Parkinson's disease (PD) is the world's second most common agerelated neurodegenerative disorder. Given the tendency for longer life expectancy and that the risk of PD increases with age, the number of people with PD is expected to double by the year 2030. 1 In PD, degeneration of the dopaminergic pathways results in striatal dopamine deficiency. The cardinal signs of disease are as follows:bradykinesia, muscle rigidity, resting tremor, and postural instability.In addition to these classic motor symptoms, non-motor features (eg, cognitive impairment, dizziness, and orthostatic hypotension) also occur. The core and first-choice therapy is dopaminergic medication (levodopa) that targets the neurotransmitter imbalance within the basal ganglia circuits. Complications of therapy such as dyskinesia (involuntary movements) and "off" periods (fluctuating drug response) often develop over time. 2 Falls and balance problems are common already in the early stages of disease 3,4 and progress over time. 5 A history of falls is the strongest predictor of future falls in PD. 6 However, it was suggested that prediction of both near falls and falls has greater clinical value than prediction of falls alone if you aim at working proactively. 7 Furthermore, fall prediction models, in order to be applicable, useful, and practical for routine clinical use, need to have sufficient discriminant ability 8,9 and must be easy to implement. 10 To this A growing body of research highlights the importance of cognition for prediction of falls in Parkinson's disease (PD). However, a previously proposed prediction model for future near falls and falls in PD, which includes history of near falls, tandem gait, and retropulsion, was developed without considering cognitive impairment.