Digital health technologies that quantify mobility in unsupervised, daily-living environments are emerging as a complementary evaluation approach in neurology. Data collected in these ecologically valid, patient-relevant settings can overcome significant limitations of conventional clinical assessments. Unsupervised assessments can capture fluctuating and rare events and have the promise of supporting clinical decision-making and serving as outcomes in clinical trials. However, studies that directly compared assessments made in unsupervised and supervised (i.e. in the lab or clinical) settings point to large disparities, even in the same parameters of mobility (up to 180% difference). These differences appear to be influenced by psychological, physiological, cognitive, environmental, and technical factors and by the specific aspect of mobility and diagnosis. To facilitate the successful adaptation of the unsupervised assessment of mobility in the clinic and in clinical trials, clinicians and future work should take into account these disparities and the multiple factors that contribute to them.