Sleep-Disorder-Classification

Sleep disorders pose a global health challenge, impacting countless individuals and straining healthcare systems. Leveraging extensive datasets and advanced algorithms, machine learning (ML) has the potential to reshape the landscape of sleep disorder diagnosis. This project focuses on classifying disorders due to their often subtle or asymptomatic nature. ML algorithms can analyze diverse clinical data like heart rates, blood pressure, and BMI to unveil hidden patterns. Trained on vast datasets, highly accurate ML models offer promising potential in diagnosing conditions such as Sleep Apnea and Insomnia. This innovation holds the key to more effective interventions and improved sleep health worldwide.In this project,among the three models employed, the Decision Tree stands out as the most fitting choice with a consistently high accuracy rate, ranging from 90% to 92%. Equally promising, the KNN model also exhibits optimized performance, offering an accuracy of up to 91%. Conversely, the Logistic Regression model displays lower accuracy, likely due to its struggle with intricate decision boundaries. This is in contrast to the more advanced nature of Decision Tree and similar models, which contributes to their superior accuracy.