Using Smartphone Keystroke Dynamics to Detect Mild Cognitive Impairment
Author Information
Author(s): Coristine Andrew, Gallucci Alessia, Mychajliw Christian, Park Jin-Hyuck
Primary Institution: Department of Occupational Therapy, College of Medical Science, Soonchunhyang University, Asan, Republic of Korea
Hypothesis
Can smartphone-derived keystroke dynamics effectively distinguish patients with mild cognitive impairment from healthy controls?
Conclusion
Smartphone-derived keystroke dynamics are an effective tool for screening mild cognitive impairment, showing higher sensitivity and specificity than traditional neuropsychological tests.
Supporting Evidence
- Patients with MCI had significantly higher keystroke latency than healthy controls.
- Keystroke dynamics showed a sensitivity of 97.9% and specificity of 96.9% in distinguishing MCI.
- Keystroke dynamics were significantly correlated with the MoCA-K scores.
Takeaway
This study shows that how you type on your smartphone can help tell if someone has early signs of memory problems.
Methodology
Participants used the Neurokeys keyboard app to collect keystroke data over a month, which was then analyzed for differences between healthy controls and patients with mild cognitive impairment.
Limitations
The study's findings may not be generalizable beyond the amnestic type of MCI, and the working memory deficits were not objectively verified through neuroimaging.
Participant Demographics
Participants included 64 healthy controls and 47 patients with mild cognitive impairment, matched for age and education.
Statistical Information
P-Value
<0.001
Confidence Interval
95% CI for AUC values ranged from .756 to 1.000
Statistical Significance
p<0.001
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website