# CXR binary classification on SIIM-ACR Pneumothorax OOD

Source: [CXR binary classification on SIIM-ACR Pneumothorax OOD](<https://www.sota2.com/research/sota/cxr-binary-classification-on-siim-acr-pneumothorax-ood>)

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

Data updated: 2026-04-08T07:16:58.907Z

Evaluation of binary classification performance on the Out-of-Distribution (OOD) split of the SIIM-ACR Pneumothorax dataset, reporting Accuracy and F1 scores.

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 | CXR binary classification |
| Dataset (including any stated split) | SIIM-ACR Pneumothorax OOD |
| Metric | Accuracy |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/cxr-binary-classification-on-siim-acr-pneumothorax-ood.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/cxr-binary-classification-on-siim-acr-pneumothorax-ood.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Unichest FT | 88.9 | Not recorded | 68fa79ff1e209131cea808a4 |
| MedGemma 4B | 87.8 | Not recorded | 68fa79ff1e209131cea808a4 |
| MedGemma 4B | 85.9 | Not recorded | 68fa79ff1e209131cea808a4 |

### Unichest FT

Accuracy: 88.9. Result ID: 69d5ff9747f34ce924be19be.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79ff1e209131cea808a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa729f1e209131cea579ae.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MedGemma 4B

Accuracy: 87.8. Result ID: 69d5ff9747f34ce924be19bd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79ff1e209131cea808a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79ff1e209131cea808a4.md>)

Recorded evaluation configuration: {"Evaluation Mode":"Fine-tuned"}. This record does not assert independent reproduction.

### MedGemma 4B

Accuracy: 85.9. Result ID: 69d5ff9747f34ce924be19bc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79ff1e209131cea808a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79ff1e209131cea808a4.md>)

Recorded evaluation configuration: {"Evaluation Mode":"Out-of-box"}. This record does not assert independent reproduction.

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