M. V. Chandrashekhar . N. Pradeep

Department of Computer Science and Engineering, Bapuji Institute of Engineering and Technology, Davangere 577004, Affiliated to Visvesvaraya Technological University, Belagavi-590018, Karnataka, India, E-mail: chandru.cmv@gmail.com Department of Computer Science and Engineering, Bapuji Institute of Engineering and Technology, Davangere 577004, Affiliated to Visvesvaraya Technological University, Belagavi-590018, Karnataka, India, E-mail: nmnpradeep@gmail.com

Received in final form on June 25, 2023

Abstract
In recent years, sleep disturbances have emerged as an early indicator of the development of non-communicable diseases (NCDs). To formally identify sleep problems, doctors use Polysomnography (PSG). Due to its exorbitant price, the PSG is not widely available in hospitals. Having a variety of sensors attached to a patient can be intrusive. The massive amounts of PSG data also necessitate the expertise of sleep doctors to decipher. Scientists are looking for new ways to detect sleep disorders. In this review work, state-of-the-art research work related to sleep disorders analysis and classification has been systematically structured and presented. To be more specific, this literature study is centered on currently prevalent detection approaches of sleep disorders based on Machine Learning and Deep Learning technologies. This literature assessment leads to conclude that future sleep problem detection systems will benefit greatly from the abundance of both types and quantities of labelled data, as this will guide the selection of the AI algorithm that caters to the requirement of a relevant decision support system.

Keywords
Polysomnography, Sleep Disorders, Obstructive Sleep Apnea (OSA), Decision Support System, Machine Learning, Deep Learning.

Cite This Article
M. V. Chandrashekhar . N. Pradeep, Ensemble Machine Learning Techniques for Analysis and Classification of Sleep Disorders – A Review, J. Innovation Sciences and Sustainable Technologies, 3(3)(2023), 183 - 196. https://doie.org/10.0904/JISST.2023389939

    105    30    Download