ObjectiveTo examine fall risk trajectories occurring naturally in a sample of individuals with early to middle stage Parkinson disease (PD). DesignLatent class analysis, specifically growth mixture modeling (GMM), of longitudinal fall risk trajectories. SettingAssessments were conducted at 1 of 4 universities. ParticipantsCommunity-dwelling participants with PD of a longitudinal cohort study who attended at least 2 of 5 assessments over a 2-year follow-up period (N=230). InterventionsNot applicable. Main Outcome MeasuresFall risk trajectory (low, medium, or high risk) and stability of fall risk trajectory (stable or fluctuating). Fall risk was determined at 6 monthly intervals using a simple clinical tool based on fall history, freezing of gait, and gait speed. ResultsThe GMM optimally grouped participants into 3 fall risk trajectories that closely mirrored baseline fall risk status (P=.001). The high fall risk trajectory was most common (42.6%) and included participants with longer and more severe disease and with higher postural instability and gait disability (PIGD) scores than the low and medium fall risk trajectories (P<.001). Fluctuating fall risk (posterior probability <0.8 of belonging to any trajectory) was found in only 22.6% of the sample, most commonly among individuals who were transitioning to PIGD predominance. ConclusionsRegardless of their baseline characteristics, most participants had clear and stable fall risk trajectories over 2 years. Further investigation is required to determine whether interventions to improve gait and balance may improve fall risk trajectories in people with PD.