This report tests the association of self-reported symptoms of irritability with overt behavior of anger attacks (uncharacteristic sudden bouts of anger that are disproportionate to situation and associated with autonomic activation).

Participants of the Establishing Moderators and Biosignatures of Antidepressant Response in Clinical Care study who completed Massachusetts General Hospital Anger Attacks questionnaire were included (n = 293). At each visit, the 17-item Hamilton Depression Rating Scale and the 16-item Concise Associated Symptom Tracking scale were used to measure depression, anxiety, and irritability. In those with anger attacks present v. those without anger attacks, separate t tests and mixed model analyses compared afore-mentioned symptoms at baseline and changes with treatment respectively. As anger attacks may occur without aggressive behaviors, analyses were repeated based only on the presence of aggressive behaviors.

At baseline, those with anger attacks (n = 109) v. those without anger attacks (n = 184) had similar levels of depression but higher levels of irritability [effect size (d) = 0.80] and anxiety (d = 0.32). With acute-phase treatment, participants with anger attacks experienced a greater reduction in irritability (p < 0.001) but not in depression (p = 0.813) or anxiety (p = 0.771) as compared to those without anger attacks. Yet, irritability levels at week-8 were higher in those with anger attacks (d = 0.32) than those without anger attacks. Similar results were found in participants with aggressive behaviors.

The presence of anger attacks in outpatients with major depressive disorder may identify a sub-group of patients with persistently elevated irritability.

Major depressive disorder (MDD) is a highly heterogeneous condition in terms of symptom presentation and, likely, underlying pathophysiology. Accordingly, it is possible that only certain individuals with MDD are well-suited to antidepressants. A potentially fruitful approach to parsing this heterogeneity is to focus on promising endophenotypes of depression, such as neuroticism, anhedonia, and cognitive control deficits.

Within an 8-week multisite trial of sertraline v. placebo for depressed adults (n = 216), we examined whether the combination of machine learning with a Personalized Advantage Index (PAI) can generate individualized treatment recommendations on the basis of endophenotype profiles coupled with clinical and demographic characteristics.

Five pre-treatment variables moderated treatment response. Higher depression severity and neuroticism, older age, less impairment in cognitive control, and being employed were each associated with better outcomes to sertraline than placebo. Across 1000 iterations of a 10-fold cross-validation, the PAI model predicted that 31% of the sample would exhibit a clinically meaningful advantage [post-treatment Hamilton Rating Scale for Depression (HRSD) difference ⩾3] with sertraline relative to placebo. Although there were no overall outcome differences between treatment groups (d = 0.15), those identified as optimally suited to sertraline at pre-treatment had better week 8 HRSD scores if randomized to sertraline (10.7) than placebo (14.7) (d = 0.58).

A subset of MDD patients optimally suited to sertraline can be identified on the basis of pre-treatment characteristics. This model must be tested prospectively before it can be used to inform treatment selection. However, findings demonstrate the potential to improve individual outcomes through algorithm-guided treatment recommendations.