AIOSA: An approach to the automatic identification of obstructive sleep apnea events based on deep learning

作者：

Highlights：

• Novel neural network for OSAS detection, based on routinely recorded vital signs

• Extraction of temporal relationships through summarization of raw physiological signals

• Evaluation on a real-world stroke unit dataset, composed of unselected patients

• OSAS events tagged at one second granularity, enabling clinical interpretability of the model outcomes

摘要

•Novel neural network for OSAS detection, based on routinely recorded vital signs•Extraction of temporal relationships through summarization of raw physiological signals•Evaluation on a real-world stroke unit dataset, composed of unselected patients•OSAS events tagged at one second granularity, enabling clinical interpretability of the model outcomes

论文关键词：AI for healthcare,Convolutional neural networks,Deep learning,Obstructive sleep apnea,Time-series

论文评审过程：Received 22 March 2021, Revised 23 June 2021, Accepted 24 June 2021, Available online 2 July 2021, Version of Record 29 July 2021.

论文官网地址：https://doi.org/10.1016/j.artmed.2021.102133