Identifying relapse predictors in individual participant data with decision trees.

BACKGROUND: Depression is a highly common and recurrent condition. Predicting who is at most risk of relapse or recurrence can inform clinical practice. Applying machine-learning methods to Individual Participant Data (IPD) can be promising to improve the accuracy of risk predictions. METHODS: Individual data of four Randomized Controlled Trials (RCTs) evaluating antidepressant treatment compared to psychological interventions with tapering ([Formula: see text]) were used to identify predictors of relapse and/or recurrence. Ten baseline predictors were assessed. Decision trees with and without gradient boosting were applied. To study the robustness of decision-tree classifications, we also performed a complementary logistic regression analysis. RESULTS: The combination of age, age of onset of depression, and depression severity significantly enhances the prediction of relapse risk when compared to classifiers solely based on depression severity. The studied decision trees can (i) identify relapse patients at intake with an accuracy, specificity, and sensitivity of about 55% (without gradient boosting) and 58% (with gradient boosting), and (ii) slightly outperform classifiers that are based on logistic regression. CONCLUSIONS: Decision tree classifiers based on multiple-rather than single-risk indicators may be useful for developing treatment stratification strategies. These classification models have the potential to contribute to the development of methods aimed at effectively prioritizing treatment for those individuals who require it the most. Our results also underline the existing gaps in understanding how to accurately predict depressive relapse.

Effectiveness and Cost-effectiveness of Online Brief Mindfulness-based Cognitive Therapy for the Improvement of Productivity in the Workplace: Study Protocol for a Randomized Controlled Trial.

BACKGROUND: Numerous studies have demonstrated the effectiveness of mindfulness-based programs (MBPs) among both clinical and nonclinical populations. These data document positive impacts in the workplace, including reducing perceived stress and burnout and increasing well-being. However, the effectiveness for productivity, which is of most interest to managers and administrators, is still unclear. In addition, MBPs in the workplace tend to be modified by reducing the number of the program sessions or delivering content online to improve accessibility. To date, however, the impact of MBPs that feature these modifications on productivity in the workplace has not been investigated. OBJECTIVE: The study aims to investigate the effectiveness and cost-effectiveness of online-delivered brief mindfulness-based cognitive therapy (bMBCT) for improving productivity and other work-related outcomes among healthy workers compared to the waitlist control. METHODS: We will conduct a 4-week randomized controlled trial (RCT) with a 6-month follow-up. Employees are included in the study if they (1) are between the ages of 20 and 65 years and (2) work longer than 30 hours weekly. Employees are randomly allocated to either the bMBCT group or the waitlist control group. The primary outcome of the study is the mean difference of productivity measured by the World Health Organization Health and Work Performance Questionnaire (WHO-HPQ) between the groups at 4, 16, and 28 weeks. Secondary outcomes include several clinical outcomes and health economics evaluation. RESULTS: We started recruiting participants in August 2021, and the intervention began in October 2021. A total of 104 participants have been enrolled in the study as of October 2021. The intervention is scheduled to be completed in December 2023. Data collection will be completed by the end of January 2024. CONCLUSIONS: The novelty of the study is that (1) it will investigate bMBCT's effectiveness on productivity, which is still unclear, and (2) samples are recruited from 3 companies in different industries. The limitations of the study are that (1) all measures assessed are in self-report format and (2) we lack an active control group. This study has the potential to provide new data on the relationship between MBPs and occupational health and productivity. TRIAL REGISTRATION: University Hospital Medical Information Network Clinical Trials Registry UMIN000044721; https://tinyurl.com/4e2fh873. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/36012.

Cost-Effectiveness of a Web-Based Program for Residual Depressive Symptoms: Mindful Mood Balance.

OBJECTIVE: Mindful Mood Balance (MMB) is an effective Web-based program for residual depressive symptoms that prevents relapse among patients with partial recovery from major depressive episodes. This cost-effectiveness analysis was conducted from the health plan perspective alongside a pragmatic randomized controlled trial of MMB. METHODS: Adults were recruited from behavioral health and primary care settings in a large integrated health system and randomly assigned to MMB plus usual depression care (MMB+UDC) or UDC. Patients had at least one prior major depressive episode; a current score of 5-9 on the Patient Health Questionnaire-9, indicating residual depressive symptoms; and Internet access. Program costs included recruitment, coaching, and MMB licensing. Center for Medicare and Medicaid fee schedules were applied to electronic health record utilization data for psychotropic medications and psychiatric and psychotherapy visits. Effectiveness was measured as depression-free days (DFDs), converted from PHQ-9 scores collected monthly for 1 year. Incremental cost-effectiveness ratios were calculated with various sets of cost inputs. RESULTS: A total of 389 patients (UDC, N=210; MMB+UDC, N=179) had adequate follow-up PHQ-9 measures for inclusion. MMB+UDC patients had 29 more DFDs during follow-up. Overall, the incremental cost of MMB+UDC was $431.54 over 12 months. Incremental costs per DFD gained ranged from $9.63 for program costs only to $15.04 when psychiatric visits, psychotherapy visits, and psychotropic medications were included. CONCLUSIONS: MMB offers a cost-effective Web-based program for reducing residual depressive symptoms and preventing relapse. Health systems should consider adopting MMB as adjunctive to traditional mental health care services.

Cost-Utility Analysis of Mindfulness-Based Cognitive Therapy Versus Antidepressant Pharmacotherapy for Prevention of Depressive Relapse in a Canadian Context: Analyse coût-utilité de la thérapie cognitive basée sur la pleine conscience contre la pharmacothérapie antidépressive pour prévenir la rechute de la dépression en contexte canadien.

OBJECTIVE: Patients suffering from major depressive disorder (MDD) experience impaired functioning and reduced quality of life, including an elevated risk of episode return. MDD is associated with high societal burden due to increased healthcare utilization, productivity losses, and suicide-related costs, making the long-term management of this illness a priority. The purpose of this study is to evaluate the cost-effectiveness of mindfulness-based cognitive therapy (MBCT), a first-line preventative psychological treatment, compared to maintenance antidepressant medication (ADM), the current standard of care. METHOD: A cost-utility analysis was conducted over a 24-month time horizon to model differences between MBCT and ADM in cost and quality-adjusted life years (QALY). The analysis was conducted using a decision tree analytic model. Intervention efficacy, utility, and costing data estimates were derived from published sources and expert consultation. RESULTS: MBCT was found to be cost-effective compared to maintenance ADM over a 24-month time horizon. Antidepressant pharmacotherapy resulted in 1.10 QALY and $17,255.37 per patient on average, whereas MBCT resulted in 1.18 QALY and $15,030.70 per patient on average. This resulted in a cost difference of $2,224.67 and a QALY difference of 0.08, in favor of MBCT. Multiple sensitivity analyses supported these findings. CONCLUSIONS: From both a societal and health system perspective, utilizing MBCT as a first-line relapse prevention treatment is potentially cost-effective in a Canadian setting. Future economic evaluations should consider combined treatment (e.g., ADM and psychotherapy) as a comparator and longer time horizons as the literature advances.