---

AIOSA: An Approach to the Automatic Identification of Obstructive Sleep Apnea Events based on Deep Learning

Description

This repository contains the source code related to our paper "AIOSA: An Approach to the Automatic Identification of Obstructive SleepApnea Events based on Deep Learning", authored by Andrea Bernardini, Andrea Brunello, Gian Luigi Gigli, Angelo Montanari, and Nicola Saccomanno.

The code is designed to run on Pytorch 1.6, exploiting TPUs.

Citation

@article{DBLP:journals/artmed/BernardiniBGMS21,
  author    = {Andrea Bernardini and
               Andrea Brunello and
               Gian Luigi Gigli and
               Angelo Montanari and
               Nicola Saccomanno},
  title     = {{AIOSA:} An approach to the automatic identification of obstructive
               sleep apnea events based on deep learning},
  journal   = {Artif. Intell. Medicine},
  volume    = {118},
  pages     = {102133},
  year      = {2021},
  url       = {https://doi.org/10.1016/j.artmed.2021.102133},
  doi       = {10.1016/j.artmed.2021.102133},
  timestamp = {Mon, 03 Jan 2022 22:00:55 +0100},
  biburl    = {https://dblp.org/rec/journals/artmed/BernardiniBGMS21.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

Dataset

The novel dataset that has been used for this work, has been made avilable on figshare. All the details can be found in the paper OSASUD: A dataset of stroke unit recordings for the detection of Obstructive Sleep Apnea Syndrome. Please, cite it using the following format

Citation

@article{bernardini2022osasud,
  title={OSASUD: A dataset of stroke unit recordings for the detection of Obstructive Sleep Apnea Syndrome},
  author={Bernardini, Andrea and Brunello, Andrea and Gigli, Gian Luigi and Montanari, Angelo and Saccomanno, Nicola},
  journal={Scientific Data},
  volume={9},
  number={1},
  pages={1--10},
  year={2022},
  publisher={Nature Publishing Group}
}