What little we know about tailoring depression treatment for individual patients

Biomarker-based subtyping of depression and anxiety disorders using Latent Class Analysis. A NESDA study

BACKGROUND

Etiological research of depression and anxiety disorders has been hampered by diagnostic heterogeneity. In order to address this, researchers have tried to identify more homogeneous patient subgroups. This work has predominantly focused on explaining interpersonal heterogeneity based on clinical features (i.e. symptom profiles). However, to explain interpersonal variations in underlying pathophysiological mechanisms, it might be more effective to take biological heterogeneity as the point of departure when trying to identify subgroups. Therefore, this study aimed to identify data-driven subgroups of patients based on biomarker profiles.

METHODS

Data of patients with a current depressive and/or anxiety disorder came from the Netherlands Study of Depression and Anxiety, a large, multi-site naturalistic cohort study (n = 1460). Thirty-six biomarkers (e.g. leptin, brain-derived neurotrophic factor, tryptophan) were measured, as well as sociodemographic and clinical characteristics. Latent class analysis of the discretized (lower 10%, middle, upper 10%) biomarkers were used to identify different patient clusters.

RESULTS

The analyses resulted in three classes, which were primarily characterized by different levels of metabolic health: 'lean' (21.6%), 'average' (62.2%) and 'overweight' (16.2%). Inspection of the classes' clinical features showed the highest levels of psychopathology, severity and medication use in the overweight class.

CONCLUSIONS

The identified classes were strongly tied to general (metabolic) health, and did not reflect any natural cutoffs along the lines of the traditional diagnostic classifications. Our analyses suggested that especially poor metabolic health could be seen as a distal marker for depression and anxiety, suggesting a relationship between the 'overweight' subtype and internalizing psychopathology.

A systematic meta-review of predictors of antidepressant treatment outcome in major depressive disorder

INTRODUCTION

The heterogeneity of symptoms and complex etiology of depression pose a significant challenge to the personalization of treatment. Meanwhile, the current application of generic treatment approaches to patients with vastly differing biological and clinical profiles is far from optimal. Here, we conduct a meta-review to identify predictors of response to antidepressant therapy in order to select robust input features for machine learning models of treatment response. These machine learning models will allow us to learn associations between patient features and treatment response which have predictive value at the individual patient level; this learning can be optimized by selecting high-quality input features for the model. While current research is difficult to directly apply to the clinic, machine learning models built using knowledge gleaned from current research may become useful clinical tools.

METHODS

The EMBASE and MEDLINE/PubMed online databases were searched from January 1996 to August 2017, using a combination of MeSH terms and keywords to identify relevant literature reviews. We identified a total of 1909 articles, wherein 199 articles met our inclusion criteria.

RESULTS

An array of genetic, immune, endocrine, neuroimaging, sociodemographic, and symptom-based predictors of treatment response were extracted, varying widely in clinical utility.

LIMITATIONS

Due to heterogeneous sample sizes, effect sizes, publication biases, and methodological disparities across reviews, we could not accurately assess the strength and directionality of every predictor.

CONCLUSION

Notwithstanding our cautious interpretation of the results, we have identified a multitude of predictors that can be used to formulate a priori hypotheses regarding the input features for a computational model. We highlight the importance of large-scale research initiatives and clinically accessible biomarkers, as well as the need for replication studies of current findings. In addition, we provide recommendations for future improvement and standardization of research efforts in this field.