Niraparib is a poly(ADP-ribose) polymerase inhibitor approved in the USA and Europe for maintenance treatment of adult patients with recurrent epithelial ovarian, fallopian tube, or primary peritoneal cancer who are in complete or partial response to platinum-based chemotherapy. In the pivotal ENGOT-OV16/NOVA trial, the dose reduction rate due to treatment-emergent adverse event (TEAE) was 68.9%, and the discontinuation rate due to TEAE was 14.7%, including 3.3% due to thrombocytopenia. A retrospective analysis was carried out to identify clinical parameters that predict dose reductions. All analyses were carried out on the safety population, comprising all patients who received at least one dose of study drug. Patients were analyzed according to the study drug consumed (i.e., as treated). A predictive modeling method (decision trees) was used to identify important variables for predicting the likelihood of developing grade≥3 thrombocytopenia within 30days after the first dose of niraparib and determine cut-off points for chosen variables. Following dose modification, 200mg was the most commonly administered dose in the ENGOT-OV16/NOVA trial. Baseline platelet count and baseline body weight were identified as risk factors for increased incidence of grade≥3 thrombocytopenia. Patients with a baseline body weight<77kg or a baseline platelet count<150000/µl in effect received an average daily dose ∼200mg (median=207mg) due to dose interruption and reduction. Progression-free survival in patients who were dose reduced to either 200 or 100mg was consistent with that of patients who remained at the 300mg starting dose. The analysis presented suggests that patients with baseline body weight of<77kg or baseline platelets of<150000/µl may benefit from a starting dose of 200mg/day. NCT01847274.