Insomnia and sleep apnea represent sleep disorders that profoundly affect human health and well-being. This study examines how different machine learning (ML) approaches can determine sleep disorder risks based on physiological measurements alongside lifestyle and demographic data. The analysis involved a complete dataset that included sleep duration and quality measurements, physical activity levels, stress levels, cardiovascular health factors, and demographic information. The study conducted a thorough evaluation of multiple supervised classification algorithms, such as logistic Regression, decision tree, random forest, k-nearest neighbors (kNN), Gaussian naïve Bayes, multinomial naïve Bayes, Bernoulli naïve Bayes, support vector machines (SVM), and linear Regression. Decision tree, random forest, and kNN algorithms showed better predictive performance after preprocessing data thoroughly and selecting features through correlation analysis and cross-validation. The random forest model produced the best results with an accuracy rate of \(94.38\%\) , a precision level of \(0.96\%\) , a recall rate of \(0.98\%\) for the no sleep disorder class, and an AUC score of \(0.98\%\) . The feature importance analysis identified age, BMI category, blood pressure, and occupation as essential predictors for sleep disorders. The findings of this study demonstrate how machine learning methods enable the precise and timely detection of sleep disorder risks within clinical settings.