Common and specific determinants of 9-year depression and anxiety course-trajectories: A machine-learning investigation in the Netherlands Study of Depression and Anxiety (NESDA).

Klaas J Wardenaar,Harriëtte Riese,Erik J Giltay,Merijn Eikelenboom,Albert J Van Hemert,Aartjan F Beekman,Brenda W.J.H Penninx,Robert A Schoevers

doi:10.1016/j.jad.2021.06.029

Abstract

Background: Given the strong relationship between depression and anxiety, there is an urge to investigate their shared and specific long-term course determinants. The current study aimed to identify and compare the main determinants of the 9-year trajectories of combined and pure depression and anxiety symptom severity.Methods: Respondents with a 6-month depression and/or anxiety diagnosis (n=1,701) provided baseline data on 152 sociodemographic, clinical and biological variables. Depression and anxiety symptom severity assessed at baseline, 2-, 4-, 6- and 9-year follow-up, were used to identify data-driven course-trajectory subgroups for general psychological distress, pure depression, and pure anxiety severity scores. For each outcome (class-probability), a Superlearner (SL) algorithm identified an optimally weighted (minimum mean squared error) combination of machine-learning prediction algorithms. For each outcome, the top determinants in the SL were identified by determining variable-importance and correlations between each SL-predicted and observed outcome (ρpred) were calculated.Results: Low to high prediction correlations (ρpred: 0.41-0.91, median=0.73) were found. In the SL, important determinants of psychological distress were age, young age of onset, respiratory rate, participation disability, somatic disease, low income, minor depressive disorder and mastery score. For course of pure depression and anxiety symptom severity, similar determinants were found. Specific determinants of pure depression included several types of healthcare-use, and of pure-anxiety course included somatic arousal and psychological distress.Limitations: Limited sample size for machine learning.Conclusions: The determinants of depression- and anxiety-severity course are mostly shared. Domain-specific exceptions are healthcare use for depression and somatic arousal and distress for anxiety-severity course.

Highlights

Both depression and anxiety generally follow chronic-intermittent course-trajectories (Verduijn et al, 2017) but considerable course het erogeneity exists (Musliner et al, 2016)
Prospective studies of long-term (≥6 years) depression course indicate that patients can have recurrent episodes (Brodaty et al, 2001; Kennedy et al, 2003), never reach full remission (e.g., Angst & Volrath, 1991; Angst, 1996; Keller et al, 1992; Piccinelli & Wilkinson, 1994; Chen et al, 2000) or have persistent residual symptoms (Judd et al, 1998; Kennedy et al, 2004; Rhebergen et al, 2011), all of which is associated with higher costs (McIntyre & O’Donovan, 2004), healthcare use (e.g., Pettit et al, 2009) and impairments (e.g., Judd et al, 2000a;(Fichter et al, 2008)
Pro spective studies of long-term anxiety course have shown high persistence over time (Cowley et al, 1996; Bruce et al, 2005; Keller, 2002; 2003; Wittchen & Fehm, 2003; Katschnig & Amering, 1998), anxiety-disorder diagnoses may change over time (Hov enkamp-Hermelink et al, 2016)

Summary

Introduction

Both depression and anxiety generally follow chronic-intermittent course-trajectories (Verduijn et al, 2017) but considerable course het erogeneity exists (Musliner et al, 2016). Depression and anxiety disorders co-occur (e.g., Clark & Watson, 1991), which is associated with a less favourable course (e.g., Bruce et al, 2005; Rhebergen et al, 2011) Both for clinical and public-health purposes, identifying the baseline determinants of the long-term course of depression and anxiety is of strong interest. Prospective studies have shown that baseline clinical characteristics such as comorbidity (Coryell et al, 2012), severity, number of previous episodes (Steinert et al, 2014), residual symptoms (Judd et al, 2000b), psychosis (Coryell et al, 1996), suicidality (Moos & Cronkite, 1999), as well as psychological characteristics (Surtees & Wainwright, 1996, Struijs et al, 2018; Hovenkamp-Hermelink et al, 2019) are associated with increased risk of long-term chronicity and/or recurrences. The current study aimed to identify and compare the main determinants of the 9-year trajectories of combined and pure depression and anxiety symptom severity

Objectives

Methods

Results

Conclusion