The aim of this study was to examine the effects of exercise and sertraline on disordered sleep in patients with major depressive disorder (MDD). Methods The Standard Medical Intervention and Long-term Exercise study randomized the patients with MDD (n = 202) to one of four arms: a) supervised exercise, b) home-based exercise, c) sertraline therapy, and d) placebo pill. Sleep disturbance was assessed with three sleep-related items from the Hamilton Rating Scale for Depression (HAM-D) before and after 4 months of treatment. The patients were followed for 12 months to assess the prognostic value of sleep disturbance on MDD relapse and recovery.Results Comparison of the active treatment and placebo groups showed no treatment differences in HAM-D sleep complaints after 4 months (p = 0.758). However, residual insomnia symptoms after treatment were strongly associated with elevated depressive symptoms assessed by the HAM-D after 4 months (β = 0.342, p < 0.0001) and MDD relapse (odds ratio, 1.55; 95% confidence interval, 1.15-2.10; p = 0.004) assessed at 1-year follow-up (16 months after randomization). Neither exercise nor sertraline was associated with greater improvements in sleep disturbance compared with the placebo controls. However, residual symptoms of insomnia after successful treatment of MDD predicted relapse, highlighting the clinical importance of addressing insomnia in patients with MDD.