Insulin Level Prediction Using Machine Learning Approach

Abstract

Diabetes patients have to continuously monitor their blood glucose levels and adjust insulin doses, striving to keep blood glucose levels as close to normal as possible. They need to take insulin dose before their every meal. The doctors have to decide insulin doses for every patient according to the patient’s previous records of doses and sugar levels measured at regular intervals. Our paper proposes a Machine Learning Approach & uses a RNN (LSTM) and ANN algorithm to predict the insulin chart for a patient efficiently to implement the model. The thirty-six months chart maintained by the patient has been used to train the model and the long sequence of next insulin prediction is done on the basis of trained data. In this research, out of various existing algorithms of finding insulin level frequent item sets and mining association rule, we use predictive Apriori algorithm for this prediction.