Automated Sleep Disorder Detection Using Machine Learning and Deep Learning Model

Sleep disorders, including insomnia, sleep apnea, etc. as significant issues of global health, and becoming more widely recognized, affecting psychological and physical health. While traditional such diagnostic techniques as polysomnography (PSG) offer precision. they are not easily, costly, and time-consuming results. Accessible. This paper proposes a solution to these problems. Hybrid ensemble framework improving with Machine Learning (ML), and Deep Learning (DL) methods of automated sleep disorder. Detection. It is based on the data of behavioral lifestyle and. physiological ECG records to deliver a comprehensive diagnosis. Gradient Boosting (GB) and Artificial Neural Networks (ANN) are. used in the analysis of lifestyle characteristics, Support Vector Machine. SVM models and CNN models deal with (SVM) and Convolutional Neural Network (CNN) models. ECG signal processing. Hyper parameters are adjusted with the help of. The outputs of each model and Genetic Algorithms (GA) are genetic algorithms. Integrated to come up with final predictions. The ensemble approach has higher classification performance than individual models and assists real time forecasting using a FastAPI web interface. This method is pointed out by the results of the experiment. The early solution to the lack of scalability, cost-effectiveness, and pragmatism. Identification of sleep disorders.