Objective Neuropsychiatric events occur unpredictably in systemic lupus erythematosus (SLE) and most biomarker associations remain to be prospectively validated. This study examined a disease inception cohort of 1047 SLE patients to determine which autoantibodies at enrolment predicted subsequent neuropsychiatric events. Methods Patients with a recent SLE diagnosis were assessed prospectively for up to 10 years for neuropsychiatric events using the American College of Rheumatology case definitions. Decision rules of graded stringency determined whether neuropsychiatric events were attributable to SLE. Associations between the first neuropsychiatric event and baseline autoantibodies (lupus anticoagulant (LA), anticardiolipin, anti-beta(2) glycoprotein-I, anti-ribosomal P and anti-NR2 glutamate receptor) were tested by Cox proportional hazards regression. Results Disease duration at enrolment was 5.4 +/- 4.2 months, follow-up was 3.6 +/- 2.6 years. Patients were 89.1% female with mean (+/- SD) age 35.2 +/- 13.7 years. 495/1047 (47.3%) developed one or more neuropsychiatric event (total 917 events). Neuropsychiatric events attributed to SLE were 15.4% (model A) and 28.2% (model B). At enrolment 21.9% of patients had LA, 13.4% anticardiolipin, 15.1% anti-beta(2) glycoprotein-I, 9.2% anti-ribosomal P and 13.7% anti-NR2 antibodies. LA at baseline was associated with subsequent intracranial thrombosis (total n=22) attributed to SLE (model B) (HR 2.54, 95% CI 1.08 to 5.94). Anti-ribosomal P antibody was associated with subsequent psychosis (total n=14) attributed to SLE (model B) (HR 3.92, 95% CI 1.23 to 12.5, p=0.02). Other autoantibodies did not predict neuropsychiatric events. Conclusion In a prospective study of 1047 recently diagnosed SLE patients, LA and anti-ribosomal P antibodies are associated with an increased future risk of intracranial thrombosis and lupus psychosis, respectively.