# Hourly deterioration prediction on ICU hourly deterioration prediction (val)

Source: [Hourly deterioration prediction on ICU hourly deterioration prediction (val)](<https://www.sota2.com/research/sota/hourly-deterioration-prediction-on-icu-hourly-deterioration-prediction-val>)

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

Data updated: 2026-03-17T10:34:57.432Z

Evaluation of models performing hourly deterioration prediction using the validation split of the ICU hourly deterioration prediction dataset, assessed using AUROC.

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 | Hourly deterioration prediction |
| Dataset (including any stated split) | ICU hourly deterioration prediction (val) |
| Metric | AUROC |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [AUROC](<https://www.sota2.com/research/sota/hourly-deterioration-prediction-on-icu-hourly-deterioration-prediction-val.md?metric=AUROC>): Higher is better; unit: SCALAR.

## Recorded results

| Method | AUROC | Result date | Report paper |
| --- | --- | --- | --- |
| Multimodal | 0.7914 | Not recorded | 69b8e0220636e5bf4afbec0c |
| Structured-only | 0.7651 | Not recorded | 69b8e0220636e5bf4afbec0c |
| XGBoost | 0.7481 | Not recorded | 69b8e0220636e5bf4afbec0c |
| Logistic Regression | 0.7339 | Not recorded | 69b8e0220636e5bf4afbec0c |
| Text-only | 0.5137 | Not recorded | 69b8e0220636e5bf4afbec0c |

### Multimodal

AUROC: 0.7914. Result ID: 69b92e3d47f34ce924a28ffe.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0220636e5bf4afbec0c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0220636e5bf4afbec0c.md>)

Recorded evaluation configuration: {"Category":"Deep Learning Models"}. This record does not assert independent reproduction.

### Structured-only

AUROC: 0.7651. Result ID: 69b92e3d47f34ce924a28fff.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0220636e5bf4afbec0c.md>)

Recorded evaluation configuration: {"Category":"Deep Learning Models"}. This record does not assert independent reproduction.

### XGBoost

AUROC: 0.7481. Result ID: 69b92e3d47f34ce924a29001.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0220636e5bf4afbec0c.md>)

Recorded evaluation configuration: {"Category":"Classical Baselines"}. This record does not assert independent reproduction.

### Logistic Regression

AUROC: 0.7339. Result ID: 69b92e3d47f34ce924a29002.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0220636e5bf4afbec0c.md>)

Recorded evaluation configuration: {"Category":"Classical Baselines"}. This record does not assert independent reproduction.

### Text-only

AUROC: 0.5137. Result ID: 69b92e3d47f34ce924a29000.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0220636e5bf4afbec0c.md>)

Recorded evaluation configuration: {"Category":"Deep Learning Models"}. This record does not assert independent reproduction.

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