techniques.

Is social support pre-treatment associated with prognosis for adults with depression in primary care?

OBJECTIVE: Depressed patients rate social support as important for prognosis, but evidence for a prognostic effect is lacking. We aimed to test the association between social support and prognosis independent of treatment type, and the severity of depression, and other clinical features indicating a more severe illness. METHODS: Individual patient data were collated from all six eligible RCTs (n = 2858) of adults seeking treatment for depression in primary care. Participants were randomized to any treatment and completed the same baseline assessment of social support and clinical severity factors. Two-stage random effects meta-analyses were conducted. RESULTS: Social support was associated with prognosis independent of randomized treatment but effects were smaller when adjusting for depressive symptoms and durations of depression and anxiety, history of antidepressant treatment, and comorbid panic disorder: percentage decrease in depressive symptoms at 3-4 months per z-score increase in social support = -4.14(95%CI: -6.91 to -1.29). Those with a severe lack of social support had considerably worse prognoses than those with no lack of social support: increase in depressive symptoms at 3-4 months = 14.64%(4.25% to 26.06%). CONCLUSIONS: Overall, large differences in social support pre-treatment were associated with differences in prognostic outcomes. Adding the Social Support scale to clinical assessments may be informative, but after adjusting for routinely assessed clinical prognostic factors the differences in prognosis are unlikely to be of a clinically important magnitude. Future studies might investigate more intensive treatments and more regular clinical reviews to mitigate risks of poor prognosis for those reporting a severe lack of social support.

Personalized treatment selection in routine care: Integrating machine learning and statistical algorithms to recommend cognitive behavioral or psychodynamic therapy.

Objective: This study aims at developing a treatment selection algorithm using a combination of machine learning and statistical inference to recommend patients' optimal treatment based on their pre-treatment characteristics. Methods: A disorder-heterogeneous, naturalistic sample of N = 1,379 outpatients treated with either cognitive behavioral therapy or psychodynamic therapy was analyzed. Based on a combination of random forest and linear regression, differential treatment response was modeled in the training data (n = 966) to indicate each individual's optimal treatment. A separate holdout dataset (n = 413) was used to evaluate personalized recommendations. Results: The difference in outcomes between patients treated with their optimal vs. non-optimal treatment was significant in the training data, but non-significant in the holdout data (b = -0.043, p = .280). However, for the 50% of patients with the largest predicted benefit of receiving their optimal treatment, the average percentage of change on the BSI in the holdout data was 52.6% for their optimal and 38.4% for their non-optimal treatment (p = .017; d = 0.33 [0.06, 0.61]). Conclusion: A treatment selection algorithm based on a combination of ML and statistical inference might improve treatment outcome for some, but not all outpatients and could support therapists' clinical decision-making.

Precision medicine for long-term depression outcomes using the Personalized Advantage Index approach: cognitive therapy or interpersonal psychotherapy?

BACKGROUND: Psychotherapies for depression are equally effective on average, but individual responses vary widely. Outcomes can be improved by optimizing treatment selection using multivariate prediction models. A promising approach is the Personalized Advantage Index (PAI) that predicts the optimal treatment for a given individual and the magnitude of the advantage. The current study aimed to extend the PAI to long-term depression outcomes after acute-phase psychotherapy. METHODS: Data come from a randomized trial comparing cognitive therapy (CT, n = 76) and interpersonal psychotherapy (IPT, n = 75) for major depressive disorder (MDD). Primary outcome was depression severity, as assessed by the BDI-II, during 17-month follow-up. First, predictors and moderators were selected from 38 pre-treatment variables using a two-step machine learning approach. Second, predictors and moderators were combined into a final model, from which PAI predictions were computed with cross-validation. Long-term PAI predictions were then compared to actual follow-up outcomes and post-treatment PAI predictions. RESULTS: One predictor (parental alcohol abuse) and two moderators (recent life events; childhood maltreatment) were identified. Individuals assigned to their PAI-indicated treatment had lower follow-up depression severity compared to those assigned to their PAI-non-indicated treatment. This difference was significant in two subsets of the overall sample: those whose PAI score was in the upper 60%, and those whose PAI indicated CT, irrespective of magnitude. Long-term predictions did not overlap substantially with predictions for acute benefit. CONCLUSIONS: If replicated, long-term PAI predictions could enhance precision medicine by selecting the optimal treatment for a given depressed individual over the long term.