Find in Library
Search millions of books, articles, and more
Indexed Open Access Databases
Apnea Detection in Polysomnographic Recordings Using Machine Learning Techniques
oleh: Marek Piorecky, Martin BartoĊ, Vlastimil Koudelka, Jitka Buskova, Jana Koprivova, Martin Brunovsky, Vaclava Piorecka
Format: | Article |
---|---|
Diterbitkan: | MDPI AG 2021-12-01 |
Deskripsi
Sleep disorders are diagnosed in sleep laboratories by polysomnography, a multi-parameter examination that monitors biological signals during sleep. The subsequent evaluation of the obtained records is very time-consuming. The goal of this study was to create an automatic system for evaluation of the airflow and SpO<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mrow></mrow><mn>2</mn></msub></semantics></math></inline-formula> channels of polysomnography records, through the use of machine learning techniques and a large database, for apnea and desaturation detection (which is unusual in other studies). To that end, a convolutional neural network (CNN) was designed using hyperparameter optimization. It was then trained and tested for apnea and desaturation. The proposed CNN was compared with the commonly used <i>k</i>-nearest neighbors (<i>k</i>-NN) method. The classifiers were designed based on nasal airflow and blood oxygen saturation signals. The final neural network accuracy for apnea detection reached 84%, and that for desaturation detection was 74%, while the <i>k</i>-NN classifier reached accuracies of 83% and 64% for apnea detection and desaturation detection, respectively.