<![CDATA[Sleep disorders significantly affect an individual's sleep quality, which can lead to serious health problems. For the elderly, poor sleep quality can drastically reduce life expectancy. The main problem is the lack of effective predictive tools to improve sleep quality among the elderly, compounded by the numerous factors that can influence their sleep quality. Therefore, analysis and prediction are necessary to enhance sleep quality. This study aims to develop and test a predictive model for sleep quality in the elderly by integrating health and environmental factors using a machine learning approach. The dataset used is a new one available on the website Kaggle.com, namely the National Poll on Healthy Aging (NPHA) data, which provides insights into health issues, healthcare, and health policies affecting Americans aged 50 and above. The aim is to improve sleep quality among the elderly. A machine learning method, specifically deep learning with the Random Forest algorithm, was used in this study and showed good results with an accuracy rate of 94.00% and a training data accuracy of 44.44%. The results of this study are expected to provide a predictive tool that can be used by healthcare practitioners to improve the sleep quality of the elderly, thereby positively impacting their health and life expectancy.]]>
Copyrights © 2024
