# Disease Classification on UK Biobank Diabetic Retinopathy (DR) primary cohort

Source: [Disease Classification on UK Biobank Diabetic Retinopathy (DR) primary cohort](<https://www.sota2.com/research/sota/disease-classification-on-uk-biobank-diabetic-retinopathy-dr-primary-cohort>)

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

Data updated: 2026-05-14T08:05:24.231Z

Evaluation of model performance for Disease Classification using the primary cohort data focused on Diabetic Retinopathy (DR) from the UK Biobank 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 | Disease Classification |
| Dataset (including any stated split) | UK Biobank Diabetic Retinopathy (DR) primary cohort |
| Metric | AUC |
| Unit | PERCENT |
| 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/disease-classification-on-uk-biobank-diabetic-retinopathy-dr-primary-cohort.md?metric=AUC>): Higher is better; unit: PERCENT.

## Recorded results

| Method | AUC | Result date | Report paper |
| --- | --- | --- | --- |
| EfficientNet-B2 | 96.1 | Not recorded | 6a0556f3dbc836b87d828b82 |
| BiomedCLIP (512-d) | 83.6 | Not recorded | 6a0556f3dbc836b87d828b82 |
| Bézier (20-d) | 70.6 | Not recorded | 6a0556f3dbc836b87d828b82 |

### EfficientNet-B2

AUC: 96.1. Result ID: 6a05813747f34ce924ec5127.

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

Recorded evaluation configuration: {"Model Architecture":"EfficientNet-B2","Training Mode":"End-to-end"}. This record does not assert independent reproduction.

### BiomedCLIP (512-d)

AUC: 83.6. Result ID: 6a05813747f34ce924ec5126.

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

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

Recorded evaluation configuration: {"Feature Type":"BiomedCLIP","Feature Dimensionality":"512-d","Classifier":"XGBoost"}. This record does not assert independent reproduction.

### Bézier (20-d)

AUC: 70.6. Result ID: 6a05813747f34ce924ec5125.

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

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

Recorded evaluation configuration: {"Feature Type":"Bézier Tree Encoding","Feature Dimensionality":"20-d","Classifier":"XGBoost"}. This record does not assert independent reproduction.

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