Sleep Disorder Detection Using Deep Learning

Since sleep disorders can have a major impact on general well-being, classifying them is crucial to enhancing human health. Experts have historically categorized the stages of sleep, but this is a challenging and error-prone process. By more efficiently assessing, tracking, and diagnosing sleep disturbances, accurate machine learning algorithms (MLAs) can be beneficial. This study uses the publicly accessible Sleep Health and Lifestyle Dataset to evaluate deep learning algorithms and traditional MLAs for the categorization of sleep disorders. Thirteen characteristics pertaining to sleep and everyday activities are included in the 400row dataset. A genetic algorithm was employed to adjust the parameters of the machine learning models in order to maximize their performance. The Artificial Neural Network (ANN) method was evaluated in the study. Significant performance differences were found in the results, with the ANN obtaining the best classification accuracy of 92.92%. In addition, it outperformed the other algorithms tested with high precision (92.01%), recall (93.80%), and F1-score (91.93%).