Opin vísindi

Anomaly detection in sleep : detecting mouth breathing in children

Anomaly detection in sleep : detecting mouth breathing in children

Title: Anomaly detection in sleep : detecting mouth breathing in children
Author: Biedebach, Luka
Óskarsdóttir, María   orcid.org/0000-0001-5095-5356
Arnardóttir, Erna Sif
Sigurdardóttir, Sigridur Erla
Clausen, Michael Valur
Sigurðardóttir, Sigurveig Þ
Serwatko, Marta
Islind, Anna Sigríður
Date: 2023-11-13
Language: English
Scope: 1350189
Department: Department of Computer Science
Department of Engineering
Other departments
Series: Data Mining and Knowledge Discovery; ()
ISSN: 1384-5810
DOI: 10.1007/s10618-023-00985-x
Subject: Barnalæknisfræði; Ónæmisfræði; Verkfræðingar; Anomaly detection; Machine learning; Mouth breathing; Sleep; Information Systems; Computer Science Applications; Computer Networks and Communications
URI: https://hdl.handle.net/20.500.11815/4575

Show full item record


Biedebach , L , Óskarsdóttir , M , Arnardóttir , E S , Sigurdardóttir , S E , Clausen , M V , Sigurðardóttir , S Þ , Serwatko , M & Islind , A S 2023 , ' Anomaly detection in sleep : detecting mouth breathing in children ' , Data Mining and Knowledge Discovery . https://doi.org/10.1007/s10618-023-00985-x


Identifying mouth breathing during sleep in a reliable, non-invasive way is challenging and currently not included in sleep studies. However, it has a high clinical relevance in pediatrics, as it can negatively impact the physical and mental health of children. Since mouth breathing is an anomalous condition in the general population with only 2% prevalence in our data set, we are facing an anomaly detection problem. This type of human medical data is commonly approached with deep learning methods. However, applying multiple supervised and unsupervised machine learning methods to this anomaly detection problem showed that classic machine learning methods should also be taken into account. This paper compared deep learning and classic machine learning methods on respiratory data during sleep using a leave-one-out cross validation. This way we observed the uncertainty of the models and their performance across participants with varying signal quality and prevalence of mouth breathing. The main contribution is identifying the model with the highest clinical relevance to facilitate the diagnosis of chronic mouth breathing, which may allow more affected children to receive appropriate treatment.


Publisher Copyright: © 2023, The Author(s).

Files in this item

This item appears in the following Collection(s)