# Sleep Apnea Detection

## Model Overview

The following table provides the latest pre-trained models for sleep apnea. Below we also provide additional details including training configuration, accuracy metrics, and hardware performance results for the models.

| NAME             | LOCATION | # CLASSES | MODEL   | PARAMS | FLOPS   | ACCURACY | F1    |
| ---------------- | -------- | --------- | ------- | ------ | ------- | -------- | ----- |
| __SA-2-TCN-SM__  | Wrist    | 2         | TCN     | 5K     | 20M/hr  | 91.0%    | 91.0% |

## Model Details

The __SA-2-TCN-SM__ model is a 2-stage sleep apnea detection model that uses a Temporal convolutional network (TCN). The model is trained on PPG sensor data collected from the wrist and is able to locate apnea/hypopnea events.

- **Location**: Wrist
- **Classes**: Normal, Apnea
- **Frame Size**: 10 minutes
- **Datasets**: [MESA](https://ambiqai.github.io/sleepkit/datasets/mesa/)
- **Features**: [FS-W-P-5](https://ambiqai.github.io/sleepkit/features/fs_w_p_5/)

## Model Performance

The following plots show the model's performance in detecting apnea/hypopnea events. The first plot shows the confusion matrix for apnea detection.

The following plot shows the model's ability to detect AHI (Apnea-Hypopnea Index) compared to the ground truth AHI values. The x-axis represents the true AHI values, while the y-axis represents the predicted AHI values. The plot shows a strong correlation between the true and predicted AHI values.

The following table provides the corresponding confusion matrix for AHI.

---

## EVB Performance

The following table provides the latest performance results when running on Apollo4 Plus EVB. These results are obtained using neuralSPOTs [Autodeploy tool](https://ambiqai.github.io/neuralSPOT/docs/From%20TF%20to%20EVB%20-%20testing%2C%20profiling%2C%20and%20deploying%20AI%20models.html). From neuralSPOT repo, the following command can be used to capture EVB results via Autodeploy:

```console title="Terminal"
python -m ns_autodeploy \
--tflite-filename model.tflite \
--model-name model \
--cpu-mode 192 \
--arena-size-scratch-buffer-padding 0 \
--max-arena-size 60 \
```

| Name            | Params   | FLOPS   | Metric     | Time     | Arena | Energy     |
| --------------- | -------- | ------- | ---------- | -------- | ----- | ---------- |
| __SA-2-TCN-SM__ | 10K      | 44M/hr  | 91.0% F1   | 1.8s/hr  |  61KB |  17.0mJ/hr |

## Downloads

| Asset                                                                | Description                   |
| -------------------------------------------------------------------- | ----------------------------- |
| [configuration.json](https://ambiqai-model-zoo.s3.us-west-2.amazonaws.com/sleepkit/apnea/sa-2-tcn-sm/latest/configuration.json)   | Configuration file            |
| [model.keras](https://ambiqai-model-zoo.s3.us-west-2.amazonaws.com/sleepkit/apnea/sa-2-tcn-sm/latest/model.keras)            | Keras Model file              |
| [model.tflite](https://ambiqai-model-zoo.s3.us-west-2.amazonaws.com/sleepkit/apnea/sa-2-tcn-sm/latest/model.tflite)       | TFLite Model file             |
| [metrics.json](https://ambiqai-model-zoo.s3.us-west-2.amazonaws.com/sleepkit/apnea/sa-2-tcn-sm/latest/metrics.json)       | Metrics file                  |