Monitoring and Detecting of Obstructive Sleep Apnoea Episodes
Obstructive sleep apnoea (OSA), or in short apnoea, is a breathing disorder which can be observed during sleep, caused by the partial or complete constriction of the patient’s upper airway.
About 4% of the general population suffer from this condition to some extent, and it is estimated that fewer than 25% of OSA sufferers are actually aware that they have this problem.
Assessing sleep quality and investigating the presence of OSA is therefore important in terms of an improvement in patient health conditions and the reduction in mortality and healthcare costs. In fact this disorder causes hypoxemia, asphyxia, and awakenings, and has immediate consequences, such as an increased heart rate and high blood pressure, as well as long-term symptoms affecting the quality of life, such as extreme fatigue, poor concentration, a compromised immune system, slower reaction times, and cardio/cerebrovascular problems.
In this regard, our research aimes at developing a simple mobile system that provides an easy, reliable, inexpensive, transportable, and fast approach to assist OSA patients. This approach is based on the automatic extraction of explicit knowledge in the form of a set of IF…THEN rules personalized for each patient. This approach is based on the automatic extraction of explicit knowledge in the form of a set of IF…THEN rules personalized for each patient. These rules detect the occurrence of OSA episodes and contain parameters related to Heart Related Variability (HRV). These rules are extracted offline starting from single-lead ECG recordings by means of a binary classification task performed by a Differential Evolution (DE) algorithm.
- G. Sannino, I. De Falco, G. De Pietro, "An automatic rule extraction-based approach to support OSA events detection in an mHealth system," IEEE Journal of Biomedical and Health Informatics, March 2014 - doi:10.1109/JBHI.2014.2311325.
- G. Sannino, I. De Falco, G. De Pietro, "Monitoring Obstructive Sleep Apnea by means of a real-time mobile system based on the automatic extraction of sets of rules through Differential Evolution", Journal of Biomedical Informatics, March 2014, ISSN 1532-0464, http://dx.doi.org/10.1016/j.jbi.2014.02.015.
- G. Sannino, I. De Falco and G. De Pietro, "Detecting Obstructive Sleep Apnea events in a realtime mobile monitoring system through automatically extracted sets of rules", in Proceedings of the 15th IEEE International Conference on e-Health Networking, Application and Services (Healthcom 2013), Lisbon, Portugal.
- G. Sannino, I. De Falco and G. De Pietro, "Automatic extraction of effective rule sets for Obstructive Sleep Apnea detection for a real-time mobile monitoring system", in Proceedings of the 14th IEEE International Conference on Information Reuse and Integration (IRI2013), San Francisco (CA)