Loading...
Journal Title
Keywords
Readers/Advisors
Bichindaritz, Isabelle
Journal Title
Term and Year
Publication Date
2025
Book Title
Publication Volume
Publication Issue
Publication Begin
Publication End
Number of pages
Collections
Files
Loading...
Quest2025_081.pdf
Adobe PDF, 586.8 KB
Research Projects
Organizational Units
Journal Issue
Abstract
This study aims to develop a machine learning-based model to predict the risk of sleep apnea using sleep patterns, physiological parameters, and lifestyle factors. The dataset consists of key attributes such as sleep duration, quality of sleep, physical activity levels, stress levels, BMI category, blood pressure, heart rate, and daily steps. Various preprocessing techniques, including feature scaling, categorical encoding, and handling class imbalance, will be applied to enhance model performance. Feature selection methods will identify the most influential factors, and machine learning models such as Random Forest, XGBoost, and Neural Networks will be evaluated. The model's performance will be assessed using accuracy, precision-recall scores, and AUC-ROC to ensure effective classification of individuals at risk of sleep apnea.