Analysis and Identification of Sleep Apnea by availing Random Forest and SVM

Sleep problems have been the subject of extensive research throughout history. One of the significant sleep disorders that endanger human life is sleep apnea, which we commonly encounter today. This incident, which happens while the person is sleeping, also has an impact on their daily lives. The obstructive sleep apnea syndrome (Disease) is a respiratory tract state that enacts roughly 2% of women and almost 4% of males. The ability to learn well, maintain well-being, and even carry out daily tasks depend on getting enough sleep. Sleep-related conditions like drowsiness sleep disruption and troubled legs are becoming more common. Obstructive respiratory condition called sleep apnea reduces the quality of sleep by triggering breathing stoppage. The apnea syndrome is characterized by an inconsistent respiratory delay or decrease in airflow when the patient is sleeping. A significant portion of the population is impacted by the sleep disorder sleep apnea. In proposed work, we suggest a machine learning model and web application on Django framework to forecast the systemic sleep apnea disorder. Here, the system model is built using the machine learning algorithms such as Random Forest and SVM Classifiers. Next, we use the web application component of the Django Framework to anticipate the patient's ailment, such as whether sleep apnea is present or absent. If apnea is present, the result is shown to the system's doctor for consultation. The results of experiments demonstrated the system's improved performance.