# Disease Prediction on Korean AI Hub dataset (temporal cross-validation (3 folds))

Source: [Disease Prediction on Korean AI Hub dataset (temporal cross-validation (3 folds))](<https://www.sota2.com/research/sota/disease-prediction-on-korean-ai-hub-dataset-temporal-cross-validation-3-folds>)

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

Data updated: 2026-03-17T10:16:15.202Z

Evaluation of Disease Prediction performance on the Korean AI Hub dataset using temporal cross-validation (3 folds), reporting metrics like F1, Precision, Recall, and 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 | Disease prediction |
| Dataset (including any stated split) | Korean AI Hub dataset (temporal cross-validation (3 folds)) |
| Metric | F1 Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [F1 Score](<https://www.sota2.com/research/sota/disease-prediction-on-korean-ai-hub-dataset-temporal-cross-validation-3-folds.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [Precision](<https://www.sota2.com/research/sota/disease-prediction-on-korean-ai-hub-dataset-temporal-cross-validation-3-folds.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/disease-prediction-on-korean-ai-hub-dataset-temporal-cross-validation-3-folds.md?metric=Recall>): Higher is better; unit: PERCENT.

- [AUROC](<https://www.sota2.com/research/sota/disease-prediction-on-korean-ai-hub-dataset-temporal-cross-validation-3-folds.md?metric=AUROC>): Higher is better; unit: PERCENT.

## Recorded results

| Method | F1 Score | Result date | Report paper |
| --- | --- | --- | --- |
| STAG-CN | 60.7 | Not recorded | 69b8e0190636e5bf4afbeb0b |
| GCN-only | 60.7 | Not recorded | 69b8e0190636e5bf4afbeb0b |
| Threshold | 41.8 | Not recorded | 69b8e0190636e5bf4afbeb0b |
| Graph WaveNet | 27.4 | Not recorded | 69b8e0190636e5bf4afbeb0b |
| DCRNN | 27.4 | Not recorded | 69b8e0190636e5bf4afbeb0b |
| LSTM | 0 | Not recorded | 69b8e0190636e5bf4afbeb0b |

### STAG-CN

F1 Score: 60.7. Result ID: 69b929de47f34ce924a26d9a.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0190636e5bf4afbeb0b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0190636e5bf4afbeb0b.md>)

Recorded evaluation configuration: {"Window":"7 days"}. This record does not assert independent reproduction.

### GCN-only

F1 Score: 60.7. Result ID: 69b929de47f34ce924a26d9b.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0190636e5bf4afbeb0b.md>)

Recorded evaluation configuration: {"Layers":"2","History":"None"}. This record does not assert independent reproduction.

### Threshold

F1 Score: 41.8. Result ID: 69b929de47f34ce924a26d9e.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0190636e5bf4afbeb0b.md>)

Recorded evaluation configuration: {"Type":"Rule-based classifier"}. This record does not assert independent reproduction.

### Graph WaveNet

F1 Score: 27.4. Result ID: 69b929de47f34ce924a26d9c.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0190636e5bf4afbeb0b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65d51e209131cea0c8f9.md>)

[Implementation](<https://github.com/nnzhan/Graph-WaveNet>)

Recorded evaluation configuration: {"Ch":"32","layers":"2","dilation":"{1, 2}","K":"2"}. This record does not assert independent reproduction.

### DCRNN

F1 Score: 27.4. Result ID: 69b929de47f34ce924a26d9d.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0190636e5bf4afbeb0b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64131e209131cea0293d.md>)

[Implementation](<https://github.com/liyaguang/DCRNN>)

Recorded evaluation configuration: {"K":"2","Ch":"32","layers":"1"}. This record does not assert independent reproduction.

### LSTM

F1 Score: 0. Result ID: 69b929de47f34ce924a26d9f.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0190636e5bf4afbeb0b.md>)

Recorded evaluation configuration: {"layers":"2"}. This record does not assert independent reproduction.

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