CONVERGENT VALIDITY AND STABILITY OF A 5-MINUTE WEB CAMERA-BASED EYE-TRACKING COGNITIVE ASSESSMENT
Bibliographic record
Abstract
Joshua Gills1, Spencer Smith1, Emily Bates1, Jordan M. Glenn2, Erica N. Madero2, Nick T. Bott2, & Michelle Gray1 1University of Arkansas, Fayetteville, AR., 2Neurotrack Technologies, Inc., Redwood City, CA. As populations age worldwide, dementia prevalence is projected to triple from current rates to 132 million by 2050. While there is no cure for Alzheimer’s disease (AD) or other forms of dementia, early detection of symptoms allow treatment to start earlier and improve outcomes. Currently, there exists a noninvasive validated 30-minute (min) eye-tracking cognitive assessment for predicting AD risk. However, the time requirements and passive nature of the paradigm creates a burden for the user. A shorter task utilizing an active paradigm would improve user experience and increase scalability of the test. PURPOSE: The purposes of this study were to 1) determine convergent validity of an active 5-min web camera-based eye-tracking task to measure visual recognition memory compared to the validated passive 30-min task and 2) determine the stability and test-retest reliability of the 5-min test. METHODS: This prospective study included 44 cognitively intact participants (n = 28 females, n = 16 males; age = 50.0 ± 27.6) who were divided into two cohorts: older adults (ages 65+ years, n = 20) and young adults (ages 18 – 46 years, n = 24). Participants reported for testing on two separate occasions. The first visit included informed consent, medical history questionnaire, Montreal Cognitive Assessment (MOCA), 30-min eye tracking test, and 5-min eye tracking test. The second testing session occurred at least 14 days later and participants were given an alternate form of the 5-min eye tracking test to minimize learning effects. RESULTS: Participants were cognitively normal based on MOCA scores (27.9 ± 1.4). A Pearson’s correlation determined the 30-min task was moderately correlated with the 5 min task at the first (r =.55; p < .001) and second (r =.58; p = .001) time points. Moreover, there was a high test re-test reliability of the 5-min test (r =.73; p < .001). CONCLUSION: The active 5-min eye-tracking assessment displayed moderate convergent validity to the passive 30-min test for assessing working memory and demonstrated strong test-retest reliability. Initial data indicate the 5-min version of the eye-tracking task may be a more scalable alternative to the original 30-min version. However further research is needed to ultimately substantiate this claim. ACKNOWLEDGEMENTS: This study was funded by Neurotrack Technologies and The University of Arkansas’ Department of Health, Human Performance, and Recreation.
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 | 0.006 | 0.019 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".