Applying deep neural networks to unstructured text notes in electronic medical records for phenotyping youth depression.

BACKGROUND: We report a study of machine learning applied to the phenotyping of psychiatric diagnosis for research recruitment in youth depression, conducted with 861 labelled electronic medical records (EMRs) documents. A model was built that could accurately identify individuals who were suitable candidates for a study on youth depression. OBJECTIVE: Our objective was a model to identify individuals who meet inclusion criteria as well as unsuitable patients who would require exclusion. METHODS: Our methods included applying a system that coded the EMR documents by removing personally identifying information, using two psychiatrists who labelled a set of EMR documents (from which the 861 came), using a brute force search and training a deep neural network for this task. FINDINGS: According to a cross-validation evaluation, we describe a model that had a specificity of 97% and a sensitivity of 45% and a second model with a specificity of 53% and a sensitivity of 89%. We combined these two models into a third one (sensitivity 93.5%; specificity 68%; positive predictive value (precision) 77%) to generate a list of most suitable candidates in support of research recruitment. CONCLUSION: Our efforts are meant to demonstrate the potential for this type of approach for patient recruitment purposes but it should be noted that a larger sample size is required to build a truly reliable recommendation system. CLINICAL IMPLICATIONS: Future efforts will employ alternate neural network algorithms available and other machine learning methods.

Cognitive Behavior Therapy for Anxious and Depressed Youth: Improving Homework Adherence Through Mobile Technology.

BACKGROUND: Anxiety and mood disorders are the most common mental illnesses, peaking during adolescence and affecting approximately 25% of Canadians aged 14-17 years. If not successfully treated at this age, they often persist into adulthood, exerting a great social and economic toll. Given the long-term impact, finding ways to increase the success and cost-effectiveness of mental health care is a pressing need. Cognitive behavior therapy (CBT) is an evidence-based treatment for mood and anxiety disorders throughout the lifespan. Mental health technologies can be used to make such treatments more successful by delivering them in a format that increases utilization. Young people embrace technologies, and many want to actively manage their mental health. Mobile software apps have the potential to improve youth adherence to CBT and, in turn, improve outcomes of treatment. OBJECTIVE: The purpose of this project is to improve homework adherence in CBT for youth anxiety and/or depression. The objectives are to (1) design and optimize the usability of a mobile app for delivering the homework component of CBT for youth with anxiety and/or depression, (2) assess the app's impact on homework completion, and (3) implement the app in CBT programs. We hypothesize that homework adherence will be greater in the app group than in the no-app group. METHODS: Phase 1: exploratory interviews will be conducted with adolescents and therapists familiar with CBT to obtain views and perspectives on the requirements and features of a usable app and the challenges involved in implementation. The information obtained will guide the design of a prototype. The prototype will be optimized via think-aloud procedures involving an iterative process of evaluation, modification, and re-evaluation, culminating in a fully functional version of the prototype that is ready for optimization in a clinical context. Phase 2: a usability study will be conducted to optimize the prototype in the context of treatment at clinics that provide CBT treatment for youth with anxiety and/or depression. This phase will result in a usable app that is ready to be tested for its effectiveness in increasing homework adherence. Phase 3: a pragmatic clinical trial will be conducted at several clinics to evaluate the impact of the app on homework adherence. Participants in the app group are expected to show greater homework completion than those in the no-app group. RESULTS: Phase 3 will be completed by September 2019. CONCLUSIONS: The app will be a unique adjunct to treatment for adolescents in CBT, focusing on both anxiety and depression, developed in partnership with end users at every stage from design to implementation, customizable for different cognitive profiles, and designed with depression symptom tracking measures for youth made interoperable with electronic medical records.

Treating child and adolescent anxiety effectively: Overview of systematic reviews.

We conducted an overview of systematic reviews about child and adolescent anxiety treatment options (psychosocial; medication; combination; web/computer-based treatment) to support evidence informed decision-making. Three questions were addressed: (i) Is the treatment more effective than passive controls? (ii) Is there evidence that the treatment is superior to or non-inferior to (i.e., as good as) active controls? (iii) What is the quality of evidence for the treatment? Pre-specified inclusion criteria identified high quality systematic reviews (2000-2015) reporting treatment effects on anxiety diagnosis and symptom severity. Evidence quality (EQ) was rated using Oxford evidence levels [EQ1 (highest); EQ5 (lowest)]. Twenty-two of 39 eligible reviews were high quality (AMSTAR score≥3/5). CBT (individual or group, with or without parents) was more effective than passive controls (EQ1). CBT effects compared to active controls were mixed (EQ1). SSRI/SNRI were more effective than placebo (EQ1) but comparative effectiveness remains uncertain. EQ for combination therapy could not be determined. RCTs of web/computer-based interventions showed mixed results (EQ1). CBM/ABM was not more efficacious than active controls (EQ1). No other interventions could be rated. High quality RCTs support treatment with CBT and medication. Findings for combination and web/computer-based treatment are encouraging but further RCTs are required. Head-to-head comparisons of active treatment options are needed.

PREVENTING CHILD AND ADOLESCENT ANXIETY DISORDERS: OVERVIEW OF SYSTEMATIC REVIEWS.

Overviews of systematic reviews (OSRs) provide rapid access to high quality, consolidated research evidence about prevention intervention options, supporting evidence-informed decision-making, and the identification of fruitful areas of new research. This OSR addressed three questions about prevention strategies for child and adolescent anxiety: (1) Does the intervention prevent anxiety diagnosis and/or reduce anxiety symptoms compared to passive controls? (2) Is the intervention equal to or more effective than active controls? (3) What is the evidence quality (EQ) for the intervention? Prespecified inclusion criteria identified systematic reviews and meta-analyses (2000-2014) with an AMSTAR quality score ≥ 3/5. EQ was rated using Oxford evidence levels EQ1 (highest) to EQ5 (lowest). Three reviews met inclusion criteria. One narrative systematic review concluded school-based interventions reduce anxiety symptoms. One meta-analysis pooled 65 randomized controlled trials (RCTs; any intervention) and reported a small, statistically significant reduction in anxiety symptoms and diagnosis incidence. Neither review provided pooled effect size estimates for specific intervention options defined by type (i.e., universal/selective/indicated), intervention content, or comparison group (i.e., passive/active control), thus precluding EQ ratings. One meta-analysis pooled trials of vigorous exercise and reported small, nonstatistically significant reductions in anxiety symptoms for comparisons against passive and active controls (EQ1). Better use of primary studies in meta-analyses, including program-specific pooled effect size estimates and network meta-analysis is needed to guide evidence-informed anxiety prevention program choices. RCTs of innovative community/primary care based interventions and web-based strategies can fill knowledge gaps.

Telemedicine as a tool to mitigate cardiometabolic risk associated with serious mental illness.

People with serious mental illness suffer from substantially higher rates of cardiometabolic morbidity and mortality than the general population. We have evaluated the efficacy of telemedicine for providing cardiometabolic risk management services compared to in-person care. A retrospective chart review was conducted in order to compare changes in body mass index (BMI), systolic blood pressure and serum triglycerides before and after telemedicine (n=38). The comparator group (n=38) was selected from a list of all clients who had a conventional appointment at the metabolic clinic. Analysis of Variance showed an overall effect of treatment on BMI (P<0.001), but no significant differences between the groups on BMI (P=0.89), systolic blood pressure (P=0.62) or fasting serum triglycerides (P=0.81). This suggests that telemedicine may be as effective as in-person care and that telemedicine has the potential to improve access to cardiometabolic risk management services for people with serious mental illness.

Types of parental involvement in CBT with anxious youth: a preliminary meta-analysis.

OBJECTIVE: Meta-analytic studies have not confirmed that involving parents in cognitive behavior therapy (CBT) for anxious children is therapeutically beneficial. There is also great heterogeneity in the type of parental involvement included. We investigated parental involvement focused on contingency management (CM) and transfer of control (TC) as a potential outcome moderator using a meta-analysis with individual patient data. METHOD: Investigators of randomized controlled trials (RCTs) of CBT for anxious children, identified systematically, were invited to submit their data. Conditions in each RCT were coded based on type of parental involvement in CBT (i.e., low involvement, active involvement without emphasis on CM or TC, active involvement with emphasis on CM or TC). Treatment outcomes were compared using a 1-stage meta-analysis. RESULTS: All cases involved in active treatment (894 of 1,618) were included for subgroup analyses. Across all CBT groups, means of clinical severity, anxiety, and internalizing symptoms significantly decreased posttreatment and were comparable across groups. The group without emphasis on CM or TC showed a higher proportion with posttreatment anxiety diagnoses than the low-involvement group. Between posttreatment and 1-year follow-up, the proportion with anxiety diagnoses significantly decreased in CBT with active parental involvement with emphasis on CM or TC, whereas treatment gains were merely maintained in the other 2 groups. CONCLUSIONS: CBT for anxious children is an effective treatment with or without active parental involvement. However, CBT with active parental involvement emphasizing CM or TC may support long-term maintenance of treatment gains. RESULTS should be replicated as additional RCTs are published.