This study examines the prevalence of mental health problems during the fourth postgraduate year, and investigates whether it is already possible to predict such problems at medical school. Univariate medical school predictors of mental health problems include: previous mental health problems; not being married/cohabitant; the personality traits ‘vulnerability’ (or neuroticism) and ‘reality weakness’; perceived medical school stress, and lack of perceived diagnostic skills. In addition, the coping variables avoidance, blamed self and wishful thinking were univariate predictors. In summation, medical school variables were inadequate for predicting which individual students would experience postgraduate mental health deterioration.