Treatment response classes in major depressive disorder identified by model-based clustering and validated by clinical prediction models

Abstract

The identification of generalizable treatment response classes (TRC[s]) in major depressive disorder (MDD) would facilitate comparisons across studies and the development of treatment prediction algorithms. Here, we investigated whether such stable TRCs can be identified and predicted by clinical baseline items. We analyzed data from an observational MDD cohort (Munich Antidepressant Response Signature [MARS] study, N = 1017), treated individually by psychopharmacological and psychotherapeutic means, and a multicenter, partially randomized clinical/pharmacogenomic study (Genome-based Therapeutic Drugs for Depression [GENDEP], N = 809). Symptoms were evaluated up to week 16 (or discharge) in MARS and week 12 in GENDEP. Clustering was performed on 809 MARS patients (discovery sample) using a mixed model with the integrated completed likelihood criterion for the assessment of cluster stability, and validated through a distinct MARS validation sample and GENDEP. A random forest algorithm was used to identify prediction patterns based on 50 clinical baseline items. From the clustering of the MARS discovery sample, seven TRCs emerged ranging from fast and complete response (average 4.9 weeks until discharge, 94% remitted patients) to slow and incomplete response (10% remitted patients at week 16). These proved stable representations of treatment response dynamics in both the MARS and the GENDEP validation sample. TRCs were strongly associated with established response markers, particularly the rate of remitted patients at discharge. TRCs were predictable from clinical items, particularly personality items, life events, episode duration, and specific psychopathological features. Prediction accuracy improved significantly when cluster-derived slopes were modelled instead of individual slopes. In conclusion, model-based clustering identified distinct and clinically meaningful treatment response classes in MDD that proved robust with regard to capturing response profiles of differently designed studies. Response classes were predictable from clinical baseline characteristics. Conceptually, model-based clustering is translatable to any outcome measure and could advance the large-scale integration of studies on treatment efficacy or the neurobiology of treatment response.

The promise of machine learning in predicting treatment outcomes in psychiatry

“…Machine learning models were then developed to try and predict the specific response tra jectory a patient will have for a given treatment. This approach is potentially more robust to the noise that is naturally present amongst individual patient trajectories and less affected by the way that outcomes are defined in trials -e.g., whether remission is defined as a score of 5 on the Patient Health Questionnaire9 (PHQ9) or a score of 5 or 6 on the Quick Inventory of Depressive Symptomatology (QIDS) 48,49 . However, the approach relies on the availability of repeated measures.…”

“…Other researchers first used techniques like growth mixture modeling 48 or finite mixture modeling 49 to identify trajectories of symptom response such as “fast and stable remitter”, “sustained response”, or “late relapse”. Machine learning models were then developed to try and predict the specific response trajectory a patient will have for a given treatment.…”

Antidepressant activity of rose oxide essential oil: possible involvement of serotonergic transmission

“…Despite advances in the treatment of depression, the medications used promote several common adverse effects like nausea, sexual dysfunction, headache, insomnia, daytime drowsiness, restlessness and weight loss ( Alexopoulos, 2019 ; Kraus et al., 2019 ; Paul et al., 2019 ). The occurrence of these adverse effects may lead to withdrawal of pharmacological treatment ( Huang et al., 2018 ).…”

Optimising treatment decision rules through generated effect modifiers: a precision medicine tutorial

“…It is quite possible that the two treatments might be equally effective on average, but each one might be preferred for a different subset of patients. From clinical trials data, identifying subgroups of patients with differential treatment response classes (for example responder and non-responder classes) can often be achieved through a latent class or latent growth analysis, 8–11 by identifying biomarkers related to these response classes from patients' baseline predictors, or based on clustering. 12 In contrast, the GEM utilises an underlying outcome model of form (1), with the focus of estimating a composite treatment effect modifier z from baseline predictors.…”