Detection of early Alzheimer’s disease at the eye clinic: The BeyeOMARKER study
Bibliographic record
Abstract
Abstract Background Early detection of Alzheimer’s disease (AD) is essential for establishing a patient management plan, and for clinical trial selection and determining who will benefit most from future therapies. Effective screening for early AD will require large‐scale implementation of non‐invasive, scalable, and accessible biomarkers such as blood‐based biomarkers and retinal scans. With a high population throughput and a visually impaired population at increased risk for AD (HR = 1.47 (Kuźma et al., J Alzheimers Dis (2021)), eye clinics provide a prime proof‐of‐concept setting to explore the potential of implementing non‐invasive biomarkers in an alternative clinical setting. The BeyeOMARKER study aims to explore the feasibility of large‐scale screening using non‐invasive tools in eye clinics, with the ultimate goal of providing recommendations for AD screening in alternative clinical settings, and exploring factors underlying the association between eye disease and AD. Method The BeyeOMARKER study is a prospective, observational, longitudinal cohort study. At the eye clinic, ∼700 participants (aged ≥45) will be screened for early AD using plasma phospho‐tau181 (p‐tau181) and a short neuropsychological test battery (Montreal Cognitive assessment). After screening, 100 plasma p‐tau181 positive cases and 50 p‐tau181 negative controls (matched based on age, sex and eye disease) will be included into the longitudinal BeyeOMARKER cohort. This cohort will be invited to the memory clinic for a hyperspectral retinal scan, structural magnetic resonance imaging (MRI), and a comprehensive neuropsychological assessment including cortical vision tests (e.g., visuo‐perceptive and visuospatial abilities). Result Main outcomes of the BeyeOMARKER study are 1) a prevalence estimate of AD in a large, diverse population of visually impaired individuals, 2) the performance of hyperspectral retinal scans to detect AD pathology in this population and its complementary benefit over‐and‐above plasma p‐tau181, and 3) improved understanding on the eye‐brain connection in the context of AD through comparison of cognitive and cortical vision performance, and brain atrophy across visually impaired p‐tau181 positive and negative individuals. Conclusion The BeyeOMARKER consortium aspires to build a detailed roadmap for the implementation of non‐invasive screening for early AD within the eye clinic.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| 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 | 0.001 |
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 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".