Smartphone keystroke dynamics (KD) showed good responsiveness to variations in disease activity, fatigue, and clinical disability in patients with MS, with better responsiveness than frequently used clinical measures, according to a study published in the European Journal of Neurology. Researchers examined the ability of KD, obtained from normal typing, to detect changes in gadolinium-enhancing lesions on MRI, relapses, fatigue, and clinical disability outcomes in participants at baseline and 3 months. They obtained 15 keystroke features and aggregated them using 16 summary and time-series statistics. The five best-performing keystroke features had an area under the curve (AUC) values from 0.72-0.78 for change in gadolinium-enhancing lesions, 0.67-0.70 for the Checklist Individual Strength Fatigue subscale, 0.66-0.79 for the Expanded Disability Status Scale, 0.69-0.73 for the Ambulation Functional System, and 0.72-0.75 for Arm function in the MS Questionnaire. The minimal clinically important difference of these features surpassed the smallest real change on the group level, and KD had greater AUC values than comparative clinical measures for most outcomes.
