Predicting the cognitive impairment with multimodal ophthalmic imaging and artificial neural network for community screening
Bibliographic record
Abstract
Background/aims To investigate the comprehensive prediction ability for cognitive impairment in a general elder population using the combination of the multimodal ophthalmic imaging and artificial neural networks. Methods Patients with cognitive impairment and cognitively healthy individuals were recruited. All subjects underwent medical history, blood pressure measurement, the Montreal Cognitive Assessment, medical optometry, intraocular pressure and custom-built multimodal ophthalmic imaging, which integrated pupillary light reaction, multispectral imaging, laser speckle contrast imaging and retinal oximetry. Multidimensional parameters were analysed by Student’s t-test. Logistic regression analysis and back-propagation neural network (BPNN) were used to identify the predictive capability for cognitive impairment. Results This study included 104 cognitive impairment patients (61.5% female; mean (SD) age, 68.3 (9.4) years), and 94 cognitively healthy age-matched and sex-matched subjects (56.4% female; mean (SD) age, 65.9 (7.6) years). The variation of most parameters including decreased pupil constriction amplitude (CA), relative CA, average constriction velocity, venous diameter, venous blood flow and increased centred retinal reflectance in 548 nm (RC 548 ) in cognitive impairment was consistent with previous studies while the reduced flow acceleration index and oxygen metabolism were reported for the first time. Compared with the logistic regression model, BPNN had better predictive performance (accuracy: 0.91 vs 0.69; sensitivity: 93.3% vs 61.70%; specificity: 90.0% vs 68.66%). Conclusions This study demonstrates retinal spectral signature alteration, neurodegeneration and angiopathy occur concurrently in cognitive impairment. The combination of multimodal ophthalmic imaging and BPNN can be a useful tool for predicting cognitive impairment with high performance for community screening.
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 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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".