Summary of Sleepppg-net2: Deep Learning Generalization For Sleep Staging From Photoplethysmography, by Shirel Attia et al.
SleepPPG-Net2: Deep learning generalization for sleep staging from photoplethysmography
by Shirel Attia, Revital Shani Hershkovich, Alissa Tabakhov, Angeleene Ang, Sharon Haimov, Riva Tauman, Joachim A. Behar
First submitted to arxiv on: 10 Apr 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Signal Processing (eess.SP)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A deep learning model called SleepPPG-Net2 is developed for four-class sleep staging (wake, light, deep, and REM) from photoplethysmogram (PPG) time series. Six sleep datasets, containing 2,574 patient recordings, are used to train the model. The approach aims to create a generalizable representation through multi-source domain training. SleepPPG-Net2 is benchmarked against two state-of-the-art models and shows consistently higher performance, with generalization performance improving by up to 19%. Performance disparities are observed in relation to age, sex, and sleep apnea severity. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Sleep researchers have created a new way to tell if someone is sleeping soundly or not. They used special heart rate sensors called photoplethysmograms (PPGs) to figure out what stage of sleep people were in – wakeful, lightly sleeping, deeply sleeping, or having those crazy dream-filled REM sleep moments. The researchers made a special computer program that can learn from lots of different PPG readings and make good predictions about which stage of sleep someone is in. This new program is called SleepPPG-Net2. |
Keywords
* Artificial intelligence * Deep learning * Generalization * Time series
