Predicting cognitive behavioral therapy outcome in the outpatient sector based on clinical routine data: A machine learning approach

Predictors of treatment outcome of psychological therapies for common mental health problems (CMHP) in older adults: A systematic literature review

Identifying factors that impact psychological treatment outcomes in older people with common mental health problems (CMHP) has important implications for supporting healthier and longer lives. The aim of the present study was to synthesise the evidence on predictors of psychological treatment outcomes in older people (aged 65+). PubMed, Scopus, Web of Science and PsycINFO were searched and 3929 articles were identified and screened, with 42 studies (N = 7978, M age = 68.9, SD age = 2.85) included: depression: k = 21, anxiety: k = 11, panic disorder: k = 3, mixed anxiety & depression: k = 3, PTSD: k = 2, various CMHP: k = 2, with CBT being the most common treatment (71%). The review identified 28 factors reported as significant predictors of treatment outcome in at least one study, across different domains: psychosocial (n = 9), clinical (n = 6), treatment-related (n = 6), socio-demographic (n = 4), neurobiological (n = 3). Homework completion was the most consistent predictor of positive treatment outcome. Baseline symptom severity was the most frequently studied significant predictor and across all conditions, with higher baseline symptom severity largely linked to worse treatment outcomes. No significant effects on treatment outcome were reported for gender, income and physical comorbidities. For a large majority of factors evidence was mixed or inconclusive. Further studies are required to identify factors affecting psychological treatment outcomes, which will be important for the development of personalised treatment approaches.

Lack of evidence for predictive utility from resting state fMRI data for individual exposure-based cognitive behavioral therapy outcomes: A machine learning study in two large multi-site samples in anxiety disorders

Data-based predictions of individual Cognitive Behavioral Therapy (CBT) treatment response are a fundamental step towards precision medicine. Past studies demonstrated only moderate prediction accuracy (i.e. ability to discriminate between responders and non-responders of a given treatment) when using clinical routine data such as demographic and questionnaire data, while neuroimaging data achieved superior prediction accuracy. However, these studies may be considerably biased due to very limited sample sizes and bias-prone methodology. Adequately powered and cross-validated samples are a prerequisite to evaluate predictive performance and to identify the most promising predictors. We therefore analyzed resting state functional magnet resonance imaging (rs-fMRI) data from two large clinical trials to test whether functional neuroimaging data continues to provide good prediction accuracy in much larger samples. Data came from two distinct German multicenter studies on exposure-based CBT for anxiety disorders, the Protect-AD and SpiderVR studies. We separately and independently preprocessed baseline rs-fMRI data from n = 220 patients (Protect-AD) and n = 190 patients (SpiderVR) and extracted a variety of features, including ROI-to-ROI and edge-functional connectivity, sliding-windows, and graph measures. Including these features in sophisticated machine learning pipelines, we found that predictions of individual outcomes never significantly differed from chance level, even when conducting a range of exploratory post-hoc analyses. Moreover, resting state data never provided prediction accuracy beyond the sociodemographic and clinical data. The analyses were independent of each other in terms of selecting methods to process resting state data for prediction input as well as in the used parameters of the machine learning pipelines, corroborating the external validity of the results. These similar findings in two independent studies, analyzed separately, urge caution regarding the interpretation of promising prediction results based on neuroimaging data from small samples and emphasizes that some of the prediction accuracies from previous studies may result from overestimation due to homogeneous data and weak cross-validation schemes. The promise of resting-state neuroimaging data to play an important role in the prediction of CBT treatment outcomes in patients with anxiety disorders remains yet to be delivered.

Association between resting-state connectivity patterns in the defensive system network and treatment response in spider phobia-a replication approach

Although highly effective on average, exposure-based treatments do not work equally well for all patients with anxiety disorders. The identification of pre-treatment response-predicting patient characteristics may enable patient stratification. Preliminary research highlights the relevance of inhibitory fronto-limbic networks as such. We aimed to identify pre-treatment neural signatures differing between exposure treatment responders and non-responders in spider phobia and to validate results through rigorous replication. Data of a bi-centric intervention study comprised clinical phenotyping and pre-treatment resting-state functional connectivity (rsFC) data of n = 79 patients with spider phobia (discovery sample) and n = 69 patients (replication sample). RsFC data analyses were accomplished using the Matlab-based CONN-toolbox with harmonized analyses protocols at both sites. Treatment response was defined by a reduction of >30% symptom severity from pre- to post-treatment (Spider Phobia Questionnaire Score, primary outcome). Secondary outcome was defined by a reduction of >50% in a Behavioral Avoidance Test (BAT). Mean within-session fear reduction functioned as a process measure for exposure. Compared to non-responders and pre-treatment, results in the discovery sample seemed to indicate that responders exhibited stronger negative connectivity between frontal and limbic structures and were characterized by heightened connectivity between the amygdala and ventral visual pathway regions. Patients exhibiting high within-session fear reduction showed stronger excitatory connectivity within the prefrontal cortex than patients with low within-session fear reduction. Whereas these results could be replicated by another team using the same data (cross-team replication), cross-site replication of the discovery sample findings in the independent replication sample was unsuccessful. Results seem to support negative fronto-limbic connectivity as promising ingredient to enhance response rates in specific phobia but lack sufficient replication. Further research is needed to obtain a valid basis for clinical decision-making and the development of individually tailored treatment options. Notably, future studies should regularly include replication approaches in their protocols.

Deep learning for the prediction of clinical outcomes in internet-delivered CBT for depression and anxiety

In treating depression and anxiety, just over half of all clients respond. Monitoring and obtaining early client feedback can allow for rapidly adapted treatment delivery and improve outcomes. This study seeks to develop a state-of-the-art deep-learning framework for predicting clinical outcomes in internet-delivered Cognitive Behavioural Therapy (iCBT) by leveraging large-scale, high-dimensional time-series data of client-reported mental health symptoms and platform interaction data. We use de-identified data from 45,876 clients on SilverCloud Health, a digital platform for the psychological treatment of depression and anxiety. We train deep recurrent neural network (RNN) models to predict whether a client will show reliable improvement by the end of treatment using clinical measures, interaction data with the iCBT program, or both. Outcomes are based on total improvement in symptoms of depression (Patient Health Questionnaire-9, PHQ-9) and anxiety (Generalized Anxiety Disorder-7, GAD-7), as reported within the iCBT program. Using internal and external datasets, we compare the proposed models against several benchmarks and rigorously evaluate them according to their predictive accuracy, sensitivity, specificity and AUROC over treatment. Our proposed RNN models consistently predict reliable improvement in PHQ-9 and GAD-7, using past clinical measures alone, with above 87% accuracy and 0.89 AUROC after three or more review periods, outperforming all benchmark models. Additional evaluations demonstrate the robustness of the achieved models across (i) different health services; (ii) geographic locations; (iii) iCBT programs, and (iv) client severity subgroups. Results demonstrate the robust performance of dynamic prediction models that can yield clinically helpful prognostic information ready for implementation within iCBT systems to support timely decision-making and treatment adjustments by iCBT clinical supporters towards improved client outcomes.

Predicting non-improvement of symptoms in daily mental healthcare practice using routinely collected patient-level data: a machine learning approach

Objectives

Anxiety and mood disorders greatly affect the quality of life for individuals worldwide. A substantial proportion of patients do not sufficiently improve during evidence-based treatments in mental healthcare. It remains challenging to predict which patients will or will not benefit. Moreover, the limited research available on predictors of treatment outcomes comes from efficacy RCTs with strict selection criteria which may limit generalizability to a real-world context. The current study evaluates the performance of different machine learning (ML) models in predicting non-improvement in an observational sample of patients treated in routine specialized mental healthcare.

Methods

In the current longitudinal exploratory prediction study diagnosis-related, sociodemographic, clinical and routinely collected patient-reported quantitative outcome measures were acquired during treatment as usual of 755 patients with a primary anxiety, depressive, obsessive compulsive or trauma-related disorder in a specialized outpatient mental healthcare center. ML algorithms were trained to predict non-response (< 0.5 standard deviation improvement) in symptomatic distress 6 months after baseline. Different models were trained, including models with and without early change scores in psychopathology and well-being and models with a trimmed set of predictor variables. Performance of trained models was evaluated in a hold-out sample (30%) as a proxy for unseen data.

Results

ML models without early change scores performed poorly in predicting six-month non-response in the hold-out sample with Area Under the Curves (AUCs) < 0.63. Including early change scores slightly improved the models' performance (AUC range: 0.68-0.73). Computationally-intensive ML models did not significantly outperform logistic regression (AUC: 0.69). Reduced prediction models performed similar to the full prediction models in both the models without (AUC: 0.58-0.62 vs. 0.58-0.63) and models with early change scores (AUC: 0.69-0.73 vs. 0.68-0.71). Across different ML algorithms, early change scores in psychopathology and well-being consistently emerged as important predictors for non-improvement.

Conclusion

Accurately predicting treatment outcomes in a mental healthcare context remains challenging. While advanced ML algorithms offer flexibility, they showed limited additional value compared to traditional logistic regression in this study. The current study confirmed the importance of taking early change scores in both psychopathology and well-being into account for predicting longer-term outcomes in symptomatic distress.

Moving toward precision PTSD treatment: predicting veterans' intensive PTSD treatment response using continuously updating machine learning models

BACKGROUND

Considerable heterogeneity exists in treatment response to first-line posttraumatic stress disorder (PTSD) treatments, such as Cognitive Processing Therapy (CPT). Relatively little is known about the timing of when during a course of care the treatment response becomes apparent. Novel machine learning methods, especially continuously updating prediction models, have the potential to address these gaps in our understanding of response and optimize PTSD treatment.

METHODS

Using data from a 3-week (n = 362) CPT-based intensive PTSD treatment program (ITP), we explored three methods for generating continuously updating prediction models to predict endpoint PTSD severity. These included Mixed Effects Bayesian Additive Regression Trees (MixedBART), Mixed Effects Random Forest (MERF) machine learning models, and Linear Mixed Effects models (LMM). Models used baseline and self-reported PTSD symptom severity data collected every other day during treatment. We then validated our findings by examining model performances in a separate, equally established, 2-week CPT-based ITP (n = 108).

RESULTS

Results across approaches were very similar and indicated modest prediction accuracy at baseline (R2 ~ 0.18), with increasing accuracy of predictions of final PTSD severity across program timepoints (e.g. mid-program R2 ~ 0.62). Similar findings were obtained when the models were applied to the 2-week ITP. Neither the MERF nor the MixedBART machine learning approach outperformed LMM prediction, though benefits of each may differ based on the application.

CONCLUSIONS

Utilizing continuously updating models in PTSD treatments may be beneficial for clinicians in determining whether an individual is responding, and when this determination can be made.

Developing Transdiagnostic Internalizing Disorder Prognostic Indices for Outpatient Cognitive Behavioral Therapy

A growing literature is devoted to understanding and predicting heterogeneity in response to cognitive behavioral therapy (CBT), including using supervised machine learning to develop prognostic models that could be used to inform treatment planning. The current study developed CBT prognostic models using data from a broad dimensionally oriented pretreatment assessment (324 predictors) of 1,210 outpatients with internalizing psychopathology. Super learning was implemented to develop prognostic indices for three outcomes assessed at 12-month follow-up: principal diagnosis improvement (attained by 65.8% of patients), principal diagnosis remission (56.8%), and transdiagnostic full remission (14.3%). The models for principal diagnosis remission and transdiagnostic remission performed best (AUROCs = 0.71-0.73). Calibration was modest for all three models. Three-quarters (77.3%) of patients in the top tertile of the predicted probability distribution achieved principal diagnosis remission, compared to 35.0% in the bottom tertile. One-third (35.3%) of patients in the top two deciles of predicted probabilities for transdiagnostic complete remission achieved this outcome, compared to 2.7% in the bottom tertile. Key predictors included principal diagnosis severity, social anxiety diagnosis/severity, hopelessness, temperament, and global impairment. While additional work is needed to improve performance, integration of CBT prognostic models ultimately could lead to more effective and efficient treatment of patients with internalizing psychopathology.

Acupuncture as an Adjunct Treatment to Cognitive-Behavioral Therapy for Insomnia

Cognitive-behavioral therapy for insomnia (CBT-I) is the main recommended treatment for patients presenting with insomnia; however, the treatment is not equally effective for all, and several factors can contribute to a diminished treatment response. The rationale for combining CBT-I treatment with acupuncture is explored, and evidence supporting its use in treating insomnia and related comorbidities is discussed. Practical, regulatory, and logistical issues with implementing a combined treatment are examined, and future directions for research are made. Growing evidence supports the effectiveness of acupuncture in treating insomnia and comorbid conditions, and warrants further investigation of acupuncture as an adjunct to CBT-I.

A Scoping Review of the Use of Machine Learning in Health Economics and Outcomes Research: Part 2-Data From Nonwearables

OBJECTIVES

Despite the increasing interest in applying machine learning (ML) methods in health economics and outcomes research (HEOR), stakeholders face uncertainties in when and how ML can be used. We reviewed the recent applications of ML in HEOR.

METHODS

We searched PubMed for studies published between January 2020 and March 2021 and randomly chose 20% of the identified studies for the sake of manageability. Studies that were in HEOR and applied an ML technique were included. Studies related to wearable devices were excluded. We abstracted information on the ML applications, data types, and ML methods and analyzed it using descriptive statistics.

RESULTS

We retrieved 805 articles, of which 161 (20%) were randomly chosen. Ninety-two of the random sample met the eligibility criteria. We found that ML was primarily used for predicting future events (86%) rather than current events (14%). The most common response variables were clinical events or disease incidence (42%) and treatment outcomes (22%). ML was less used to predict economic outcomes such as health resource utilization (16%) or costs (3%). Although electronic medical records (35%) were frequently used for model development, claims data were used less frequently (9%). Tree-based methods (eg, random forests and boosting) were the most commonly used ML methods (31%).

CONCLUSIONS

The use of ML techniques in HEOR is growing rapidly, but there remain opportunities to apply them to predict economic outcomes, especially using claims databases, which could inform the development of cost-effectiveness models.

Error-related activity of the sensorimotor network contributes to the prediction of response to cognitive-behavioral therapy in obsessive-compulsive disorder

BACKGROUND

Although cognitive behavioral therapy is a highly effective treatment for obsessive-compulsive disorder (OCD), yielding large symptom reductions on the group level, individual treatment response varies considerably. Identification of treatment response predictors may provide important information for maximizing individual treatment response and thus achieving efficient treatment resource allocation. Here, we investigated the predictive value of previously identified biomarkers of OCD, namely the error-related activity of the supplementary motor area (SMA) and the sensorimotor network (SMN, postcentral gyrus/precuneus).

METHODS

Seventy-two participants with a primary diagnosis of OCD underwent functional magnetic resonance imaging (fMRI) scanning while performing a flanker task prior to receiving routine-care CBT.

RESULTS

Error-related BOLD response of the SMN significantly contributed to the prediction of treatment response beyond the variance accounted for by clinical and sociodemographic variables. Stronger error-related SMN activity at baseline was associated with a higher likelihood of treatment response.

CONCLUSIONS

The present results illustrate that the inclusion of error-related SMN activity can significantly increase treatment response prediction quality in OCD. Stronger error-related activity of the SMN may reflect the ability to activate symptom-relevant processing networks and may thus facilitate response to exposure-based CBT interventions.

Using clinical patient characteristics to predict treatment outcome of cognitive behavior therapies for individuals with medically unexplained symptoms: A systematic review and meta-analysis

OBJECTIVE

For individuals with medically unexplained symptoms (MUS), cognitive behavioral therapy (CBT) is the best-evaluated treatment. This systematic review and meta-analyses identify clinical patient characteristics associated with the treatment outcome of CBT for MUS.

METHODS

A systematic literature search (PubMed, PsycInfo, Web of Science) resulted in 53 eligible studies; of these 32 studies could be included in meta-analyses. Pooled correlation coefficients between predictors and treatment outcome were calculated with a random-effects model. Moderator analyses were conducted to examine differences between subgroups of MUS and different levels of methodological study quality.

RESULTS

Meta-analyses demonstrated that individuals with higher symptom intensity (r = 0.38; p < 0.001), lower physical functioning (r = -0.29; p < 0.001), lower emotional and social functioning (r = -0.37; p < 0.001), more potential symptom-related incentives (r = -0.15; p = 0.001), or longer symptom duration (r = 0.10; p = 0.033) at the beginning of treatment reported less change of symptom severity until the end of therapy or higher end-of-treatment symptom severity. The pooled effect sizes did not differ between certain subgroups of MUS or between different levels of methodological quality.

CONCLUSION

Our findings indicated that clinical characteristics of MUS patients are associated with treatment outcome of CBT. We discuss how the results can be used to optimize and personalize future treatments for MUS.

Who will respond to intensive PTSD treatment? A machine learning approach to predicting response prior to starting treatment

Despite the established effectiveness of evidence-based PTSD treatments, not everyone responds the same. Specifically, some individuals respond early while others respond minimally throughout treatment. Our ability to predict these trajectories at baseline has been limited. Predicting which individuals will respond to a certain type of treatment can significantly reduce short- and long-term costs and increase the ability to preemptively match individuals with treatments to which they are most likely to respond. In the present study, we examined whether veterans' responses to a 3-week Cognitive Processing Therapy-based intensive PTSD treatment program could be accurately predicted prior to the first session. Using a sample of 432 veterans, and a wide range of demographic and clinical data collected during intake, we assessed six machine learning and statistical methods and their ability to predict fast and minimal responders prior to treatment initiation. For fast response classification, gradient boosted models (GBM) had the highest AUC-PR (0.466). For minimal response classification, elastic net (EN) had the highest mean CV AUC-PR (0.628). Using the best performing classifiers, we were able to predict both fast and minimal responders prior to starting treatment with relatively high AUC-ROC of 0.765 (GBM) and 0.826 (EN), respectively. These results may inform treatment modifications, although the accuracy may not be sufficient for clinicians to base inclusion/exclusion decisions entirely on the classifiers. Future research should evaluate whether these classifiers can be expanded to predict to which treatment type(s) an individual is most likely to respond based on various clinical, circumstantial, and biological features.

The potential of precision psychiatry: what is in reach?

Progress in developing personalised care for mental disorders is supported by numerous proof-of-concept machine learning studies in the area of risk assessment, diagnostics and precision prescribing. Most of these studies primarily use clinical data, but models might benefit from additional neuroimaging, blood and genetic data to improve accuracy. Combined, multimodal models might offer potential for stratification of patients for treatment. Clinical implementation of machine learning is impeded by a lack of wider generalisability, with efforts primarily focused on psychosis and dementia. Studies across all diagnostic groups should work to test the robustness of machine learning models, which is an essential first step to clinical implementation, and then move to prospective clinical validation. Models need to exceed clinicians' heuristics to be useful, and safe, in routine decision-making. Engagement of clinicians, researchers and patients in digitalisation and 'big data' approaches are vital to allow the generation and accessibility of large, longitudinal, prospective data needed for precision psychiatry to be applied into real-world psychiatric care.

Predicting non-response to multimodal day clinic treatment in severely impaired depressed patients: a machine learning approach

A considerable number of depressed patients do not respond to treatment. Accurate prediction of non-response to routine clinical care may help in treatment planning and improve results. A longitudinal sample of N = 239 depressed patients was assessed at admission to multi-modal day clinic treatment, after six weeks, and at discharge. First, patient’s treatment response was modelled by identifying longitudinal trajectories using the Hamilton Depression Rating Scale (HDRS-17). Then, individual items of the HDRS-17 at admission as well as individual patient characteristics were entered as predictors of response/non-response trajectories into the binary classification model (eXtremeGradient Boosting; XGBoost). The model was evaluated on a hold-out set and explained in human-interpretable form by SHapley Additive explanation (SHAP) values. The prediction model yielded a multi-class AUC = 0.80 in the hold-out set. The predictive power for the binary classification yielded an AUC = 0.83 (sensitivity = .80, specificity = .77). Most relevant predictors for non-response were insomnia symptoms, younger age, anxiety symptoms, depressed mood, being unemployed, suicidal ideation and somatic symptoms of depressive disorder. Non-responders to routine treatment for depression can be identified and screened for potential next-generation treatments. Such predictors may help personalize treatment and improve treatment response.

The Relationship Between CBT-Mindedness and iCBT Outcomes Amongst a Large Adult Sample

Background

Predicting response to cognitive behavior therapy (CBT) assists efforts to enhance treatment outcome when predictive factors are modifiable prior to, or during, treatment. The extent to which clients hold beliefs and attitudes consistent with CBT (termed CBT-mindedness) is a relatively new concept with research suggesting it predicts response to CBT amongst small samples of adults with anxiety. This study aimed to investigate CBT-mindedness amongst a larger clinical population receiving internet-delivered CBT (iCBT).

Method

1132 adults with anxiety, depression or mixed anxiety and depression who accessed iCBT with or without therapist support via the THIS WAY UP clinic completed a brief self-report measure of CBT-mindedness along with measures of distress, anxiety, and depression. Measures were completed pre- and post-treatment.

Results

The 3-factor structure of the CBT Suitability Scale (CBT-SUITS) was confirmed and scores were unrelated or very weakly related to symptoms/distress. CBT-mindedness increased amongst treatment completers. CBT-mindedness predicted post-treatment distress (but not symptoms), and change in CBT-mindedness predicted lower post-treatment symptoms and distress.

Conclusions

The CBT-SUITS represents a psychometrically sound measure of CBT-mindedness. Results amongst this large sample of adults accessing iCBT in a community service indicate that CBT-mindedness (or CBT-mindedness change) is an important predictor of therapy response.

Predicting therapy outcome in a digital mental health intervention for depression and anxiety: A machine learning approach

Objective

Predicting the outcomes of individual participants for treatment interventions appears central to making mental healthcare more tailored and effective. However, little work has been done to investigate the performance of machine learning-based predictions within digital mental health interventions. Therefore, this study evaluates the performance of machine learning in predicting treatment response in a digital mental health intervention designed for treating depression and anxiety.

Methods

Several algorithms were trained based on the data of 970 participants to predict a significant reduction in depression and anxiety symptoms using clinical and sociodemographic variables. As a random forest classifier performed best over cross-validation, it was used to predict the outcomes of 279 new participants.

Results

The random forest achieved an accuracy of 0.71 for the test set (base rate: 0.67, area under curve (AUC): 0.60, p = 0.001, balanced accuracy: 0.60). Additionally, predicted non-responders showed less average reduction of their Patient Health Questionnaire-9 (PHQ-9) (-2.7, p = 0.004) and General Anxiety Disorder Screener-7 values (-3.7, p < 0.001) compared to responders. Besides pre-treatment Patient Health Questionnaire-9 and General Anxiety Disorder Screener-7 values, the self-reported motivation, type of referral into the programme (self vs. healthcare provider) as well as Work Productivity and Activity Impairment Questionnaire items contributed most to the predictions.

Conclusions

This study provides evidence that social-demographic and clinical variables can be used for machine learning to predict therapy outcomes within the context of a therapist-supported digital mental health intervention. Despite the overall moderate performance, this appears promising as these predictions can potentially improve the outcomes of non-responders by monitoring their progress or by offering alternative or additional treatment.

Mental health trajectories of individuals and families following the COVID-19 pandemic: Study protocol of a longitudinal investigation and prevention program

Introduction

Many adults, adolescents and children are suffering from persistent stress symptoms in the face of the COVID-19 pandemic. This study aims to characterize long-term trajectories of mental health and to reduce the transition to manifest mental disorders by means of a stepped care program for indicated prevention.

Methods and analysis

Using a prospective-longitudinal design, we will assess the mental strain of the pandemic using the Patient Health Questionnaire, Strength and Difficulties Questionnaire and Spence Child Anxiety Scale. Hair samples will be collected to assess cortisol as a biological stress marker of the previous months. Additionally, we will implement a stepped-care program with online- and face-to-face-interventions for adults, adolescents, and children. After that we will assess long-term trajectories of mental health at 6, 12, and 24 months follow-up. The primary outcome will be psychological distress (depression, anxiety and somatoform symptoms). Data will be analyzed with general linear model and machine learning. This study will contribute to the understanding of the impact of the COVID-19 pandemic on mental health. The evaluation of the stepped-care program and longitudinal investigation will inform clinicians and mental health stakeholders on populations at risk, disease trajectories and the sufficiency of indicated prevention to ameliorate the mental strain of the pandemic.

Ethics and dissemination

The study is performed according to the Declaration of Helsinki and was approved by the Ethics Committee of the Department of Psychology at the Humboldt Universität zu Berlin (no. 2020-35).

Trial registration number

DRKS00023220.

Clinical predictors of treatment response towards exposure therapy in virtuo in spider phobia: A machine learning and external cross-validation approach

While being highly effective on average, exposure-based treatments are not equally effective in all patients. The a priori identification of patients with a poor prognosis may enable the application of more personalized psychotherapeutic interventions. We aimed at identifying sociodemographic and clinical pre-treatment predictors for treatment response in spider phobia (SP). N = 174 patients with SP underwent a highly standardized virtual reality exposure therapy (VRET) at two independent sites. Analyses on group-level were used to test the efficacy. We applied a state-of-the-art machine learning protocol (Random Forests) to evaluate the predictive utility of clinical and sociodemographic predictors for a priori identification of individual treatment response assessed directly after treatment and at 6-month follow-up. The reliability and generalizability of predictive models was tested via external cross-validation. Our study shows that one session of VRET is highly effective on a group-level and is among the first to reveal long-term stability of this treatment effect. Individual short-term symptom reductions could be predicted above chance, but accuracies dropped to non-significance in our between-site prediction and for predictions of long-term outcomes. With performance metrics hardly exceeding chance level and the lack of generalizability in the employed between-site replication approach, our study suggests limited clinical utility of clinical and sociodemographic predictors. Predictive models including multimodal predictors may be more promising.

Neural processing of emotional facial stimuli in specific phobia: An fMRI study

BACKGROUND

Patients with specific phobia (SP) show altered brain activation when confronted with phobia-specific stimuli. It is unclear whether this pathogenic activation pattern generalizes to other emotional stimuli. This study addresses this question by employing a well-powered sample while implementing an established paradigm using nonspecific aversive facial stimuli.

METHODS

N = 111 patients with SP, spider subtype, and N = 111 healthy controls (HCs) performed a supraliminal emotional face-matching paradigm contrasting aversive faces versus shapes in a 3-T magnetic resonance imaging scanner. We performed region of interest (ROI) analyses for the amygdala, the insula, and the anterior cingulate cortex using univariate as well as machine-learning-based multivariate statistics based on this data. Additionally, we investigated functional connectivity by means of psychophysiological interaction (PPI).

RESULTS

Although the presentation of emotional faces showed significant activation in all three ROIs across both groups, no group differences emerged in all ROIs. Across both groups and in the HC > SP contrast, PPI analyses showed significant task-related connectivity of brain areas typically linked to higher-order emotion processing with the amygdala. The machine learning approach based on whole-brain activity patterns could significantly differentiate the groups with 73% balanced accuracy.

CONCLUSIONS

Patients suffering from SP are characterized by differences in the connectivity of the amygdala and areas typically linked to emotional processing in response to aversive facial stimuli (inferior parietal cortex, fusiform gyrus, middle cingulate, postcentral cortex, and insula). This might implicate a subtle difference in the processing of nonspecific emotional stimuli and warrants more research furthering our understanding of neurofunctional alteration in patients with SP.

The promise of machine learning in predicting treatment outcomes in psychiatry

For many years, psychiatrists have tried to understand factors involved in response to medications or psychotherapies, in order to personalize their treatment choices. There is now a broad and growing interest in the idea that we can develop models to personalize treatment decisions using new statistical approaches from the field of machine learning and applying them to larger volumes of data. In this pursuit, there has been a paradigm shift away from experimental studies to confirm or refute specific hypotheses towards a focus on the overall explanatory power of a predictive model when tested on new, unseen datasets. In this paper, we review key studies using machine learning to predict treatment outcomes in psychiatry, ranging from medications and psychotherapies to digital interventions and neurobiological treatments. Next, we focus on some new sources of data that are being used for the development of predictive models based on machine learning, such as electronic health records, smartphone and social media data, and on the potential utility of data from genetics, electrophysiology, neuroimaging and cognitive testing. Finally, we discuss how far the field has come towards implementing prediction tools in real-world clinical practice. Relatively few retrospective studies to-date include appropriate external validation procedures, and there are even fewer prospective studies testing the clinical feasibility and effectiveness of predictive models. Applications of machine learning in psychiatry face some of the same ethical challenges posed by these techniques in other areas of medicine or computer science, which we discuss here. In short, machine learning is a nascent but important approach to improve the effectiveness of mental health care, and several prospective clinical studies suggest that it may be working already.

Predicting outcome of daycare cognitive behavioural therapy in a naturalistic sample of patients with PTSD: a machine learning approach

BACKGROUND

Identifying predictors for treatment outcome in patients with posttraumatic stress disorder (PTSD) is important in order to provide an effective treatment, but robust and replicated treatment outcome predictors are not available up to now.

OBJECTIVES

We investigated predictors of treatment outcome in a naturalistic sample of patients with PTSD admitted to an 8-week daycare cognitive behavioural therapy programme following a wide range of traumatic events.

METHOD

We used machine learning (linear and non-linear regressors and cross-validation) to predict outcome at discharge for 116 patients and sustained treatment effects 6 months after discharge for 52 patients who had a follow-up assessment. Predictions were based on a wide selection of demographic and clinical assessments including age, gender, comorbid psychiatric disorders, trauma history, posttraumatic symptoms, posttraumatic cognitions, depressive symptoms, general psychopathology and psychosocial functioning.

RESULTS

We found that demographic and clinical variables significantly, but only modestly predicted PTSD treatment outcome at discharge (r = 0.21, p = .021 for the best model) and follow-up (r = 0.31, p = .026). Among the included variables, more severe posttraumatic cognitions were negatively associated with treatment outcome. Early response in PTSD symptomatology (percentage change of symptom scores after 4 weeks of treatment) allowed more accurate predictions of outcome at discharge (r = 0.56, p < .001) and follow-up (r = 0.43, p = .001).

CONCLUSION

Our results underscore the importance of early treatment response for short- and long-term treatment success. Nevertheless, it remains an unresolved challenge to identify variables that can robustly predict outcome before the initiation of treatment.

Clinical Efficacy and Cost-Effectiveness of Imagery Rescripting Only Compared to Imagery Rescripting and Schema Therapy in Adult Patients With PTSD and Comorbid Cluster C Personality Disorder: Study Design of a Randomized Controlled Trial

Background: Posttraumatic stress disorder (PTSD) is a serious and relatively common mental disorder causing a high burden of suffering. Whereas evidence-based treatments are available, dropout and non-response rates remain high. PTSD and Cluster C personality disorders (avoidant, dependent or obsessive-compulsive personality disorder; CPD) are highly comorbid and there is evidence for suboptimal treatment effects in this subgroup of patients. An integrated PTSD and CPD treatment may be needed to increase treatment efficacy. However, no studies directly comparing the efficacy of regular PTSD treatment and treatment tailored to PTSD and comorbid CPD are available. Whether integrated treatment is more effective than treatment focused on PTSD alone is important, since (1) no evidence-based guideline for PTSD and comorbid CPD treatment exists, and (2) treatment approaches to CPD are costly and time consuming. Present study design describes a randomized controlled trial (RCT) directly comparing trauma focused treatment with integrated trauma focused and personality focused treatment. Methods: An RCT with two parallel groups design will be used to compare the clinical efficacy and cost-effectiveness of "standalone" imagery rescripting (n = 63) with integrated imagery rescripting and schema therapy (n = 63). This trial is part of a larger research project on PTSD and personality disorders. Predictors, mediators and outcome variables are measured at regular intervals over the course of 18 months. The main outcome is PTSD severity at 12 months. Additionally, machine-learning techniques will be used to predict treatment outcome using biopsychosocial variables. Discussion: This study protocol outlines the first RCT aimed at directly comparing the clinical efficacy and cost-effectiveness of imagery rescripting and integrated imagery rescripting and schema therapy for treatment seeking adult patients with PTSD and comorbid cluster C personality pathology. Additionally, biopsychosocial variables will be used to predict treatment outcome. As such, the trial adds to the development of an empirically informed and individualized treatment indication process. Clinical Trial registration: ClinicalTrials.gov, NCT03833531.

The comparison between CBT focused on perfectionism and CBT focused on emotion regulation for individuals with depression and anxiety disorders and dysfunctional perfectionism: a randomized controlled trial

BACKGROUND

There is considerable evidence indicating that similar aetiological and maintenance processes underlie depressive and anxious psychopathology. According to the literature, perfectionism and emotion regulation are two transdiagnostic constructs associated with symptoms of emotional disorders.

AIMS

This study is the first randomized controlled trial comparing the efficacy of cognitive behavioural therapy for perfectionism (CBT-P) and the unified protocol for the transdiagnostic treatment of emotional disorders (UP).

METHOD

Seventy-five participants with a range of depressive and anxiety disorders and elevated perfectionism were randomized to three conditions: CBT-P, UP or a waitlist control (WL).

RESULTS

Repeated measures ANOVA indicated that the treatment groups reported a significantly greater pre-post reduction in the severity of symptoms of disorders, as well as a significantly greater pre-post increase in quality of life, all with moderate to large effect sizes compared with the WL group. Treatment gains were maintained at 6-month follow-up. The CBT-P group reported a significantly greater pre-post reduction in perfectionism compared with UP, and the UP group reported a significantly greater pre-post improvement in emotion regulation compared with CBT-P.

CONCLUSIONS

Findings support CBT for perfectionism and regard UP as efficacious treatments for individuals with depression and anxiety disorders who also have dysfunctional perfectionism. It appears that perfectionism cannot be a serious obstacle to UP. As this is a preliminary study and has some limitations, it is recommended that further research be conducted.

Predicting alcohol dependence treatment outcomes: a prospective comparative study of clinical psychologists versus 'trained' machine learning models

BACKGROUND AND AIMS

Clinical staff are typically poor at predicting alcohol dependence treatment outcomes. Machine learning (ML) offers the potential to model complex clinical data more effectively. This study tested the predictive accuracy of ML algorithms demonstrated to be effective in predicting alcohol dependence outcomes, compared with clinical judgement and traditional linear regression.

DESIGN

Prospective study. ML models were trained on 1016 previously treated patients (training-set) who attended a hospital-based alcohol and drug clinic. ML models (n = 27), clinical psychologists (n = 10) and a 'traditional' logistic regression model (n = 1) predicted treatment outcome during the initial treatment session of an alcohol dependence programme.

SETTING

A 12-week cognitive behavioural therapy (CBT)-based abstinence programme for alcohol dependence in a hospital-based alcohol and drug clinic in Australia.

PARTICIPANTS

Prospective predictions were made for 220 new patients (test-set; 70.91% male, mean age = 35.78 years, standard deviation = 9.19). Sixty-nine (31.36%) patients successfully completed treatment.

MEASUREMENTS

Treatment success was the primary outcome variable. The cross-validated training-set accuracy of ML models was used to determine optimal parameters for selecting models for prospective prediction. Accuracy, sensitivity, specificity, area under the receiver operator curve (AUC), Brier score and calibration curves were calculated and compared across predictions.

FINDINGS

The mean aggregate accuracy of the ML models (63.06%) was higher than the mean accuracy of psychologist predictions (56.36%). The most accurate ML model achieved 70% accuracy, as did logistic regression. Both were more accurate than psychologists (P < 0.05) and had superior calibration. The high specificity for the selected ML (79%) and logistic regression (90%) meant they were significantly (P < 0.001) more effective than psychologists (50%) at correctly identifying patients whose treatment was unsuccessful. For ML and logistic regression, high specificity came at the expense of sensitivity (26 and 31%, respectively), resulting in poor prediction of successful patients.

CONCLUSIONS

Machine learning models and logistic regression appear to be more accurate than psychologists at predicting treatment outcomes in an abstinence programme for alcohol dependence, but sensitivity is low.

Enriching CBT by Neuroscience: Novel Avenues to Achieve Personalized Treatments

Although cognitive behavioral therapy (CBT) is an established and efficient treatment for a variety of common mental disorders, a considerable number of patients do not respond to treatment or relapse after successful CBT. Recent findings and approaches from neuroscience could pave the way for clinical developments to enhance the outcome of CBT. Herein, we will present how neuroscience can offer novel perspectives to better understand (a) the biological underpinnings of CBT, (b) how we can enrich CBT with neuroscience-informed techniques (augmentation of CBT), and (c) why some patients may respond better to CBT than others (predictors of therapy outcomes), thus paving the way for more personalized and effective treatments. We will introduce some key topics and describe a selection of findings from CBT-related research using tools from neuroscience, with the hope that this will provide clinicians and clinical researchers with a brief and comprehensible overview of the field.