A proposed real-time analytics approach using machine learning on wearable sensor data aims to monitor vital signs and predict cardiovascular disease risk to improve diagnostic accuracy.
A proposed machine learning approach for real-time wearable sensor data analytics aims to predict cardiovascular disease risk and improve personalized healthcare.
Disease identification and diagnosis of ailments are at the forefront of machine learning research in healthcare. Today, the increasingly sedentary nature of many forms of recreation time and increasing urbanization results in decreased physical activity and thereby leading to a rise in health problems. A lot of wearables available today can provide important cues to people; however, these devices are not able to perform advanced predictions from the collected data about a disease condition. In this paper, we propose a real-time analytics approach on sensor data to monitor the vital signs of a person, e.g., heart rate, and notify the user if there is a risk of cardiovascular disease. A machine learning model is developed to perform predictions based on the captured physiological parameters. The outcome is a personalized healthcare service, which can significantly improve diagnostic accuracy, healthcare quality, and patients' quality of life.
Amin et al. (Mon,) conducted a other in Cardiovascular disease. Real-time analytics approach on sensor data was evaluated. A proposed real-time analytics approach using machine learning on wearable sensor data aims to monitor vital signs and predict cardiovascular disease risk to improve diagnostic accuracy.