Integrating proteomic, sociodemographic and clinical data to predict future depression diagnosis in subthreshold symptomatic individuals

Sung Yeon Sarah Han,Sabine Bahn,Jason D Cooper,Brenda W.J.H Penninx,Nitin Rustogi,Sureyya Ozcan

doi:10.1038/s41398-019-0623-2

Abstract

Individuals with subthreshold depression have an increased risk of developing major depressive disorder (MDD). The aim of this study was to develop a prediction model to predict the probability of MDD onset in subthreshold individuals, based on their proteomic, sociodemographic and clinical data. To this end, we analysed 198 features (146 peptides representing 77 serum proteins (measured using MRM-MS), 22 sociodemographic factors and 30 clinical features) in 86 first-episode MDD patients (training set patient group), 37 subthreshold individuals who developed MDD within two or four years (extrapolation test set patient group), and 86 subthreshold individuals who did not develop MDD within four years (shared reference group). To ensure the development of a robust and reproducible model, we applied feature extraction and model averaging across a set of 100 models obtained from repeated application of group LASSO regression with ten-fold cross-validation on the training set. This resulted in a 12-feature prediction model consisting of six serum proteins (AACT, APOE, APOH, FETUA, HBA and PHLD), three sociodemographic factors (body mass index, childhood trauma and education level) and three depressive symptoms (sadness, fatigue and leaden paralysis). Importantly, the model demonstrated a fair performance in predicting future MDD diagnosis of subthreshold individuals in the extrapolation test set (AUC = 0.75), which involved going beyond the scope of the model. These findings suggest that it may be possible to detect disease indications in subthreshold individuals up to four years prior to diagnosis, which has important clinical implications regarding the identification and treatment of high-risk individuals.

Highlights

Major depressive disorder (MDD) is a complex and burdensome disorder that is characterised by low mood and energy levels, as well as concentration problems, sleep disturbances and changes in weight and appetite[1,2]
To identify early biomarkers or indicators of MDD, we would ideally test for differences between subthreshold individuals who later developed and did not develop MDD; as the number of subthreshold individuals who developed MDD was limited, we first trained the model to differentiate between 86 subthreshold individuals who had no current or lifetime diagnosis of MDD at the baseline assessment and did not develop MDD by the fourth-year follow-up assessment and 86 recent-onset MDD patients who experienced their first and only major depressive episode within a month before the baseline assessment
In this study, we evaluated the accuracy with which future onset of MDD could be predicted in subthreshold symptomatic individuals by extrapolating a disease

Summary

Introduction

Major depressive disorder (MDD) is a complex and burdensome disorder that is characterised by low mood and energy levels, as well as concentration problems, sleep disturbances and changes in weight and appetite[1,2]. While subthreshold depression has been identified as a risk factor for developing MDD in the future[13,16,17,18], there is growing evidence that targeting subthreshold individuals with indicated preventive interventions can help to prevent or delay the onset of MDD19,20. This highlights the clinical importance of finding early manifestations or biomarkers of incident MDD in subthreshold individuals, which could be used to identify those who will benefit most from appropriate preventive interventions. And more accurate detection of MDD is essential for reducing the disease burden and the related healthcare costs

Objectives

Methods

Results

Conclusion