Predicting Pattern Standard Deviation in Glaucoma: A Machine Learning Approach Leveraging Clinical Data
Bibliographic record
Abstract
Visual field (VF) testing is crucial for the management of glaucoma. However, the process is often hindered by technician shortages and reliability issues. In this study, we leveraged machine learning to predict pattern standard deviation (PSD) using clinical inputs. This machine learning retrospective study used publicly accessible data from 743 eyes (541 glaucoma and 202 non-glaucoma controls). An automated neural network (ANN) model was trained using seven clinical input features: mean retinal nerve fiber layer (RNFL), IOP, patient age, CCT, glaucoma diagnosis, study protocol, and laterality. The ANN demonstrated efficient training across 1000 epochs, with consistent error reduction in training and test sets. Mean RMSEs were 1.67 ± 0.05 for training, and 2.27 ± 0.27 for testing. The r was 0.89 ± 0.01 for training, and 0.81 ± 0.04 for testing, indicating strong predictive accuracy with minimal overfitting. The LOFO analysis revealed that the primary contributors to PSD prediction were RNFL, CCT, IOP, glaucoma status, study protocol, and age, listed in order of significance. Our neural network successfully predicted PSD from RNFL and clinical data with strong performance metrics, in addition to demonstrating construct validity. This work demonstrates that neural networks hold the potential to predict or even generate VF estimations based solely on RNFL and clinical inputs.
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 | 0.002 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 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 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".