Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Apr 6, 2024
Open Peer Review Period: Apr 6, 2024 - Jun 1, 2024
Date Accepted: Oct 11, 2024
(closed for review but you can still tweet)
Can smartphone-derived keystroke dynamics better discriminate mild cognitive impairment than a neuropsychological screening test?: A cross-sectional study
ABSTRACT
Background:
Conventional neuropsychological screening tools for mild cognitive impairment (MCI) have been threatened by their burdensomeness and inaccurate at detecting MCI. From a digital healthcare perspective, smartphone interaction, longitudinally and unobtrusively acquired behavior data in a non-clinical setting, alleviate these limitations.
Objective:
This study aimed to investigate the discriminant powers of digital biomarkers, drawn from smartphone-derived keystroke dynamics using the Neurokeys keyboard application.
Methods:
64 healthy controls (HCs) and 47 patients with MCI producing 3,530 typing sessions within a month, performing the Korean version of the Montreal Cognitive Assessment (MoCA-K), were tested. A total of 2,740 were finally analyzed using the receiving operant curve analysis to investigate sensitivity and specificity.
Results:
Patients with MCI had significantly higher keystroke latency than controls. In particular, latency between key presses resulted in the highest sensitivity (97.9%) and specificity (96.9%). In addition, keystroke dynamics were significantly correlated with the MoCA-K (hold time: r=-.468, P<0.001; flight time: r=-0.497, P<0.001).
Conclusions:
The current findings shed new light on the potential of smartphone-derived keystroke dynamics as an ecological surrogate for a laboratory-based conventional screening tool. Clinical Trial: Thaiclinicaltrial.org TCTR20220415002, https:// https://www.thaiclinicaltrials.org/show/TCTR20220415002
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.