# Diabetic Retinopathy Classification on DR cohort (val + test union split)

Source: [Diabetic Retinopathy Classification on DR cohort (val + test union split)](<https://www.sota2.com/research/sota/diabetic-retinopathy-classification-on-dr-cohort-val-plus-test-union-split>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-14T08:05:24.491Z

Evaluation of Diabetic Retinopathy Classification performance using the combined validation and test splits of the DR cohort dataset, typically measured using AUC.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Diabetic Retinopathy Classification |
| Dataset (including any stated split) | DR cohort (val + test union split) |
| Metric | AUC |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [AUC](<https://www.sota2.com/research/sota/diabetic-retinopathy-classification-on-dr-cohort-val-plus-test-union-split.md?metric=AUC>): Higher is better; unit: SCALAR.

## Recorded results

| Method | AUC | Result date | Report paper |
| --- | --- | --- | --- |
| BiomedCLIP | 0.8587 | Not recorded | 6a0556f3dbc836b87d828b82 |
| BiomedCLIP | 0.8128 | Not recorded | 6a0556f3dbc836b87d828b82 |
| Bézier geometric | 0.7146 | Not recorded | 6a0556f3dbc836b87d828b82 |

### BiomedCLIP

AUC: 0.8587. Result ID: 6a05813747f34ce924ec5136.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556f3dbc836b87d828b82.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa768f1e209131cea6db5b.md>)

Recorded evaluation configuration: {"Dim":"512","Feature set":"frozen features","Evaluation protocol":"5-fold CV"}. This record does not assert independent reproduction.

### BiomedCLIP

AUC: 0.8128. Result ID: 6a05813747f34ce924ec5137.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556f3dbc836b87d828b82.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa768f1e209131cea6db5b.md>)

Recorded evaluation configuration: {"Dim":"20","Feature set":"PCA to 20-d (EVR = 85%)","Evaluation protocol":"5-fold CV"}. This record does not assert independent reproduction.

### Bézier geometric

AUC: 0.7146. Result ID: 6a05813747f34ce924ec5135.

[Reporting paper](<https://www.sota2.com/research/paper/6a0556f3dbc836b87d828b82.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0556f3dbc836b87d828b82.md>)

Recorded evaluation configuration: {"Dim":"20","Evaluation protocol":"5-fold CV"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.