Abstract Background Long-acting antipsychotics (e.g. 1-monthly (PP1M) / 3-monthly (PP3M) injection forms of paliperidone palmitate) have been developed to improve treatment continuation in schizophrenia patients. We aim to assess risk factors of treatment discontinuation of patients on paliperidone palmitate and risperidone microsphere. Additionally, treatment discontinuation between patients with PP1M and PP3M was compared. Methods The IQVIA Longitudinal Prescription databases were used. Risk factors of treatment discontinuation were identified by a multilevel survival regression using Cox proportional hazards model. Kaplan Meier analyses were performed by identified significant risk factors. Results Twenty-five thousand three hundred sixty-one patients (France: 9,720; Germany: 14,461; Belgium: 1,180) were included. Over a one-year follow-up period, a significant lower treatment discontinuation was observed for patients newly initiated on paliperidone palmitate (53.8%) than those on risperidone microspheres (85.4%). Additionally, a significantly lower treatment discontinuation was found for ‘stable’ PP3M patients (19.2%) than ‘stable’ PP1M patients (37.1%). Patients were more likely to discontinue when drugs were prescribed by GP only (HR = 1.68, p < 0.001 vs. psychiatrist only) or if they were female (HR = 1.07, p < 0.001), whereas discontinuation decreased with age (31–50 years: HR = 0.95, p = 0.006 and > 50 years: HR = 0.91, p < 0.001 vs. 18–30 years). Conclusions This study demonstrates that patients stay significantly longer on treatment when initiated on paliperidone palmitate as compared to risperidone microspheres. It also indicated a higher treatment continuation of PP3M over PP1M. Treatment continuation is likely to be improved by empowering GPs with mental health knowledge and managing patients by a collaborative primary care-mental health model. Further research is needed to understand why females and younger patients have more treatment discontinuation.