# Symptom trajectory classification on CES-D personalized threshold label (test)

Source: [Symptom trajectory classification on CES-D personalized threshold label (test)](<https://www.sota2.com/research/sota/symptom-trajectory-classification-on-ces-d-personalized-threshold-label-test>)

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

Data updated: 2026-04-28T07:22:19.423Z

Evaluation of models for Symptom trajectory classification on the CES-D personalized threshold dataset (test split), focusing on outcomes like worsening, improving, and stable states.

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 | Symptom trajectory classification |
| Dataset (including any stated split) | CES-D personalized threshold label N = 411; 10% worsening, 12% improving, 78% stable (test) |
| Metric | Balanced Accuracy |
| 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

- [Balanced Accuracy](<https://www.sota2.com/research/sota/symptom-trajectory-classification-on-ces-d-personalized-threshold-label-test.md?metric=Balanced%20Accuracy>): Higher is better; unit: PERCENT.

- [AUC (OvR)](<https://www.sota2.com/research/sota/symptom-trajectory-classification-on-ces-d-personalized-threshold-label-test.md?metric=AUC%20(OvR)>): Higher is better; unit: PERCENT.

- [Sensitivity (worsening)](<https://www.sota2.com/research/sota/symptom-trajectory-classification-on-ces-d-personalized-threshold-label-test.md?metric=Sensitivity%20(worsening)>): Higher is better; unit: PERCENT.

- [PPV (worsening)](<https://www.sota2.com/research/sota/symptom-trajectory-classification-on-ces-d-personalized-threshold-label-test.md?metric=PPV%20(worsening)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Balanced Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| XGBoost | 62 | Not recorded | 69f03f1855a3c32af89fa09a |
| SVM | 62 | Not recorded | 69f03f1855a3c32af89fa09a |
| ElasticNet | 60.3 | Not recorded | 69f03f1855a3c32af89fa09a |
| LightGBM | 58.6 | Not recorded | 69f03f1855a3c32af89fa09a |
| Regression to person's mean | 53.3 | Not recorded | 69f03f1855a3c32af89fa09a |
| Person-specific modal class | 33.3 | Not recorded | 69f03f1855a3c32af89fa09a |
| Predict all stable | 33.3 | Not recorded | 69f03f1855a3c32af89fa09a |
| Last value carried forward | 32.2 | Not recorded | 69f03f1855a3c32af89fa09a |

### XGBoost

Balanced Accuracy: 62. Result ID: 69f0602247f34ce924d5d6de.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f1855a3c32af89fa09a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f03f1855a3c32af89fa09a.md>)

Recorded evaluation configuration: {"Model Type":"Machine Learning"}. This record does not assert independent reproduction.

### SVM

Balanced Accuracy: 62. Result ID: 69f0602247f34ce924d5d6e0.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f1855a3c32af89fa09a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f03f1855a3c32af89fa09a.md>)

Recorded evaluation configuration: {"Model Type":"Machine Learning"}. This record does not assert independent reproduction.

### ElasticNet

Balanced Accuracy: 60.3. Result ID: 69f0602247f34ce924d5d6e1.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f1855a3c32af89fa09a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f03f1855a3c32af89fa09a.md>)

Recorded evaluation configuration: {"Model Type":"Machine Learning","Highlight":"Best AUC"}. This record does not assert independent reproduction.

### LightGBM

Balanced Accuracy: 58.6. Result ID: 69f0602247f34ce924d5d6df.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f1855a3c32af89fa09a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f03f1855a3c32af89fa09a.md>)

Recorded evaluation configuration: {"Model Type":"Machine Learning"}. This record does not assert independent reproduction.

### Regression to person's mean

Balanced Accuracy: 53.3. Result ID: 69f0602247f34ce924d5d6e2.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f1855a3c32af89fa09a.md>)

Recorded evaluation configuration: {"Model Type":"Rule-based baseline","Highlight":"Strongest baseline"}. This record does not assert independent reproduction.

### Person-specific modal class

Balanced Accuracy: 33.3. Result ID: 69f0602247f34ce924d5d6e4.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f1855a3c32af89fa09a.md>)

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

### Predict all stable

Balanced Accuracy: 33.3. Result ID: 69f0602247f34ce924d5d6e5.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f1855a3c32af89fa09a.md>)

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

### Last value carried forward

Balanced Accuracy: 32.2. Result ID: 69f0602247f34ce924d5d6e3.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f1855a3c32af89fa09a.md>)

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

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