Predicting Sleep Disorders: Leveraging Sleep Health and Lifestyle Data with Dipper Throated Optimization Algorithm for Feature Selection and Logistic Regression for Classification

Abstract

This paper is a thorough examination of the modeling of sleep disorders based on machine learning that is applied to the sleep-health-and-lifestyle data. The use of the Dipper Throated Optimization Algorithm for feature selection and Logistic Regression for classification is the basis of the study that explores the effectiveness of predictive models in identifying sleep disorders based on varied sleep metrics and lifestyle factors. The binary Dipper Throated Optimization Algorithm was the most successful with the lowest Average error of 0.71933 uses feature selection as the most effective method, which proves that it is successful the method of choosing the relevant features for predictive modeling. Moreover, Logistic Regression proved to be very efficient in classification; it got an Accuracy of 0.95. The results of these studies support the idea of the personalized treatment and earlier detection of sleep disorders; this, in turn, will be of great help to the progress in sleep health research and healthcare practice.