Analysis of Features Selected by a Deep Learning Model for Differential Treatment Selection in Depression

Linguistic markers of anxiety and depression in Somatic Symptom and Related Disorders: Observational study of a digital intervention

BACKGROUND

Somatic Symptom and Related Disorders (SSRD), including chronic pain, result in frequent primary care visits, depression and anxiety symptoms, and diminished quality of life. Treatment access remains limited due to structural barriers and functional impairment. Digital delivery offers to improve access and enables transcript analysis via Natural Language Processing (NLP) to inform treatment. Therefore, we investigated asynchronous message-delivered SSRD treatment, and used NLP methods to identify symptom reduction markers from emotional valence.

METHODS

173 individuals diagnosed with SSRD received interventions from licensed therapists via messaging 5 days/week for 8 weeks. Depression and anxiety symptoms were measured with the PHQ-9 and GAD-7 from baseline every three weeks. Symptoms trajectories were identified using unsupervised random forest clustering. Emotional valence expressed and use of emotional words were extracted from patients' de-identified transcripts, respectively using VADER and NCR Lexicon. Valence differences were examined using logistic regression.

RESULTS

Two subpopulations were identified showing symptoms Improvement (n = 72; 41.62 %) and non-response (n = 101; 58.38 %). Improvement patients expressed more positive valence in the first week of treatment (OR = 1.84, CI: 1.12-3.02; p = .015) and were less likely to express negative valence by the end of treatment (OR = 0.05; CI: 0.30-0.83; p = .008). Non-response patients used more negative valence words, including pain.

LIMITATIONS

Findings were derived from observational data obtained during an ecological intervention, without the inclusion of a control group.

CONCLUSIONS

NLP identified linguistic markers distinguishing changes in anxiety and depression symptoms over treatment. Digital interventions offer new forms of delivery and provide the opportunity to automatically collect data for linguistic analysis.

Development of a multivariate prediction model for antidepressant resistant depression using reward-related predictors

Introduction

Individuals with depression who do not respond to two or more courses of serotonergic antidepressants tend to have greater deficits in reward processing and greater internalizing symptoms, yet there is no validated self-report method to determine the likelihood of treatment resistance based on these symptom dimensions.

Methods

This online case-control study leverages machine learning techniques to identify differences in self-reported anhedonia and internalizing symptom profiles of antidepressant non-responders compared to responders and healthy controls, as an initial proof-of-concept for relating these indicators to medication responsiveness. Random forest classifiers were used to identify a subset from a set of 24 reward predictors that distinguished among serotonergic medication resistant, non-resistant, and non-depressed individuals recruited online (N = 393). Feature selection was implemented to refine model prediction and improve interpretability.

Results

Accuracies for full predictor models ranged from .54 to .71, while feature selected models retained 3-5 predictors and generated accuracies of .42 to .70. Several models performed significantly above chance. Sensitivity for non-responders was greatest after feature selection when compared to only responders, reaching .82 with 3 predictors. The predictors retained from feature selection were then explored using factor analysis at the item level and cluster analysis of the full data to determine empirically driven data structures.

Discussion

Non-responders displayed 3 distinct symptom profiles along internalizing dimensions of anxiety, anhedonia, motivation, and cognitive function. Results should be replicated in a prospective cohort sample for predictive validity; however, this study demonstrates validity for using a limited anhedonia and internalizing self-report instrument for distinguishing between antidepressant resistant and responsive depression profiles.

Towards Outcome-Driven Patient Subgroups: A Machine Learning Analysis Across Six Depression Treatment Studies

BACKGROUND

Major depressive disorder (MDD) is a heterogeneous condition; multiple underlying neurobiological and behavioral substrates are associated with treatment response variability. Understanding the sources of this variability and predicting outcomes has been elusive. Machine learning (ML) shows promise in predicting treatment response in MDD, but its application is limited by challenges to the clinical interpretability of ML models, and clinicians often lack confidence in model results. In order to improve the interpretability of ML models in clinical practice, our goal was to demonstrate the derivation of treatment-relevant patient profiles comprised of clinical and demographic information using a novel ML approach.

METHODS

We analyzed data from six clinical trials of pharmacological treatment for depression (total n = 5438) using the Differential Prototypes Neural Network (DPNN), a ML model that derives patient prototypes which can be used to derive treatment-relevant patient clusters while learning to generate probabilities for differential treatment response. A model classifying remission and outputting individual remission probabilities for five first-line monotherapies and three combination treatments was trained using clinical and demographic data. Prototypes were evaluated for interpretability by assessing differences in feature distributions (e.g. age, sex, symptom severity) and treatment-specific outcomes.

RESULTS

A 3-prototype model achieved an area under the receiver operating curve of 0.66 and an expected absolute improvement in remission rate for those receiving the best predicted treatment of 6.5% (relative improvement of 15.6%) compared to the population remission rate. We identified three treatment-relevant patient clusters. Cluster A patients tended to be younger, to have increased levels of fatigue, and more severe symptoms. Cluster B patients tended to be older, female, have less severe symptoms, and the highest remission rates. Cluster C patients had more severe symptoms, lower remission rates, more psychomotor agitation, more intense suicidal ideation, and more somatic genital symptoms.

CONCLUSION

It is possible to produce novel treatment-relevant patient profiles using ML models; doing so may improve interpretability of ML models and the quality of precision medicine treatments for MDD.

On "Reflections on the concept of optimality of single decision point treatment regimes"

This is a discussion of "Reflections on the concept of optimality of single decision point treatment regimes" by Trung Dung Tran, Ariel Alonso Abad, Geert Verbeke, Geert Molenberghs, and Iven Van Mechelen. The authors propose a thoughtful consideration of optimization targets and the implications of such targets for the resulting optimal treatment rule. However, we contest the assertation that targets of optimization have been overlooked and suggest additional considerations that researchers must contemplate as part of a complete framework for learning about optimal treatment regimes.

Barriers and solutions to the adoption of translational tools for computational psychiatry

Computational psychiatry is a field aimed at developing formal models of information processing in the human brain, and how alterations in this processing can lead to clinical phenomena. There has been significant progress in the development of tasks and how to model them, presenting an opportunity to incorporate computational psychiatry methodologies into large- scale research projects or into clinical practice. In this viewpoint, we explore some of the barriers to incorporation of computational psychiatry tasks and models into wider mainstream research directions. These barriers include the time required for participants to complete tasks, test-retest reliability, limited ecological validity, as well as practical concerns, such as lack of computational expertise and the expense and large sample sizes traditionally required to validate tasks and models. We then discuss solutions, such as the redesigning of tasks with a view toward feasibility, and the integration of tasks into more ecologically valid and standardized game platforms that can be more easily disseminated. Finally, we provide an example of how one task, the conditioned hallucinations task, might be translated into such a game. It is our hope that interest in the creation of more accessible and feasible computational tasks will help computational methods make more positive impacts on research as well as, eventually, clinical practice.

AI-assisted prediction of differential response to antidepressant classes using electronic health records

Antidepressant selection is largely a trial-and-error process. We used electronic health record (EHR) data and artificial intelligence (AI) to predict response to four antidepressants classes (SSRI, SNRI, bupropion, and mirtazapine) 4 to 12 weeks after antidepressant initiation. The final data set comprised 17,556 patients. Predictors were derived from both structured and unstructured EHR data and models accounted for features predictive of treatment selection to minimize confounding by indication. Outcome labels were derived through expert chart review and AI-automated imputation. Regularized generalized linear model (GLM), random forest, gradient boosting machine (GBM), and deep neural network (DNN) models were trained and their performance compared. Predictor importance scores were derived using SHapley Additive exPlanations (SHAP). All models demonstrated similarly good prediction performance (AUROCs ≥ 0.70, AUPRCs ≥ 0.68). The models can estimate differential treatment response probabilities both between patients and between antidepressant classes for the same patient. In addition, patient-specific factors driving response probabilities for each antidepressant class can be generated. We show that antidepressant response can be accurately predicted from real-world EHR data with AI modeling, and our approach could inform further development of clinical decision support systems for more effective treatment selection.

Taking modern psychiatry into the metaverse: Integrating augmented, virtual, and mixed reality technologies into psychiatric care

The landscape of psychiatry is ever evolving and has recently begun to be influenced more heavily by new technologies. One novel technology which may have particular application to psychiatry is the metaverse, a three-dimensional digital social platform accessed via augmented, virtual, and mixed reality (AR/VR/MR). The metaverse allows the interaction of users in a virtual world which can be measured and manipulated, posing at once exciting new possibilities and significant potential challenges and risks. While the final form of the nascent metaverse is not yet clear, the immersive simulation and holographic mixed reality-based worlds made possible by the metaverse have the potential to redefine neuropsychiatric care for both patients and their providers. While a number of applications for this technology can be envisioned, this article will focus on leveraging the metaverse in three specific domains: medical education, brain stimulation, and biofeedback. Within medical education, the metaverse could allow for more precise feedback to students performing patient interviews as well as the ability to more easily disseminate highly specialized technical skills, such as those used in advanced neurostimulation paradigms. Examples of potential applications in brain stimulation and biofeedback range from using AR to improve precision targeting of non-invasive neuromodulation modalities to more innovative practices, such as using physiological and behavioral measures derived from interactions in VR environments to directly inform and personalize treatment parameters for patients. Along with promising future applications, we also discuss ethical implications and data security concerns that arise when considering the introduction of the metaverse and related AR/VR technologies to psychiatric research and care.

A systematic meta-review of patient-level predictors of psychological therapy outcome in major depressive disorder

BACKGROUND

Psychological therapies are effective for treating major depressive disorder, but current clinical guidelines do not provide guidance on the personalization of treatment choice. Established predictors of psychotherapy treatment response could help inform machine learning models aimed at predicting individual patient responses to different therapy options. Here we sought to comprehensively identify known predictors.

METHODS

EMBASE, Medline, PubMed, PsycINFO were searched for systematic reviews with or without meta-analysis published until June 2020 to identify individual patient-level predictors of response to psychological treatments. 3113 abstracts were identified and 300 articles assessed. We qualitatively synthesized our findings by predictor category (sociodemographic; symptom profile; social support; personality features; affective, cognitive, and behavioural; comorbidities; neuroimaging; genetics) and treatment type. We used the AMSTAR 2 to evaluate the quality of included reviews.

RESULTS

Following screening and full-text assessment, 27 systematic reviews including 12 meta-analyses were eligible for inclusion. 74 predictors emerged for various psychological treatments, primarily cognitive behavioural therapy, interpersonal therapy, and mindfulness-based cognitive therapy.

LIMITATIONS

A paucity of studies examining predictors of psychological treatment outcome, as well as methodological heterogeneities and publication biases limit the strength of the identified predictors.

CONCLUSIONS

The synthesized predictors could be used to supplement clinical decision-making in selecting psychological therapies based on individual patient characteristics. These predictors could also be used as a priori input features for machine learning models aimed at predicting a given patient's likelihood of response to different treatment options for depression, and may contribute toward the development of patient-specific treatment recommendations in clinical guidelines.

A Promising Approach to Optimizing Sequential Treatment Decisions for Depression: Markov Decision Process

The most appropriate next step in depression treatment after the initial treatment fails is unclear. This study explores the suitability of the Markov decision process for optimizing sequential treatment decisions for depression. We conducted a formal comparison of a Markov decision process approach and mainstream state-transition models as used in health economic decision analysis to clarify differences in the model structure. We performed two reviews: the first to identify existing applications of the Markov decision process in the field of healthcare and the second to identify existing health economic models for depression. We then illustrated the application of a Markov decision process by reformulating an existing health economic model. This provided input for discussing the suitability of a Markov decision process for solving sequential treatment decisions in depression. The Markov decision process and state-transition models differed in terms of flexibility in modeling actions and rewards. In all, 23 applications of a Markov decision process within the context of somatic disease were included, 16 of which concerned sequential treatment decisions. Most existing health economic models relating to depression have a state-transition structure. The example application replicated the health economic model and enabled additional capacity to make dynamic comparisons of more interventions over time than was possible with traditional state-transition models. Markov decision processes have been successfully applied to address sequential treatment-decision problems, although the results have been published mostly in economics journals that are not related to healthcare. One advantage of a Markov decision process compared with state-transition models is that it allows extended action space: the possibility of making dynamic comparisons of different treatments over time. Within the context of depression, although existing state-transition models are too basic to evaluate sequential treatment decisions, the assumptions of a Markov decision process could be satisfied. The Markov decision process could therefore serve as a powerful model for optimizing sequential treatment in depression. This would require a sufficiently elaborate state-transition model at the cohort or patient level.

Evaluating the Clinical Feasibility of an Artificial Intelligence-Powered, Web-Based Clinical Decision Support System for the Treatment of Depression in Adults: Longitudinal Feasibility Study

BACKGROUND

Approximately two-thirds of patients with major depressive disorder do not achieve remission during their first treatment. There has been increasing interest in the use of digital, artificial intelligence-powered clinical decision support systems (CDSSs) to assist physicians in their treatment selection and management, improving the personalization and use of best practices such as measurement-based care. Previous literature shows that for digital mental health tools to be successful, the tool must be easy for patients and physicians to use and feasible within existing clinical workflows.

OBJECTIVE

This study aims to examine the feasibility of an artificial intelligence-powered CDSS, which combines the operationalized 2016 Canadian Network for Mood and Anxiety Treatments guidelines with a neural network-based individualized treatment remission prediction.

METHODS

Owing to the COVID-19 pandemic, the study was adapted to be completed entirely remotely. A total of 7 physicians recruited outpatients diagnosed with major depressive disorder according to the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition criteria. Patients completed a minimum of one visit without the CDSS (baseline) and 2 subsequent visits where the CDSS was used by the physician (visits 1 and 2). The primary outcome of interest was change in appointment length after the introduction of the CDSS as a proxy for feasibility. Feasibility and acceptability data were collected through self-report questionnaires and semistructured interviews.

RESULTS

Data were collected between January and November 2020. A total of 17 patients were enrolled in the study; of the 17 patients, 14 (82%) completed the study. There was no significant difference in appointment length between visits (introduction of the tool did not increase appointment length; F2,24=0.805; mean squared error 58.08; P=.46). In total, 92% (12/13) of patients and 71% (5/7) of physicians felt that the tool was easy to use; 62% (8/13) of patients and 71% (5/7) of physicians rated that they trusted the CDSS. Of the 13 patients, 6 (46%) felt that the patient-clinician relationship significantly or somewhat improved, whereas 7 (54%) felt that it did not change.

CONCLUSIONS

Our findings confirm that the integration of the tool does not significantly increase appointment length and suggest that the CDSS is easy to use and may have positive effects on the patient-physician relationship for some patients. The CDSS is feasible and ready for effectiveness studies.

TRIAL REGISTRATION

ClinicalTrials.gov NCT04061642; http://clinicaltrials.gov/ct2/show/NCT04061642.

Using a simulation centre to evaluate preliminary acceptability and impact of an artificial intelligence-powered clinical decision support system for depression treatment on the physician-patient interaction

BACKGROUND

Recently, artificial intelligence-powered devices have been put forward as potentially powerful tools for the improvement of mental healthcare. An important question is how these devices impact the physician-patient interaction.

AIMS

Aifred is an artificial intelligence-powered clinical decision support system (CDSS) for the treatment of major depression. Here, we explore the use of a simulation centre environment in evaluating the usability of Aifred, particularly its impact on the physician-patient interaction.

METHOD

Twenty psychiatry and family medicine attending staff and residents were recruited to complete a 2.5-h study at a clinical interaction simulation centre with standardised patients. Each physician had the option of using the CDSS to inform their treatment choice in three 10-min clinical scenarios with standardised patients portraying mild, moderate and severe episodes of major depression. Feasibility and acceptability data were collected through self-report questionnaires, scenario observations, interviews and standardised patient feedback.

RESULTS

All 20 participants completed the study. Initial results indicate that the tool was acceptable to clinicians and feasible for use during clinical encounters. Clinicians indicated a willingness to use the tool in real clinical practice, a significant degree of trust in the system's predictions to assist with treatment selection, and reported that the tool helped increase patient understanding of and trust in treatment. The simulation environment allowed for the evaluation of the tool's impact on the physician-patient interaction.

CONCLUSIONS

The simulation centre allowed for direct observations of clinician use and impact of the tool on the clinician-patient interaction before clinical studies. It may therefore offer a useful and important environment in the early testing of new technological tools. The present results will inform further tool development and clinician training materials.