SLEEP DISORDER SCORING AUTOMATED USING ADVANCED DATA SCIENCE AND MACHINE LEARNING TECHNIQUES

Abstract

Sleep disorders are now being considered as a major issue of public health concern impacting on millions of people across the world. Insomnia, sleep apnea, restless leg syndrome are some of the conditions that may have a serious effect on physical health, mental health, and productivity in everyday life. To be effectively treated and prevent development of long-term health complications, these disorders should be detected and identified on the initial stage. Machine learning methods have become enthusiastic tools to analyzing large datasets in healthcare and finding concealed patterns in sleep behavior in recent years. The study examines how machine learning algorithms can be used to identify and categorize sleep disorders. It is trained on a dataset of physiological and lifestyle features including the duration of sleep, the level of stress, the heart rate, the body mass index, and activity during a day, all of which belong to a healthcare dataset. Some of the supervised machine learning algorithms such as Decision Tree, Random Forest, Support Vector Machine and Logistic Regression are applied and tested to establish their usefulness in predicting patterns of sleep disorders. The outcomes of the experiments prove that machine learning models can be used to make accurate predictions and help healthcare specialists to diagnose early. Comparison of implemented algorithms reveals their accuracy and precision, recall and F1-score.

The results indicate that machine learning methods can be applied to the healthcare systems in order to improve the detection of sleep disorders and assist the clinicians with making their decisions. On the whole, this paper adds to the emerging body of research on the topic of intelligent healthcare systems by showing that machine learning solutions have a potential effect on the process of diagnosing and treating sleep disorders.