# AD vs HC classification on EEG AD vs HC (summary)

Source: [AD vs HC classification on EEG AD vs HC (summary)](<https://www.sota2.com/research/sota/ad-vs-hc-classification-on-eeg-ad-vs-hc-summary>)

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

Data updated: 2026-05-29T09:54:02.417Z

Evaluation of binary classification performance distinguishing Alzheimer's Disease (AD) subjects from Healthy Control (HC) subjects using the EEG AD vs HC (summary) dataset, utilizing specialized metrics like SRC balanced accuracy and Top-2 Margin.

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 | AD vs HC classification |
| Dataset (including any stated split) | EEG AD vs HC (summary) |
| Metric | SRC Balanced Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [SRC Balanced Accuracy](<https://www.sota2.com/research/sota/ad-vs-hc-classification-on-eeg-ad-vs-hc-summary.md?metric=SRC%20Balanced%20Accuracy>): Higher is better; unit: PERCENT.

- [Top-2 Margin](<https://www.sota2.com/research/sota/ad-vs-hc-classification-on-eeg-ad-vs-hc-summary.md?metric=Top-2%20Margin>): Higher is better; unit: SCALAR.

- [Effective Rank](<https://www.sota2.com/research/sota/ad-vs-hc-classification-on-eeg-ad-vs-hc-summary.md?metric=Effective%20Rank>): Higher is better; unit: SCALAR.

- [Max Cohesion](<https://www.sota2.com/research/sota/ad-vs-hc-classification-on-eeg-ad-vs-hc-summary.md?metric=Max%20Cohesion>): Higher is better; unit: PERCENT.

## Recorded results

| Method | SRC Balanced Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Geometry-shaped | 87.1 | Not recorded | 6a191dcfdbd7150506f82a61 |
| CE-shaped | 85.9 | Not recorded | 6a191dcfdbd7150506f82a61 |
| Geometry-shaped | 85.1 | Not recorded | 6a191dcfdbd7150506f82a61 |
| Raw EEG | 82.1 | Not recorded | 6a191dcfdbd7150506f82a61 |

### Geometry-shaped

SRC Balanced Accuracy: 87.1. Result ID: 6a196220fbc373592c143248.

[Reporting paper](<https://www.sota2.com/research/paper/6a191dcfdbd7150506f82a61.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a191dcfdbd7150506f82a61.md>)

Recorded evaluation configuration: {"Selection strategy":"acc-tied, margin-selected","Inference method":"SRC (OMP-s with s = 30)"}. This record does not assert independent reproduction.

### CE-shaped

SRC Balanced Accuracy: 85.9. Result ID: 6a196220fbc373592c143249.

[Reporting paper](<https://www.sota2.com/research/paper/6a191dcfdbd7150506f82a61.md>)

Recorded evaluation configuration: {"Representation":"reference","Inference method":"SRC (OMP-s with s = 30)"}. This record does not assert independent reproduction.

### Geometry-shaped

SRC Balanced Accuracy: 85.1. Result ID: 6a196220fbc373592c143247.

[Reporting paper](<https://www.sota2.com/research/paper/6a191dcfdbd7150506f82a61.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a191dcfdbd7150506f82a61.md>)

Recorded evaluation configuration: {"Selection strategy":"avg over grid","Inference method":"SRC (OMP-s with s = 30)"}. This record does not assert independent reproduction.

### Raw EEG

SRC Balanced Accuracy: 82.1. Result ID: 6a196220fbc373592c143246.

[Reporting paper](<https://www.sota2.com/research/paper/6a191dcfdbd7150506f82a61.md>)

Recorded evaluation configuration: {"Representation":"connectivity features","Inference method":"SRC (OMP-s with s = 30)"}. This record does not assert independent reproduction.

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