Process-Based psychotherapy personalization: considering causality with continuous-time dynamic modeling.

Psychotherapy can be improved by integrating the study of mediators (how it works) and moderators (for whom it works). To demonstrate this integration, we studied the relationship between resource activation, problem-coping experiences and symptoms in cognitive-behavior therapy (CBT) for depression, to obtain preliminary insights on causal inference (which process leads to symptom improvement?) and prediction (which one for whom?).A sample of 715 patients with depression who received CBT was analyzed. Hierarchical Bayesian continuous time dynamic modeling was used to study the temporal dynamics between the variables analyzed within the first ten sessions. Depression and self-efficacy at baseline were examined as predictors of these dynamics.There were significant cross-effects between the processes studied. Under typical assumptions, resource activation had a significant effect on symptom improvement. Problem-coping experience had a significant effect on resource activation. Depression and self-efficacy moderated these effects. However, when system noise was considered, these effects may be affected by other processes.Resource activation was strongly associated with symptom improvement. To the extent of inferring causality, for patients with mild-moderate depression and high self-efficacy, promoting resource activation can be recommended. For patients with severe depression and low self-efficacy, promoting problem-coping experiences can be recommended.

Predicting dropout from psychological treatment using different machine learning algorithms, resampling methods, and sample sizes.

Objective: The occurrence of dropout from psychological interventions is associated with poor treatment outcome and high health, societal and economic costs. Recently, machine learning (ML) algorithms have been tested in psychotherapy outcome research. Dropout predictions are usually limited by imbalanced datasets and the size of the sample. This paper aims to improve dropout prediction by comparing ML algorithms, sample sizes and resampling methods. Method: Twenty ML algorithms were examined in twelve subsamples (drawn from a sample of N = 49,602) using four resampling methods in comparison to the absence of resampling and to each other. Prediction accuracy was evaluated in an independent holdout dataset using the F1-Measure. Results: Resampling methods improved the performance of ML algorithms and down-sampling can be recommended, as it was the fastest method and as accurate as the other methods. For the highest mean F1-Score of .51 a minimum sample size of N = 300 was necessary. No specific algorithm or algorithm group can be recommended. Conclusion: Resampling methods could improve the accuracy of predicting dropout in psychological interventions. Down-sampling is recommended as it is the least computationally taxing method. The training sample should contain at least 300 cases.

Predicting patients who will drop out of out-patient psychotherapy using machine learning algorithms.

BACKGROUND: About 30% of patients drop out of cognitive-behavioural therapy (CBT), which has implications for psychiatric and psychological treatment. Findings concerning drop out remain heterogeneous. AIMS: This paper aims to compare different machine-learning algorithms using nested cross-validation, evaluate their benefit in naturalistic settings, and identify the best model as well as the most important variables. METHOD: The data-set consisted of 2543 out-patients treated with CBT. Assessment took place before session one. Twenty-one algorithms and ensembles were compared. Two parameters (Brier score, area under the curve (AUC)) were used for evaluation. RESULTS: The best model was an ensemble that used Random Forest and nearest-neighbour modelling. During the training process, it was significantly better than generalised linear modelling (GLM) (Brier score: d = -2.93, 95% CI (-3.95, -1.90)); AUC: d = 0.59, 95% CI (0.11 to 1.06)). In the holdout sample, the ensemble was able to correctly identify 63.4% of cases of patients, whereas the GLM only identified 46.2% correctly. The most important predictors were lower education, lower scores on the Personality Style and Disorder Inventory (PSSI) compulsive scale, younger age, higher scores on the PSSI negativistic and PSSI antisocial scale as well as on the Brief Symptom Inventory (BSI) additional scale (mean of the four additional items) and BSI overall scale. CONCLUSIONS: Machine learning improves drop-out predictions. However, not all algorithms are suited to naturalistic data-sets and binary events. Tree-based and boosted algorithms including a variable selection process seem well-suited, whereas more advanced algorithms such as neural networks do not.

Prospective evaluation of a clinical decision support system in psychological therapy.

OBJECTIVE: Thus far, most applications in precision mental health have not been evaluated prospectively. This article presents the results of a prospective randomized-controlled trial investigating the effects of a digital decision support and feedback system, which includes two components of patient-specific recommendations: (a) a clinical strategy recommendation and (b) adaptive recommendations for patients at risk for treatment failure. METHOD: Therapist-patient dyads (N = 538) in a cognitive behavioral therapy outpatient clinic were randomized to either having access to a decision support system (intervention group; n = 335) or not (treatment as usual; n = 203). First, treatment strategy recommendations (problem-solving, motivation-oriented, or a mix of both strategies) for the first 10 sessions were evaluated. Second, the effect of psychometric feedback enhanced with clinical problem-solving tools on treatment outcome was investigated. RESULTS: The prospective evaluation showed a differential effect size of about 0.3 when therapists followed the recommended treatment strategy in the first 10 sessions. Moreover, the linear mixed models revealed therapist symptom awareness and therapist attitude and confidence as significant predictors of an outcome as well as therapist-rated usefulness of feedback as a significant moderator of the feedback-outcome and the not on track-outcome associations. However, no main effects were found for feedback. CONCLUSIONS: The results demonstrate the importance of prospective studies and the high-quality implementation of digital decision support tools in clinical practice. Therapists seem to be able to learn from such systems and incorporate them into their clinical practice to enhance patient outcomes, but only when implementation is successful. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

Are some therapists better at facilitating and consolidating sudden gains than others?

BACKGROUND: Changes during psychotherapy often include sudden symptom improvements, called sudden gains (SGs), which have been identified as being superior to gradual symptom change with regard to treatment success. This study investigates the role of therapists in initiating and/or consolidating SGs. METHODS: The analyses are based on a sample of patients (N = 1937) who were seen by 155 therapists and received individual psychotherapy at a university outpatient clinic. First, the therapist effect (TE) on SG was investigated using multilevel modeling (MLM). Second, MLM was used to explore the relative importance of patient and therapist variability in SGs as they relate to outcome. RESULTS: The TE on SGs accounted for 1.8% of variance, meaning that therapists are accountable for inter-individual differences in their patients' likelihood to experience SGs. Furthermore, results revealed a significant effect of SGs on outcome for both levels, while therapist differences regarding the consolidation of SGs were not significant. CONCLUSIONS: The analyses indicated that some therapists are better in facilitating and initiating SGs. The process of triggering SGs seems to be a therapist skill or competence, which opens up an additional pathway to positive outcomes that could be used to improve clinical training.

Therapist Interventions and Skills as Predictors of Dropout in Outpatient Psychotherapy.

The current study employed machine learning to investigate whether the inclusion of observer-rated therapist interventions and skills in early sessions of psychotherapy improved dropout prediction beyond intake assessments. Patients were treated by postgraduate clinicians at a university outpatient clinic. Psychometric instruments were assessed at intake and therapeutic interventions and skills in the third session were routinely rated by independent observers. After variable preselection, an elastic net algorithm was used to build two dropout prediction models, one including and one excluding observer-rated session variables. The best model included observer-rated variables and was significantly superior to the model including intake variables only. Alongside intake variables, two observer-rated variables significantly predicted dropout: therapist use of feedback and summaries and treatment difficulty. Although not retained in the final prediction model, the observer-rated use of cognitive techniques was also significantly correlated with dropout. Observer ratings of therapist interventions and skills in early sessions of psychotherapy improve predictors of dropout from psychotherapy beyond intake variables alone. Future research could work toward personalizing dropout predictions to the specific dyad, thereby improving their validity and aiding therapists to recognize and react to increased dropout risk.

Assessing treatment integrity in personalized CBT: the inventory of therapeutic interventions and skills.

The third wave of cognitive behavioral therapy (CBT) has increased the heterogeneity of today's CBT practice, while developments in patient-focused research are paving the road to the empirical personalization of CBT. This paper presents the development and psychometric properties of a therapy video rating instrument, which was designed to adequately assess the treatment integrity (adherence and competence) of modern, personalized CBT. The Inventory of Therapeutic Interventions and Skills (ITIS) was developed based on two existing CBT adherence and competence scales and augmented with third wave content and overarching therapeutic strategies. The instrument was then applied by graduate students and post-graduate clinicians to rate N = 185 therapy videos from N = 70 patients treated at a university outpatient clinic. Descriptive results, inter-rater reliability, item structure, and associations with session outcome and alliance were examined. Average inter-rater reliability was excellent for Interventions items and good for Skills items. Intercorrelations were low between Interventions items, but higher and significant between Skills items, which loaded on a single factor. Several ITIS items were shown to be predictive of session outcome and alliance, even after controlling for the nested data structure. Implications of these results for future research and clinical training are discussed.