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

A Tutorial Introduction to Heterogeneous Treatment Effect Estimation with Meta-learners

Psychotherapy has been proven to be effective on average, though patients respond very differently to treatment. Understanding which characteristics are associated with treatment effect heterogeneity can help to customize therapy to the individual patient. In this tutorial, we describe different meta-learners, which are flexible algorithms that can be used to estimate personalized treatment effects. More specifically, meta-learners decompose treatment effect estimation into multiple prediction tasks, each of which can be solved by any machine learning model. We begin by reviewing necessary assumptions for interpreting the estimated treatment effects as causal, and then give an overview over key concepts of machine learning. Throughout the article, we use an illustrative data example to show how the different meta-learners can be implemented in R. We also point out how current popular practices in psychotherapy research fit into the meta-learning framework. Finally, we show how heterogeneous treatment effects can be analyzed, and point out some challenges in the implementation of meta-learners.

Large language models could change the future of behavioral healthcare: a proposal for responsible development and evaluation

Large language models (LLMs) such as Open AI's GPT-4 (which power ChatGPT) and Google's Gemini, built on artificial intelligence, hold immense potential to support, augment, or even eventually automate psychotherapy. Enthusiasm about such applications is mounting in the field as well as industry. These developments promise to address insufficient mental healthcare system capacity and scale individual access to personalized treatments. However, clinical psychology is an uncommonly high stakes application domain for AI systems, as responsible and evidence-based therapy requires nuanced expertise. This paper provides a roadmap for the ambitious yet responsible application of clinical LLMs in psychotherapy. First, a technical overview of clinical LLMs is presented. Second, the stages of integration of LLMs into psychotherapy are discussed while highlighting parallels to the development of autonomous vehicle technology. Third, potential applications of LLMs in clinical care, training, and research are discussed, highlighting areas of risk given the complex nature of psychotherapy. Fourth, recommendations for the responsible development and evaluation of clinical LLMs are provided, which include centering clinical science, involving robust interdisciplinary collaboration, and attending to issues like assessment, risk detection, transparency, and bias. Lastly, a vision is outlined for how LLMs might enable a new generation of studies of evidence-based interventions at scale, and how these studies may challenge assumptions about psychotherapy.

Neural differentiation of emotional faces as a function of interpersonal violence among adolescent girls

Interpersonal violence (IV) is associated with altered neural threat processing and risk for psychiatric disorder. Representational similarity analysis (RSA) is a multivariate approach examining the extent to which differences between stimuli correspond to differences in multivoxel activation patterns to these stimuli within each ROI. Using RSA, we examine overlap in neural patterns between threat and neutral faces in youth with IV. Participants were female adolescents aged 11-17 who had a history of IV exposure (n = 77) or no history of IV, psychiatric diagnoses, nor psychiatric medications (n = 37). Participants completed a facial emotion processing task during fMRI. Linear mixed models indicated that increasing hippocampal differentiation of fear and neutral faces was associated with increasing IV severity. Increased neural differentiation of these facial stimuli in the left and right hippocampus was associated with increasing physical abuse severity. Increased differentiation by the dACC correlated with increasing physical assault severity. RSA for most ROIs were not significantly associated with univariate activity, except for a positive association between amygdala RSA and activity to fear faces. Differences in statistically significant ROIs for physical assault and physical abuse may highlight distinct effects of trauma type on encoding of threat vs. neutral faces. Null associations between RSA and univariate activation in most ROIs suggest unique contributions of RSA for understanding IV compared to traditional activation. Implications include understanding mechanisms of risk in IV and trauma-specific treatment selection. Future work should replicate these findings in longitudinal studies and identify sensitive periods for neural alterations in RSA.

When Are Social Protests Effective?

Around the world, people engage in social protests aimed at addressing major societal problems. Certain protests have led to significant progress, yet other protests have resulted in little demonstrable change. We introduce a framework for evaluating the effectiveness of social protest made up of three components: (i) what types of action are being considered; (ii) what target audience is being affected; and (iii) what outcomes are being evaluated? We then review relevant research to suggest how the framework can help synthesize conflicting findings in the literature. This synthesis points to two key conclusions: that nonviolent protests are effective at mobilizing sympathizers to support the cause, whereas more disruptive protests can motivate support for policy change among resistant individuals.

To Use or Not to Use: Exploring Therapists' Experiences with Pre-Treatment EMA-Based Personalized Feedback in the TheraNet Project

BACKGROUND

Using idiographic network models in psychotherapy has been a growing area of interest. However, little is known about the perceived clinical utility of network models. The present study aims to explore therapists' experiences with network model-based feedback within the context of the TheraNet Project.

METHODS

In total, 18 therapists who had received network-based feedback for at least 1 patient at least 2 months prior were invited to retrospective focus groups. The focus group questions related to how participation in the study influenced the therapeutic relationship, how the networks were used, and what might improve their clinical utility. The transcribed focus groups were analyzed descriptively using qualitative content analysis.

RESULTS

Most therapists mentioned using the feedback to support their existingtheir case concept, while fewer therapists discussed the feedback directly with the patients. Several barriers to using the feedback were discussed, as well as various suggestions for how to make it more clinically useful. Many therapists reported skepticism with regards to research in the outpatient training center in general, though they were also all pleasantly surprised by being involved, having their opinions heard, and showing a readiness to adapt research to their needs/abilities.

CONCLUSIONS

This study highlights the gap between researchers' and therapists' perceptions about what useful feedback should look like. The TheraNet therapists' interest in adapting the feedback and building more informative feedback systems signals a general openness to the implementation of clinically relevant research. We provide suggestions for future implementations of network-based feedback systems in the outpatient clinical training center setting.

Using the Personalized Advantage Index to determine which veterans may benefit from more vs. less comprehensive intensive PTSD treatment programs

Background: Intensive PTSD treatment programs (ITPs) are highly effective but tend to differ greatly in length and the number of adjunctive services that are provided in conjunction with evidence-based PTSD treatments. Individuals' treatment response to more or less comprehensive ITPs is poorly understood.Objective: To apply a machine learning-based decision-making model (the Personalized Advantage Index (PAI)), using clinical and demographic factors to predict response to more or less comprehensive ITPs.Methods: The PAI was developed and tested on a sample of 747 veterans with PTSD who completed a 3-week (more comprehensive; n = 360) or 2-week (less comprehensive; n = 387) ITP.Results: Approximately 12.32% of the sample had a PAI value that suggests that individuals would have experienced greater PTSD symptom change (5 points) on the PTSD Checklist for DSM-5 in either a more- or less comprehensive ITP. For individuals with the highest 25% of PAI values, effect sizes for the amount of PTSD symptom change between those in their optimal vs. non-optimal programs was d = 0.35.Conclusions: Although a minority was predicted to have benefited more from a program, there generally was not a substantial difference in predicted outcomes. Less comprehensive and thus more financially sustainable ITPs appear to work well for most individuals with PTSD.

Exploring alternative approaches to precision medicine through genomics and artificial intelligence - a systematic review

The core idea behind precision medicine is to pinpoint the subpopulations that differ from one another in terms of disease risk, drug responsiveness, and treatment outcomes due to differences in biology and other traits. Biomarkers are found through genomic sequencing. Multi-dimensional clinical and biological data are created using these biomarkers. Better analytic methods are needed for these multidimensional data, which can be accomplished by using artificial intelligence (AI). An updated review of 80 latest original publications is presented on four main fronts-preventive medicine, medication development, treatment outcomes, and diagnostic medicine-All these studies effectively illustrated the significance of AI in precision medicine. Artificial intelligence (AI) has revolutionized precision medicine by swiftly analyzing vast amounts of data to provide tailored treatments and predictive diagnostics. Through machine learning algorithms and high-resolution imaging, AI assists in precise diagnoses and early disease detection. AI's ability to decode complex biological factors aids in identifying novel therapeutic targets, allowing personalized interventions and optimizing treatment outcomes. Furthermore, AI accelerates drug discovery by navigating chemical structures and predicting drug-target interactions, expediting the development of life-saving medications. With its unrivaled capacity to comprehend and interpret data, AI stands as an invaluable tool in the pursuit of enhanced patient care and improved health outcomes. It's evident that AI can open a new horizon for precision medicine by translating complex data into actionable information. To get better results in this regard and to fully exploit the great potential of AI, further research is required on this pressing subject.

Predictors and moderators of three online interventions for eating disorder symptoms in a randomized controlled trial

OBJECTIVE

To optimize treatment recommendations for eating disorders, it is important to investigate whether some individuals may benefit more (or less) from certain treatments. The current study explored predictors and moderators of an automated online self-help intervention "Featback" and online support from a recovered expert patient.

METHODS

Data were used from a randomized controlled trial. For a period of 8 weeks, participants aged 16 or older with at least mild eating disorder symptoms were randomized to four conditions: (1) Featback, (2) chat or e-mail support from an expert patient, (3) Featback with expert-patient support, and (4) a waitlist. A mixed-effects partitioning method was used to see if age, educational level, BMI, motivation to change, treatment history, duration of eating disorder, number of binge eating episodes in the past month, eating disorder pathology, self-efficacy, anxiety and depression, social support, or self-esteem predicted or moderated intervention outcomes in terms of eating disorder symptoms (primary outcome), and symptoms of anxiety and depression (secondary outcome).

RESULTS

Higher baseline social support predicted less eating disorder symptoms 8 weeks later, regardless of condition. No variables emerged as moderator for eating disorder symptoms. Participants in the three active conditions who had not received previous eating disorder treatment, experienced larger reductions in anxiety and depression symptoms.

DISCUSSION

The investigated online low-threshold interventions were especially beneficial for treatment-naïve individuals, but only in terms of secondary outcomes, making them well-suited for early intervention. The study results also highlight the importance of a supportive environment for individuals with eating disorder symptoms.

PUBLIC SIGNIFICANCE

To optimize treatment recommendations it is important to investigate what works for whom. For an internet-based intervention for eating disorders developed in the Netherlands, individuals who had never received eating disorder treatment seemed to benefit more from the intervention than those who had received eating disorder treatment, because they experienced larger reductions in symptoms of depression and anxiety. Stronger feelings of social support were related to less eating disorder symptoms in the future.

Why is it so hard to identify (consistent) predictors of treatment outcome in psychotherapy? - clinical and research perspectives

BACKGROUND

Anxiety and depression are two of the most debilitating psychological disorders worldwide today. Fortunately, effective treatments exist. However, a large proportion of patients do not recover from treatment, and many still have symptoms after completing treatment. Numerous studies have tried to identify predictors of treatment outcome. So far, researchers have found few or no consistent predictors applicable to allocate patients to relevant treatment.

METHODS

We set out to investigate why it is so hard to identify (consistent) predictors of treatment outcome for psychotherapy in anxiety and depression by reviewing relevant literature.

RESULTS

Four challenges stand out; a) the complexity of human lives, b) sample size and statistical power, c) the complexity of therapist-patient relationships, and d) the lack of consistency in study designs. Together these challenges imply there are a countless number of possible predictors. We also consider ethical implications of predictor research in psychotherapy. Finally, we consider possible solutions, including the use of machine learning, larger samples and more realistic complex predictor models.

CONCLUSIONS

Our paper sheds light on why it is so hard to identify consistent predictors of treatment outcome in psychotherapy and suggest ethical implications as well as possible solutions to this problem.

Behavioural and nondirective parent training for children with externalising disorders: First steps towards personalised treatment recommendations

For children with externalising disorders, parent training programmes with different theoretical foundations are available. Currently, there is little knowledge concerning which programme should be recommended to a family based on their individual needs (e.g., single parenthood). The personalised advantage index (PAI) indicates the predicted treatment advantage of one treatment over another. The aim of the present study was to examine the usefulness of this score in providing individualised treatment recommendations. The analysis considered 110 parents (per-protocol sample) of children (4-11 years) with attention-deficit/hyperactivity (ADHD) or oppositional defiant disorder (ODD), randomised to either a behavioural or a nondirective telephone-assisted self-help parent training. In multiple moderator analyses with four different regression algorithms (linear, ridge, k-nearest neighbors, and tree), the linear model was preferred for computing the PAI. For ODD, families randomised to their PAI-predicted optimal intervention showed a treatment advantage of d = 0.54, 95% CI [0.17, 0.97]; for ADHD, the advantage was negligible at d = 0.35, 95% CI [-0.01, 0.78]. For children with conduct problems, it may be helpful if the PAI includes the treatment moderators single parent status and ODD baseline symptoms when providing personalised treatment recommendations for the selection of behavioural versus nondirective parent training. TRIAL REGISTRATION: The study was registered prospectively with ClinicalTrials.gov (Identifier NCT01350986).

Moderators of LGBQ-affirmative cognitive behavioral therapy: ESTEEM is especially effective among Black and Latino sexual minority men

OBJECTIVE

Lesbian, gay, bisexual, and queer (LGBQ)-affirmative cognitive behavioral therapy (CBT) focused on minority stress processes can address gay and bisexual men's transdiagnostic mental and behavioral health concerns. Identifying moderators of treatment outcomes may inform the mechanisms of LGBQ-affirmative CBT and subpopulations who may derive particular benefit.

METHOD

Data were from a clinical trial in which gay and bisexual men with mental and behavioral health concerns were randomized to receive Effective Skills to Empower Effective Men (ESTEEM; an LGBQ-affirmative transdiagnostic CBT; n = 100) or one of two control conditions (n = 154): LGBQ-affirmative community mental health treatment (CMHT) or HIV counseling and testing (HCT). The preregistered outcome was a comorbidity index of depression, anxiety, alcohol/drug problems, and human immunodeficiency virus (HIV) transmission risk behavior at 8-month follow-up (i.e., 4 months postintervention). A two-step exploratory machine learning process was employed for 20 theoretically informed baseline variables identified by study therapists as potential moderators of ESTEEM efficacy. Potential moderators included demographic factors, pretreatment comorbidities, clinical facilitators, and minority stress factors.

RESULTS

Racial/ethnic minority identification, namely as Black or Latino, was the only statistically significant moderator of treatment efficacy (B = -3.23, 95% CI [-5.03, -1.64]), t(197) = -3.88, p < .001. Racially/ethnically minoritized recipients (d = -0.71, p < .001), but not White/non-Latino recipients (d = 0.22, p = .391), had greater reductions in comorbidity index scores in ESTEEM compared to the control conditions. This moderation was driven by improvements in anxiety and alcohol/drug use problems.

DISCUSSION

Black and Latino gay and bisexual men experiencing comorbid mental and behavioral health risks might particularly benefit from a minority stress-focused LGBQ-affirmative CBT. Future research should identify mechanisms for this moderation to inform targeted treatment delivery and dissemination. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Methodological and Quality Flaws in the Use of Artificial Intelligence in Mental Health Research: Systematic Review

BACKGROUND

Artificial intelligence (AI) is giving rise to a revolution in medicine and health care. Mental health conditions are highly prevalent in many countries, and the COVID-19 pandemic has increased the risk of further erosion of the mental well-being in the population. Therefore, it is relevant to assess the current status of the application of AI toward mental health research to inform about trends, gaps, opportunities, and challenges.

OBJECTIVE

This study aims to perform a systematic overview of AI applications in mental health in terms of methodologies, data, outcomes, performance, and quality.

METHODS

A systematic search in PubMed, Scopus, IEEE Xplore, and Cochrane databases was conducted to collect records of use cases of AI for mental health disorder studies from January 2016 to November 2021. Records were screened for eligibility if they were a practical implementation of AI in clinical trials involving mental health conditions. Records of AI study cases were evaluated and categorized by the International Classification of Diseases 11th Revision (ICD-11). Data related to trial settings, collection methodology, features, outcomes, and model development and evaluation were extracted following the CHARMS (Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies) guideline. Further, evaluation of risk of bias is provided.

RESULTS

A total of 429 nonduplicated records were retrieved from the databases and 129 were included for a full assessment-18 of which were manually added. The distribution of AI applications in mental health was found unbalanced between ICD-11 mental health categories. Predominant categories were Depressive disorders (n=70) and Schizophrenia or other primary psychotic disorders (n=26). Most interventions were based on randomized controlled trials (n=62), followed by prospective cohorts (n=24) among observational studies. AI was typically applied to evaluate quality of treatments (n=44) or stratify patients into subgroups and clusters (n=31). Models usually applied a combination of questionnaires and scales to assess symptom severity using electronic health records (n=49) as well as medical images (n=33). Quality assessment revealed important flaws in the process of AI application and data preprocessing pipelines. One-third of the studies (n=56) did not report any preprocessing or data preparation. One-fifth of the models were developed by comparing several methods (n=35) without assessing their suitability in advance and a small proportion reported external validation (n=21). Only 1 paper reported a second assessment of a previous AI model. Risk of bias and transparent reporting yielded low scores due to a poor reporting of the strategy for adjusting hyperparameters, coefficients, and the explainability of the models. International collaboration was anecdotal (n=17) and data and developed models mostly remained private (n=126).

CONCLUSIONS

These significant shortcomings, alongside the lack of information to ensure reproducibility and transparency, are indicative of the challenges that AI in mental health needs to face before contributing to a solid base for knowledge generation and for being a support tool in mental health management.

Psychosocial factors associated with anxious depression

BACKGROUND

Anxious depression is a common subtype of major depressive disorder (MDD) associated with adverse outcomes and severely impaired social function. The aim of this study was to explore the relationships between child maltreatment, family functioning, social support, interpersonal problems, dysfunctional attitudes, and anxious depression.

METHODS

Data were collected from 809 MDD patients. The Hamilton Anxiety Scale (HAMA), Hamilton Depression Scale-17 (HAMD-17), Family Assessment Device (FAD), Childhood Trauma Questionnaire (CTQ), Social Support Rating Scale (SSRS), Interpersonal Relationship Integrative Diagnostic Scale (IRIDS), and Dysfunctional Attitudes Scale (DAS) were administered and recorded. Anxious depression was defined as an anxiety/somatization factor score ≥ 7 on the HAMD-17. Chi-squared tests, Mann-Whitney U tests, distance correlations, and structural equation models were used for data analysis.

RESULTS

Two-fifths of MDD patients had comorbid anxiety, and there were significant differences in child maltreatment, family functioning, social support, interpersonal problems, and dysfunctional attitudes between groups. Of these factors, interpersonal relationships were most related to anxiety in MDD patients, and dysfunctional attitudes mediated the relationship between interpersonal relationships and anxiety in MDD patients.

LIMITATIONS

This study used cross-sectional data with no further follow-up to assess patient outcomes. This study did not include information about pharmacological treatments. A larger sample size is needed to validate the results.

CONCLUSIONS

Psychosocial factors were significantly associated with anxious depression. Interpersonal relationships and dysfunctional attitudes have a direct effect on anxious depression, and interpersonal relationships also mediate the effects of anxious depression via dysfunctional attitudes.

Treatment efficacy and effectiveness in adults with major depressive disorder and childhood trauma history: a systematic review and meta-analysis

BACKGROUND

Childhood trauma is a common and potent risk factor for developing major depressive disorder in adulthood, associated with earlier onset, more chronic or recurrent symptoms, and greater probability of having comorbidities. Some studies indicate that evidence-based pharmacotherapies and psychotherapies for adult depression might be less efficacious in patients with a history of childhood trauma than patients without childhood trauma, but findings are inconsistent. Therefore, we examined whether individuals with major depressive disorder, including chronic forms of depression, and a reported history of childhood trauma, had more severe depressive symptoms before treatment, had more unfavourable treatment outcomes following active treatments, and were less likely to benefit from active treatments relative to a control condition, compared with individuals with depression without childhood trauma.

METHODS

We did a comprehensive meta-analysis (PROSPERO CRD42020220139). Study selection combined the search of bibliographical databases (PubMed, PsycINFO, and Embase) from Nov 21, 2013, to March 16, 2020, and full-text randomised clinical trials (RCTs) identified from several sources (1966 up to 2016-19) to identify articles in English. RCTs and open trials comparing the efficacy or effectiveness of evidence-based pharmacotherapy, psychotherapy, or combination intervention for adult patients with depressive disorders and the presence or absence of childhood trauma were included. Two independent researchers extracted study characteristics. Group data for effect-size calculations were requested from study authors. The primary outcome was depression severity change from baseline to the end of the acute treatment phase, expressed as standardised effect size (Hedges' g). Meta-analyses were done using random-effects models.

FINDINGS

From 10 505 publications, 54 trials met the inclusion criteria, of which 29 (20 RCTs and nine open trials) contributed data of a maximum of 6830 participants (age range 18-85 years, male and female individuals and specific ethnicity data unavailable). More than half (4268 [62%] of 6830) of patients with major depressive disorder reported a history of childhood trauma. Despite having more severe depression at baseline (g=0·202, 95% CI 0·145 to 0·258, I2=0%), patients with childhood trauma benefitted from active treatment similarly to patients without childhood trauma history (treatment effect difference between groups g=0·016, -0·094 to 0·125, I2=44·3%), with no significant difference in active treatment effects (vs control condition) between individuals with and without childhood trauma (childhood trauma g=0·605, 0·294 to 0·916, I2=58·0%; no childhood trauma g=0·178, -0·195 to 0·552, I2=67·5%; between-group difference p=0·051), and similar dropout rates (risk ratio 1·063, 0·945 to 1·195, I2=0%). Findings did not significantly differ by childhood trauma type, study design, depression diagnosis, assessment method of childhood trauma, study quality, year, or treatment type or length, but differed by country (North American studies showed larger treatment effects for patients with childhood trauma; false discovery rate corrected p=0·0080). Most studies had a moderate to high risk of bias (21 [72%] of 29), but the sensitivity analysis in low-bias studies yielded similar findings to when all studies were included.

INTERPRETATION

Contrary to previous studies, we found evidence that the symptoms of patients with major depressive disorder and childhood trauma significantly improve after pharmacological and psychotherapeutic treatments, notwithstanding their higher severity of depressive symptoms. Evidence-based psychotherapy and pharmacotherapy should be offered to patients with major depressive disorder regardless of childhood trauma status.

FUNDING

None.

Prediction model study focusing on eHealth in the management of urinary incontinence: the Personalised Advantage Index as a decision-making aid

OBJECTIVE

To develop a prediction model and illustrate the practical potential of personalisation of treatment decisions between app-based treatment and care as usual for urinary incontinence (UI).

DESIGN

A prediction model study using data from a pragmatic, randomised controlled, non-inferiority trial.

SETTING

Dutch primary care from 2015, with social media included from 2017. Enrolment ended on July 2018.

PARTICIPANTS

Adult women were eligible if they had ≥2 episodes of UI per week, access to mobile apps and wanted treatment. Of the 350 screened women, 262 were eligible and randomised to app-based treatment or care as usual; 195 (74%) attended follow-up.

PREDICTORS

Literature review and expert opinion identified 13 candidate predictors, categorised into two groups: Prognostic factors (independent of treatment type), such as UI severity, postmenopausal state, vaginal births, general physical health status, pelvic floor muscle function and body mass index; and modifiers (dependent on treatment type), such as age, UI type and duration, impact on quality of life, previous physical therapy, recruitment method and educational level.

MAIN OUTCOME MEASURE

Primary outcome was symptom severity after a 4-month follow-up period, measured by the International Consultation on Incontinence Questionnaire the Urinary Incontinence Short Form. Prognostic factors and modifiers were combined into a final prediction model. For each participant, we then predicted treatment outcomes and calculated a Personalised Advantage Index (PAI).

RESULTS

Baseline UI severity (prognostic) and age, educational level and impact on quality of life (modifiers) independently affected treatment effect of eHealth. The mean PAI was 0.99±0.79 points, being of clinical relevance in 21% of individuals. Applying the PAI also significantly improved treatment outcomes at the group level.

CONCLUSIONS

Personalising treatment choice can support treatment decision making between eHealth and care as usual through the practical application of prediction modelling. Concerning eHealth for UI, this could facilitate the choice between app-based treatment and care as usual.

TRIAL REGISTRATION NUMBER

NL4948t.

Towards optimal treatment selection for borderline personality disorder patients (BOOTS): a study protocol for a multicenter randomized clinical trial comparing schema therapy and dialectical behavior therapy

BACKGROUND

Specialized evidence-based treatments have been developed and evaluated for borderline personality disorder (BPD), including Dialectical Behavior Therapy (DBT) and Schema Therapy (ST). Individual differences in treatment response to both ST and DBT have been observed across studies, but the factors driving these differences are largely unknown. Understanding which treatment works best for whom and why remain central issues in psychotherapy research. The aim of the present study is to improve treatment response of DBT and ST for BPD patients by a) identifying patient characteristics that predict (differential) treatment response (i.e., treatment selection) and b) understanding how both treatments lead to change (i.e., mechanisms of change). Moreover, the clinical effectiveness and cost-effectiveness of DBT and ST will be evaluated.

METHODS

The BOOTS trial is a multicenter randomized clinical trial conducted in a routine clinical setting in several outpatient clinics in the Netherlands. We aim to recruit 200 participants, to be randomized to DBT or ST. Patients receive a combined program of individual and group sessions for a maximum duration of 25 months. Data are collected at baseline until three-year follow-up. Candidate predictors of (differential) treatment response have been selected based on the literature, a patient representative of the Borderline Foundation of the Netherlands, and semi-structured interviews among 18 expert clinicians. In addition, BPD-treatment-specific (ST: beliefs and schema modes; DBT: emotion regulation and skills use), BPD-treatment-generic (therapeutic environment characterized by genuineness, safety, and equality), and non-specific (attachment and therapeutic alliance) mechanisms of change are assessed. The primary outcome measure is change in BPD manifestations. Secondary outcome measures include functioning, additional self-reported symptoms, and well-being.

DISCUSSION

The current study contributes to the optimization of treatments for BPD patients by extending our knowledge on "Which treatment - DBT or ST - works the best for which BPD patient, and why?", which is likely to yield important benefits for both BPD patients (e.g., prevention of overtreatment and potential harm of treatments) and society (e.g., increased economic productivity of patients and efficient use of treatments).

TRIAL REGISTRATION

Netherlands Trial Register, NL7699 , registered 25/04/2019 - retrospectively registered.

Can Artificial Intelligence Improve Psychotherapy Research and Practice?

Leonard Bickman's article on the future of artificial intelligence (AI) in psychotherapy research paints an encouraging picture of the progress to be made in this field. We support his perspective, but we also offer some cautionary notes about the boost AI can provide. We suggest that AI is not likely to transform psychotherapy research or practice to the degree seen in pharmacology and medicine because the factors that contribute to treatment response in these realms differ so markedly from one another, and in ways that do not favor advances in psychotherapy. Despite this limitation, it seems likely that AI will have a beneficial impact, improving empirical analysis through data-driven model development, tools for addressing the limitations of traditional regression methods, and novel means of personalizing treatment. In addition, AI has the potential to augment the reach of the researcher and therapist by expanding our ability to gather data and deliver interventions beyond the confines of the lab or clinical office.

Mechanisms of change and heterogeneous treatment effects in psychodynamic and cognitive behavioural therapy for patients with depressive disorder: a randomized controlled trial

BACKGROUND

Major depressive disorder (MDD) is a prevalent psychiatric condition associated with significant disability, mortality and economic burden. Cognitive behavioral therapy (CBT) and psychodynamic psychotherapy (PDT) are found to be equally effective for patients with depression. However, many patients do not respond sufficiently to either treatment. To offer individualized treatment, we need to know if some patients benefit more from one of the two therapies. At present little is known about what patient characteristics (moderators) may be associated with differential outcomes of CBT and PDT, and through what therapeutic processes and mechanisms (mediators) improvements occur in each therapy mode. Presently only theoretical assumptions, sparsely supported by research findings, describe what potentially moderates and mediates the treatment effects of CBT and PDT. The overall aim of this study is to examine theoretically derived putative moderators and mediators in CBT and PDT and strengthen the evidence base about for whom and how these treatments works in a representative sample of patients with MDD.

METHODS

One hundred patients with a diagnosis of MDD will be randomized to either CBT or PDT. Patients will be treated over 28 weeks with either CBT (one weekly session over 16 weeks and three monthly booster sessions) or PDT (one weekly session over 28 weeks). The patients will be evaluated at baseline, during the course of therapy, at the end of therapy, and at follow-up investigations 1 and 3 years post treatment. A large range of patient and observer rated questionnaires (specific preselected putative moderators and mediators) are included.

DISCUSSION

The clinical outcome of this study may better guide clinicians when deciding what kind of treatment any individual patient should be offered. Moreover, the study aims to further our knowledge of what mechanisms lead to symptom improvement and increased psychosocial functioning.

TRIAL REGISTRATION

ClinicalTrials.gov Identifier: NCT03022071.

Personalized Psychotherapy for Outpatients with Major Depression and Anxiety Disorders: Transdiagnostic Versus Diagnosis-Specific Group Cognitive Behavioural Therapy

Background

Only about half of all patients with anxiety disorders or major depression respond to cognitive behaviour therapy (CBT), even though this is an evidence-based treatment. Personalized treatment offers an approach to increase the number of patients who respond to therapy. The aim of this study was to examine predictors and moderators of (differential) treatment outcomes in transdiagnostic versus diagnosis-specific group CBT.

Methods

A sample of 291 patients from three different mental health clinics in Denmark was randomized to either transdiagnostic or diagnosis-specific group CBT. The study outcome was the regression slope of the individual patient's repeated scores on the WHO-5 Well-being Index. Pre-treatment variables were identified as moderators or predictors through a two-step variable selection approach.

Results

While the two-step approach failed to identify any moderators, four predictors were found: level of positive affect, duration of disorder, the detachment personality trait, and the coping strategy of cognitive reappraisal. A prognostic index was constructed, but did not seem to be robust across treatment sites.

Conclusions

Our findings give insufficient evidence to support a recommendation of either transdiagnostic or diagnosis-specific CBT for a given patient or to predict the response to the applied group therapies.

Using the Personalized Advantage Index for Individual Treatment Allocation to Blended Treatment or Treatment as Usual for Depression in Secondary Care

A variety of effective psychotherapies for depression are available, but patients who suffer from depression vary in their treatment response. Combining face-to-face therapies with internet-based elements in the sense of blended treatment is a new approach to treatment for depression. The goal of this study was to answer the following research questions: (1) What are the most important predictors determining optimal treatment allocation to treatment as usual or blended treatment? and (2) Would model-determined treatment allocation using this predictive information and the personalized advantage index (PAI)-approach result in better treatment outcomes? Bayesian model averaging (BMA) was applied to the data of a randomized controlled trial (RCT) comparing the efficacy of treatment as usual and blended treatment in depressive outpatients. Pre-treatment symptomatology and treatment expectancy predicted outcomes irrespective of treatment condition, whereas different prescriptive predictors were found. A PAI of 2.33 PHQ-9 points was found, meaning that patients who would have received the treatment that is optimal for them would have had a post-treatment PHQ-9 score that is two points lower than if they had received the treatment that is suboptimal for them. For 29% of the sample, the PAI was five or greater, which means that a substantial difference between the two treatments was predicted. The use of the PAI approach for clinical practice must be further confirmed in prospective research; the current study supports the identification of specific interventions favorable for specific patients.