Naturalistic smartphone keyboard typing reflects processing speed and executive function

• Published in: Brain and behavior Vol. 11; no. 11; pp. e2363 - n/a
• Main Authors: Ross, Mindy K., Demos, Alexander P., Zulueta, John, Piscitello, Andrea, Langenecker, Scott A., McInnis, Melvin, Ajilore, Olusola, Nelson, Peter C., Ryan, Kelly A., Leow, Alex
• Format: Journal Article
• Language: English
• Published: United States John Wiley & Sons, Inc 01-11-2021; John Wiley and Sons Inc; Wiley
• Subjects: Bipolar disorder; Cognition; Cognition & reasoning; Executive Function; Humans; Keyboards; mHealth; Neuropsychological Tests; Neuropsychology; Original; Reproducibility of Results; Smartphone; Smartphones; Trail Making Test; trail making tests; typing dynamics; United States > US; Michigan; mHealth; typing dynamics; bipolar disorder; trail making tests; cognition
• ISSN: 2162-3279; 2162-3279
• DOI: 10.1002/brb3.2363

Objective
The increase in smartphone usage has enabled the possibility of more accessible ways to conduct neuropsychological evaluations. The objective of this study was to determine the feasibility of using smartphone typing dynamics with mood scores to supplement cognitive assessment through trail making tests.
Methods
Using a custom‐built keyboard, naturalistic keypress dynamics were unobtrusively recorded in individuals with bipolar disorder (n = 11) and nonbipolar controls (n = 8) on an Android smartphone. Keypresses were matched to digital trail making tests part B (dTMT‐B) administered daily in two periods and weekly mood assessments. Following comparison of dTMT‐Bs to the pencil‐and‐paper equivalent, longitudinal mixed‐effects models were used to analyze daily dTMT‐B performance as a function of typing and mood.
Results
Comparison of the first dTMT‐B to paper TMT‐B showed adequate reliability (intraclass correlations = 0.74). In our model, we observed that participants who typed slower took longer to complete dTMT‐B (b = 0.189, p < .001). This trend was also seen in individual fluctuations in typing speed and dTMT‐B performance (b = 0.032, p = .004). Moreover, participants who were more depressed completed the dTMT‐B slower than less depressed participants (b = 0.189, p < .001). A practice effect was observed for the dTMT‐Bs.
Conclusion
Typing speed in combination with depression scores has the potential to infer aspects of cognition (visual attention, processing speed, and task switching) in people's natural environment to complement formal in‐person neuropsychological assessments that commonly include the trail making test.
This study explored the feasibility of using smartphone typing dynamics with mood scores to supplement cognitive assessment through trail making tests. Naturalistic keypress dynamics were unobtrusively collected from individuals with bipolar disorder and nonbipolar controls using a custom‐built keyboard and compared to serial administrations of the trail making test part B. Typing speed in combination with depression scores significantly predicted trail making test time and may have the potential to be used to assess cognition in real time to complement in‐person assessments.