Brain Age Is Not a Significant Predictor of Relapse Risk in Late-Life Depression

Abstract

BackgroundLate-life depression (LLD) has been associated cross-sectionally with lower brain structural volumes and accelerated brain aging compared with healthy control participants (HCs). There are few longitudinal studies on the neurobiological predictors of recurrence in LLD. We tested a machine learning brain age model and its prospective association with LLD recurrence risk. MethodsWe recruited individuals with LLD (n = 102) and HCs (n = 43) into a multisite, 2-year longitudinal study. Individuals with LLD were enrolled within 4 months of remission. Remitted participants with LLD underwent baseline neuroimaging and longitudinal clinical follow-up. Over 2 years, 43 participants with LLD relapsed and 59 stayed in remission. We used a previously developed machine learning brain age algorithm to compute brain age at baseline, and we evaluated brain age group differences (HC vs. LLD and HC vs. remitted LLD vs. relapsed LLD). We conducted a Cox proportional hazards model to evaluate whether baseline brain age predicted time to relapse. ResultsWe found that brain age did not significantly differ between the HC and LLD groups or between the HC, remitted LLD, and relapsed LLD groups. Brain age did not significantly predict time to relapse. ConclusionsIn contrast to our hypothesis, we found that brain age did not differ between control participants without depression and individuals with remitted LLD, and brain age was not associated with subsequent recurrence. This is in contrast to existing literature which has identified baseline brain age differences in late life but consistent with work that has shown no differences between people who do and do not relapse on gross structural measures.