# Length of Stay (LOS) on EHRSHOT (test)

Source: [Length of Stay (LOS) on EHRSHOT (test)](<https://www.sota2.com/research/sota/length-of-stay-los-on-ehrshot-test>)

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

Data updated: 2026-06-04T07:10:02.022Z

Evaluation of model performance on predicting Length of Stay (LOS) using the test split of the EHRSHOT dataset, reporting Precision, Recall, 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 | Length of Stay (LOS) |
| Dataset (including any stated split) | EHRSHOT (test) |
| Metric | Precision |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [Precision](<https://www.sota2.com/research/sota/length-of-stay-los-on-ehrshot-test.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/length-of-stay-los-on-ehrshot-test.md?metric=Recall>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/length-of-stay-los-on-ehrshot-test.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Precision | Result date | Report paper |
| --- | --- | --- | --- |
| CLMBR + Linear | 66.7 | Not recorded | 6a21067ec10484bac23f0036 |
| ChatHealthAI | 44.2 | Not recorded | 6a21067ec10484bac23f0036 |
| Llama-3.1-8B-Instruct | 26.9 | Not recorded | 6a21067ec10484bac23f0036 |
| BioMistral-7B | 26.9 | Not recorded | 6a21067ec10484bac23f0036 |
| DeepSeek-R1-14B | 25.8 | Not recorded | 6a21067ec10484bac23f0036 |
| Llama-3.1-8B-Instruct | 25.3 | Not recorded | 6a21067ec10484bac23f0036 |
| BioMistral-7B | 25.2 | Not recorded | 6a21067ec10484bac23f0036 |
| DeepSeek-R1-14B | 23.7 | Not recorded | 6a21067ec10484bac23f0036 |

### CLMBR + Linear

Precision: 66.7. Result ID: 6a2124c7fbc373592c1c2e2c.

[Reporting paper](<https://www.sota2.com/research/paper/6a21067ec10484bac23f0036.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa717c1e209131cea5191b.md>)

Recorded evaluation configuration: {"Threshold":"0.5"}. This record does not assert independent reproduction.

### ChatHealthAI

Precision: 44.2. Result ID: 6a2124c7fbc373592c1c2e33.

[Reporting paper](<https://www.sota2.com/research/paper/6a21067ec10484bac23f0036.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a21067ec10484bac23f0036.md>)

Recorded evaluation configuration: {"Setting":"finetuned"}. This record does not assert independent reproduction.

### Llama-3.1-8B-Instruct

Precision: 26.9. Result ID: 6a2124c7fbc373592c1c2e2e.

[Reporting paper](<https://www.sota2.com/research/paper/6a21067ec10484bac23f0036.md>)

Recorded evaluation configuration: {"Setting":"finetuned"}. This record does not assert independent reproduction.

### BioMistral-7B

Precision: 26.9. Result ID: 6a2124c7fbc373592c1c2e30.

[Reporting paper](<https://www.sota2.com/research/paper/6a21067ec10484bac23f0036.md>)

Recorded evaluation configuration: {"Setting":"finetuned"}. This record does not assert independent reproduction.

### DeepSeek-R1-14B

Precision: 25.8. Result ID: 6a2124c7fbc373592c1c2e31.

[Reporting paper](<https://www.sota2.com/research/paper/6a21067ec10484bac23f0036.md>)

Recorded evaluation configuration: {"Setting":"zero-shot"}. This record does not assert independent reproduction.

### Llama-3.1-8B-Instruct

Precision: 25.3. Result ID: 6a2124c7fbc373592c1c2e2d.

[Reporting paper](<https://www.sota2.com/research/paper/6a21067ec10484bac23f0036.md>)

Recorded evaluation configuration: {"Setting":"zero-shot"}. This record does not assert independent reproduction.

### BioMistral-7B

Precision: 25.2. Result ID: 6a2124c7fbc373592c1c2e2f.

[Reporting paper](<https://www.sota2.com/research/paper/6a21067ec10484bac23f0036.md>)

Recorded evaluation configuration: {"Setting":"zero-shot"}. This record does not assert independent reproduction.

### DeepSeek-R1-14B

Precision: 23.7. Result ID: 6a2124c7fbc373592c1c2e32.

[Reporting paper](<https://www.sota2.com/research/paper/6a21067ec10484bac23f0036.md>)

Recorded evaluation configuration: {"Setting":"finetuned"}. This record does not assert independent reproduction.

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