Development and Validation of the Short-Form BrainOK: An Efficient Digital Screening Tool for Mild Cognitive Impairment
Bibliographic record
Abstract
Background/Objectives: Population aging requires scalable approaches for early identification of cognitive decline, particularly mild cognitive impairment (MCI). Although the full 11-task BrainOK smartphone assessment showed excellent discrimination (AUC = 0.941), its administration time constrains large-scale use. To develop and validate a brief Short-Form BrainOK (SF-BrainOK) that preserves diagnostic performance while substantially reducing testing time. Methods: We enrolled 168 community-dwelling older adults (≥60 years). MCI was defined using the Montreal Cognitive Assessment (MoCA; score ≤ 23) as the reference standard. Candidate tasks were selected from the original BrainOK via LASSO-based preselection. To maximize data utilization given the limited sample size, model performance was evaluated using Leave-One-Out Cross-Validation (LOOCV). The cut-off value was determined by maximizing Youden’s J. Results: The final two-task model combined executive function task (Rule-based Drumming I) and memory task (Password Memory I). On the independent test set, discrimination was robust (AUC = 0.783), with sensitivity = 0.75 (95% CI: 0.63–0.85, specificity = 0.71 (95% CI: 0.62–0.80, and accuracy = 0.765 (95% CI: 0.65–0.79) at the optimal cutoff. Conclusions: SF-BrainOK provides a brief, two-task digital screen that markedly reduces administration time while maintaining effective diagnostic performance. By targeting executive function and memory—domains repeatedly shown to be sensitive to early MCI-related change—SF-BrainOK supports scalable, opportunistic screening and the timely identification of at-risk individuals in resource-constrained settings.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".