# Per-second Sleep Apnea Detection on Stroke Unit 1.0 (Without val patients)

Source: [Per-second Sleep Apnea Detection on Stroke Unit 1.0 (Without val patients)](<https://www.sota2.com/research/sota/per-second-sleep-apnea-detection-on-stroke-unit-1-0-without-val-patients>)

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

Data updated: 2026-02-26T06:04:15.001Z

Evaluation of per-second sleep apnea detection performance using the Stroke Unit 1.0 dataset, specifically restricted to data excluding validation patients, reporting Sensitivity (Sens), Specificity (Spec), Accuracy (Acc), F1, and AUC.

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 | Per-second Sleep Apnea Detection |
| Dataset (including any stated split) | Stroke Unit 1.0 (Without val patients) |
| Metric | Sensitivity |
| 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

- [Sensitivity](<https://www.sota2.com/research/sota/per-second-sleep-apnea-detection-on-stroke-unit-1-0-without-val-patients.md?metric=Sensitivity>): Higher is better; unit: PERCENT.

- [Specificity](<https://www.sota2.com/research/sota/per-second-sleep-apnea-detection-on-stroke-unit-1-0-without-val-patients.md?metric=Specificity>): Higher is better; unit: PERCENT.

- [Accuracy](<https://www.sota2.com/research/sota/per-second-sleep-apnea-detection-on-stroke-unit-1-0-without-val-patients.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/per-second-sleep-apnea-detection-on-stroke-unit-1-0-without-val-patients.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [AUC](<https://www.sota2.com/research/sota/per-second-sleep-apnea-detection-on-stroke-unit-1-0-without-val-patients.md?metric=AUC>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Sensitivity | Result date | Report paper |
| --- | --- | --- | --- |
| CNN + LSTM | 65.5 | Not recorded | 68fa6e901e209131cea40a57 |
| CNN + LSTM | 64.3 | Not recorded | 68fa6e901e209131cea40a57 |
| LSTM | 62.4 | Not recorded | 68fa6e901e209131cea40a57 |
| ResNet | 10.7 | Not recorded | 68fa6e901e209131cea40a57 |

### CNN + LSTM

Sensitivity: 65.5. Result ID: 699035743a6c314849feeb75.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e901e209131cea40a57.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e901e209131cea40a57.md>)

[Implementation](<https://github.com/dslab-uniud/OSAS>)

Recorded evaluation configuration: {"Model":"CNN + LSTM","Signal":"ECG + SpO2","Evaluation protocol":"Leave-one-patient-out CV"}. This record does not assert independent reproduction.

### CNN + LSTM

Sensitivity: 64.3. Result ID: 699035743a6c314849feeb74.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e901e209131cea40a57.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e901e209131cea40a57.md>)

[Implementation](<https://github.com/dslab-uniud/OSAS>)

Recorded evaluation configuration: {"Model":"CNN + LSTM","Signal":"ECG","Evaluation protocol":"Leave-one-patient-out CV"}. This record does not assert independent reproduction.

### LSTM

Sensitivity: 62.4. Result ID: 699035743a6c314849feeb73.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e901e209131cea40a57.md>)

Recorded evaluation configuration: {"Model":"LSTM","Signal":"SpO2","Evaluation protocol":"Leave-one-patient-out CV"}. This record does not assert independent reproduction.

### ResNet

Sensitivity: 10.7. Result ID: 699035743a6c314849feeb72.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e901e209131cea40a57.md>)

Recorded evaluation configuration: {"Model":"ResNet","Signal":"ECG","Evaluation protocol":"Leave-one-patient-out CV"}. This record does not assert independent reproduction.

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