Healthcare is the organized provision of medical services to preserve or improve physical and mental health. Enhance the well-being of the individual and the community, this involves identifying, treating, preventing, and managing illnesses. Analyzing health-related data for better decision-making, efficiency, and results is known as healthcare analytics. Healthcare sensor data analytics, in particular, focuses on using data from medical sensors to improve clinical decision-making and patient illness monitoring. Many sensor-based devices are used to collect the patient’s health information. They can be processed using effective algorithms that help physicians get insights and make better treatment decisions. This article aims to predict osteoporosis disease with the collected data from sensor devices. The ultra-sonometer device is used to collect bone mineral density data. A bone's strength and fracture risk is indicated by its mineral content, mostly calcium, in a specific volume of bone measured by bone mineral density (BMD). This work focused on predicting osteoporosis disease using the Random Forest, Decision Tree, and ID3 classification algorithms. Execution time and classification accuracy are used to assess these algorithms' performance. According to experimental outcomes, the Decision Tree classifier is the most efficient technique as it gets the maximum classification accuracy on the other hand, the ID3 and Random Forest classifiers show the fastest execution times.

Classification Bone Mineral Density Sensor Osteoporosis Decision Tree Random Forest ID3