
A study evaluated the reliability and validity of keystroke dynamics as clinical assessment tools in patients with multiple sclerosis (MS).
The observational study encompassed 102 patients with MS and 24 controls. The Neurokeys keyboard application was used to collect keyboard interactions. The researchers evaluated eight timing-related keystroke features for reliability with intraclass correlation coefficients (ICCs); construct validity by evaluating group differences in fatigue, gadolinium-enhancing lesions on MRI, and patients versus controls; and concurrent validity by correlating with disability measures.
In two features, reliability was moderate (ICC, 0.601 and 0.742), and in the other six features it was good to excellent, with ICCs ranging from 0.760 to 0.965. Patients, compared with controls, had much higher keystroke latencies. Latency between key presses was most significantly associated with Expanded Disability Status Scale (r=0.407), and latency between key releases was most significantly correlated with Nine-Hole Peg Test (P=0.503) and Symbol Digit Modalities Test (r=−0.553; P<0.001).
“Keystroke dynamics were reliable, distinguished patients and controls, and were associated with clinical disability measures. Consequently, keystroke dynamics are a promising valid surrogate marker for clinical disability in MS,” the study authors concluded.