Optimizing Telemedicine for Public Health: Novel Machine Learning-Driven Blood Pressure Evaluation Model

As a form of asynchronous interaction between patients and doctors through electronic technology to provide distant clinical solutions, telemedicine seems not to deliver sufficient and accurate means of predicting and evaluating public health indicators outside conventional health settings like BP. In this investigation, we have used a new fish migration optimized cat boost technique named fish migration optimized cat boost (FMO+CB) for predicting blood pressure rates with the help of the physiological data collected from human subjects by the Electrical Impedance Myography (EIMO) apparatus. To further enhance the prediction performance of BP, the FMO technique and the CB method are incorporated. An analysis of the FMO approach shows that it is used to select the correct parameters to avoid overlearning. Evaluation of the prediction result of BP using various criteria such as MAE =3.06, MSE =50.04, and MAPE =3.03 are tested using the proposed approach through a Python platform. The experimental results prove the fact that the FMO+CB methodology has better prediction accuracy compared to the other methods.