Research on the Adoption of Machine Learning in the Domain of Sleep Disorder Detection

Healthy sleep is very important for people's vitality and physical health. However, due to the need for socio-economic development and changes in people's lifestyles, people suffer from sleep disorder problems. Timely detection of sleep disorders is important for people's lives afterwards. This study collected and evaluated Laksika Tharmalingam data using a variety of machine learning techniques, including Random Forests, Decision Trees, and Logistic Regression (LR) to find out the relationship between 11 factors including lifestyle factors and sleep disorders. The research found that the LR algorithm produced the best model with 89.33 per cent accuracy, 90.24 per cent precision, 89.33 per cent recall, and an f1-score of 0.89. Lifestyle-related factors such as occupation, sleep duration, and level of physical activity all have an impact on whether or not a sleep disorder develops. This paper can serve as a valuable resource and provide insightful information for future research endeavors focused on sleep disorders, contributing to a deeper understanding of the complexities surrounding these conditions and potentially guiding the development of more effective interventions and treatments.