Discriminant Power of Smartphone-Derived Keystroke Dynamics for Mild Cognitive Impairment Compared to a Neuropsychological Screening Test: Cross-Sectional Study (Preprint)
Bibliographic record
Abstract
BACKGROUND Conventional neuropsychological screening tools for mild cognitive impairment (MCI) face challenges in terms of accuracy and practicality. Digital health solutions, such as unobtrusively capturing smartphone interaction data, offer a promising alternative. However, the potential of digital biomarkers as a surrogate for MCI screening remains unclear, with few comparisons between smartphone interactions and existing screening tools. OBJECTIVE This study aimed to investigate the effectiveness of smartphone-derived keystroke dynamics, captured via the Neurokeys keyboard app, in distinguishing patients with MCI from healthy controls (HCs). This study also compared the discriminant performance of these digital biomarkers against the Korean version of the Montreal Cognitive Assessment (MoCA-K), which is widely used for MCI detection in clinical settings. METHODS A total of 64 HCs and 47 patients with MCI were recruited. Over a 1-month period, participants generated 3530 typing sessions, with 2740 (77.6%) analyzed for this study. Keystroke metrics, including hold time and flight time, were extracted. Receiver operating characteristics analysis was used to assess the sensitivity and specificity of keystroke dynamics in discriminating between HCs and patients with MCI. This study also explored the correlation between keystroke dynamics and MoCA-K scores. RESULTS Patients with MCI had significantly higher keystroke latency than HCs (P<.001). 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<.001; flight time: r=–.497; P<.001), further supporting the validity of these digital biomarkers. CONCLUSIONS These findings highlight the potential of smartphone-derived keystroke dynamics as an effective and ecologically valid tool for screening MCI. With higher sensitivity and specificity than the MoCA-K, particularly in measuring flight time, keystroke dynamics can serve as a noninvasive, scalable, and continuous method for early cognitive impairment detection. This novel approach could revolutionize MCI screening, offering a practical alternative to traditional tools in everyday settings. CLINICALTRIAL Thai Clinical Trials Registry TCTR20220415002; https://www.thaiclinicaltrials.org/show/TCTR20220415002
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".