# In-hospital Duration Prediction on In-hospital dataset (test)

Source: [In-hospital Duration Prediction on In-hospital dataset (test)](<https://www.sota2.com/research/sota/in-hospital-duration-prediction-on-in-hospital-dataset-test>)

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

Data updated: 2026-03-17T07:30:01.951Z

Evaluation of models predicting the length of stay within a hospital setting using the test split of the In-hospital dataset, assessed using regression metrics like MAE, RMSE, and R2.

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 | In-hospital Duration Prediction |
| Dataset (including any stated split) | In-hospital dataset (test) |
| Metric | MAE |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 12 of 12 |
| 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

- [MAE](<https://www.sota2.com/research/sota/in-hospital-duration-prediction-on-in-hospital-dataset-test.md?metric=MAE>): Lower is better; unit: SCALAR.

- [RMSE](<https://www.sota2.com/research/sota/in-hospital-duration-prediction-on-in-hospital-dataset-test.md?metric=RMSE>): Lower is better; unit: SCALAR.

- [R2](<https://www.sota2.com/research/sota/in-hospital-duration-prediction-on-in-hospital-dataset-test.md?metric=R2>): Higher is better; unit: SCALAR.

- [MAPE](<https://www.sota2.com/research/sota/in-hospital-duration-prediction-on-in-hospital-dataset-test.md?metric=MAPE>): Lower is better; unit: PERCENT.

## Recorded results

| Method | MAE | Result date | Report paper |
| --- | --- | --- | --- |
| Qwen3-32B | 33.43 | Not recorded | 69b8e0050636e5bf4afbe987 |
| Quantile Random Forest | 33.8 | Not recorded | 69b8e0050636e5bf4afbe987 |
| XGBoost | 34.7 | Not recorded | 69b8e0050636e5bf4afbe987 |
| HuatuoGPT-o1-7B | 34.98 | Not recorded | 69b8e0050636e5bf4afbe987 |
| Random Forest | 35.01 | Not recorded | 69b8e0050636e5bf4afbe987 |
| Qwen3-8B | 35.19 | Not recorded | 69b8e0050636e5bf4afbe987 |
| Bagging | 36.18 | Not recorded | 69b8e0050636e5bf4afbe987 |
| Gradient Boosting Trees | 36.61 | Not recorded | 69b8e0050636e5bf4afbe987 |
| Ridge Regression | 40.96 | Not recorded | 69b8e0050636e5bf4afbe987 |
| Linear Regression | 41.15 | Not recorded | 69b8e0050636e5bf4afbe987 |
| SVR | 44.63 | Not recorded | 69b8e0050636e5bf4afbe987 |
| Decision Tree | 49.8 | Not recorded | 69b8e0050636e5bf4afbe987 |

### Qwen3-32B

MAE: 33.43. Result ID: 69b901c947f34ce924a11b0b.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0050636e5bf4afbe987.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0050636e5bf4afbe987.md>)

Recorded evaluation configuration: {"Type":"LLM","Model Setting":"RAG-Based Few-Shot (Ours)"}. This record does not assert independent reproduction.

### Quantile Random Forest

MAE: 33.8. Result ID: 69b901c947f34ce924a11b05.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0050636e5bf4afbe987.md>)

Recorded evaluation configuration: {"Type":"ML","Model Setting":"Full-Parameter Training"}. This record does not assert independent reproduction.

### XGBoost

MAE: 34.7. Result ID: 69b901c947f34ce924a11b08.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0050636e5bf4afbe987.md>)

Recorded evaluation configuration: {"Type":"ML","Model Setting":"Full-Parameter Training"}. This record does not assert independent reproduction.

### HuatuoGPT-o1-7B

MAE: 34.98. Result ID: 69b901c947f34ce924a11b09.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0050636e5bf4afbe987.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0050636e5bf4afbe987.md>)

Recorded evaluation configuration: {"Type":"LLM","Model Setting":"RAG-Based Few-Shot (Ours)"}. This record does not assert independent reproduction.

### Random Forest

MAE: 35.01. Result ID: 69b901c947f34ce924a11b04.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0050636e5bf4afbe987.md>)

Recorded evaluation configuration: {"Type":"ML","Model Setting":"Full-Parameter Training"}. This record does not assert independent reproduction.

### Qwen3-8B

MAE: 35.19. Result ID: 69b901c947f34ce924a11b0a.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0050636e5bf4afbe987.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0050636e5bf4afbe987.md>)

Recorded evaluation configuration: {"Type":"LLM","Model Setting":"RAG-Based Few-Shot (Ours)"}. This record does not assert independent reproduction.

### Bagging

MAE: 36.18. Result ID: 69b901c947f34ce924a11b03.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0050636e5bf4afbe987.md>)

Recorded evaluation configuration: {"Type":"ML","Model Setting":"Full-Parameter Training"}. This record does not assert independent reproduction.

### Gradient Boosting Trees

MAE: 36.61. Result ID: 69b901c947f34ce924a11b02.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0050636e5bf4afbe987.md>)

Recorded evaluation configuration: {"Type":"ML","Model Setting":"Full-Parameter Training"}. This record does not assert independent reproduction.

### Ridge Regression

MAE: 40.96. Result ID: 69b901c947f34ce924a11b07.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0050636e5bf4afbe987.md>)

Recorded evaluation configuration: {"Type":"ML","Model Setting":"Full-Parameter Training"}. This record does not assert independent reproduction.

### Linear Regression

MAE: 41.15. Result ID: 69b901c947f34ce924a11b06.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0050636e5bf4afbe987.md>)

Recorded evaluation configuration: {"Type":"ML","Model Setting":"Full-Parameter Training"}. This record does not assert independent reproduction.

### SVR

MAE: 44.63. Result ID: 69b901c947f34ce924a11b00.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0050636e5bf4afbe987.md>)

Recorded evaluation configuration: {"Type":"ML","Model Setting":"Full-Parameter Training"}. This record does not assert independent reproduction.

### Decision Tree

MAE: 49.8. Result ID: 69b901c947f34ce924a11b01.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0050636e5bf4afbe987.md>)

Recorded evaluation configuration: {"Type":"ML","Model Setting":"Full-Parameter Training"}. This record does not assert independent reproduction.

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