A Machine Learning Model Based Web App to Predict Diabetic Blood Glucose

Abstract

Aim of this study is to use machine learning approaches for predicting blood glucose based on basic non-invasive health checkup test results, dietary information, and socio-demographic characteristics and to develop a web application to predict blood glucose easily. We evaluated the performance of five widely used machine learning models. Data have been collected from 271 employees of Grameen Bank complex, in Dhaka, Bangladesh. This study used continuous blood glucose data to train the model and predicted new blood glucose values using the trained data. Finally, we developed a blood glucose prediction web application. The Boosted Decision Tree Regression model showed the best performance among other models based on the Root Mean Squared Error (RMSE) 2.30, this RMSE is better than any reported in the literature. This study developed a blood glucose prediction model and web application which is easier, more convenient, and more efficient for people. People can also easily check their blood glucose values using our app, especially in remote areas of developing countries that lack adequate skilled doctors and nurses. By predicting blood glucose, this study can help to save medical costs and time and to reduce health management costs. Our system can be helpful in achieving SDGs, Universal Health Coverage and thus reducing overall morbidity and mortality.

Prediction of Shelf Life of Pearl Millet Flour Based on Rancidity and Nutritional Indicators Using a Long Short-Term Memory Network Model

“…The FFNN and LSTM network architectures were used to predict the remaining shelf life. MSE was utilized as the loss function during model training …”

“…MSE was utilized as the loss function during model training. 25 The performance of LSTM and FFNN models was evaluated using MSE, MAE, and coefficient of determination (R 2 ) as the performance metric and is shown in Table 5.…”