Exploring the Experimental Possibilities of an Intelligent Blood Pressure Prediction Scheme using IoT enabled Machine Learning Principles

Blood pressure is a severe worldwide public health issue that has an impact on every person. High blood pressure is a dangerous medical disease that can occasionally result in death and damage vital organs including the heart, brain, and kidneys. It is one of the unsolved issues in the medical field. One major risk factor for cardiovascular disease (CVD) is hypertension. It is imperative to identify these high-risk individuals in order to avoid wasting time or money on more complex, invasive, or expensive diagnostic procedures. Recent advances in machine learning may be used to partially achieve this goal. More specifically, a number of affordable, non-invasive, and readily-obtained indicator traits of high-risk individuals may serve as the foundation for the creation of a prediction model. This research presents a new machine learning model, Learning based Intelligent Blood Pressure Prediction (LIBPP), and assesses its efficacy by cross-validating it against the traditional learning model, Naive Bayes Classifier (NBC). First and foremost, this research aims to improve our understanding of the importance of variables in hypertension modelling. Second, the study aims to assess the suggested approach’s predictive performance. Young and middle-aged persons who might not take regular blood pressure readings can benefit from early warnings provided by this innovative approach of forecasting systolic blood pressure. Additionally, because isolated blood pressure readings are known to fluctuate frequently, our prediction can give medical professionals an additional point of reference. Our experimental findings demonstrate the suitability of LIBPP for systolic blood pressure modelling and prediction.