Early-warning signals for disease activity in patients diagnosed with multiple sclerosis based on keystroke dynamics

Abstract

Within data gathered through passive monitoring of patients with Multiple Sclerosis (MS), there is a clear necessity for improved methodological approaches to match the emergence of continuous, objective, measuring technologies. As most gold standards measure infrequently and require clinician presence, fluctuations in the daily progression are not accounted for. Due to the underlying conditions of homogeneity and stationarity (the main tenets of ergodicity) not being met for the majority of the statistical methods employed in the clinical setting, alternative approaches should be investigated. A solution is to use a non-linear time series analysis approach. Here, Early-Warning Signals (EWS) in the form of critical fluctuations in Keystroke Dynamics (KD), collected using participant’s smartphones, are investigated as indicators for a clinical change in three groups. These are patients with MS and changes in Magnetic Resonance Imaging (MRI), patients with MS but without changes in MRI, and healthy controls (HCs). Here, we report examples of EWS and changes in KD coinciding with clinically relevant changes in outcome measures in both patients with and without differences in the amount of MRI enhancing lesions. We also report no clinically relevant changes in EWS in the HC population. This study is a first promising step toward using EWS to identify periods of instability as measured by a continuous objective measure as a proxy for outcome measures in the field of MS.

Diagnostic accuracy of keystroke dynamics as digital biomarkers for fine motor decline in neuropsychiatric disorders: a systematic review and meta-analysis

“…The diagnostic accuracy revealed by our meta-analysis reflects, for the first time, the reproducibility of keystroke dynamic models in the assessment of multiple disorders with neurologically defined fine motor impairment. Besides the three disease categories reviewed in this paper, researchers are currently employing them for Multiple Sclerosis 70 , 71 and Huntington’s disease 72 . We therefore conclude that we can rely on keystroke dynamics obtained passively from natural interactions with keyboards to detect fine motor impairments induced by early stage neurological and/or psychiatric disorders.…”

Show me your smartphone… and then I will show you your brain structure and brain function

“…Also see recent work investigating nonexercise activity in the context of brain data (Reichert et al, 2020b). We also mention recent work studying early-warning signals for multiple sclerosis disease activity via keystroke dynamics of the smartphone also taking into account the MRI data of patients (Twose, Licitra, McConchie, Lam, & Killestein, 2020).…”

A Systematic Literature Review on Latest Keystroke Dynamics Based Models

“…Mental health status monitoring: Fine motor skills have a relationship with KD. By recognising this skill, KD could be used in the following areas -Parkinson's disease detection [83], [84], mental health monitoring using chat session [85], Alzheimer's disease prediction [86], mild cognitive impairment [36], clinical disability in multiple sclerosis [87], [88], quantification of traumatic brain injury [89], identifying spastic diplegia under cerebral palsy [90], stress monitoring [82].…”