Sleep is a fundamental aspect of human life, constituting approximately one-third of our daily routine. Adequate sleep is vital for physical recovery and overall well-being. However, issues like sleep apnea and insomnia can disrupt these restorative processes, resulting in diminished daily functioning and long-term health risks. The prevalence of sleep disorders has risen due to modern lifestyle challenges, highlighting the necessity for effective diagnostic methods.
This research focuses on employing Machine Learning (ML) techniques, specifically the Random Forest algorithm, to identify and evaluate sleep disorder patterns in health and lifestyle datasets. Random Forest is advantageous for this task as it constructs multiple decision trees, enhancing its ability to handle complex data sets and create a robust classification model.
The study’s results indicate that the Random Forest algorithm can detect sleep disorders with high accuracy. The model achieved an impressive test accuracy of 97.33%, a precision of 96%, and a recall rate of 100%. Furthermore, it recorded an F1-Score of 98% and a Kappa Score of 0.945, demonstrating the algorithm’s reliability in classifying sleep disorders accurately.
These findings contribute to a better understanding of sleep disorder patterns and support the development of targeted interventions aimed at improving sleep quality. By implementing such diagnostic tools, healthcare providers may enhance treatment strategies, ultimately improving the quality of life for those affected by sleep disorders.
Spanish 
English 
French 
German 
Russian 
Belarusian 
Ukrainian