The present work demonstrates the design and implementation of a human-safe, portable, noninvasive device capable of predicting type 2 diabetes, using electrical bioimpedance and biometric features to train an artificial learning machine using an active learning algorithm based on population selection. In addition, there is an API with a graphical interface that allows the prediction and storage of data when the characteristics of the person are sent. The results obtained show an accuracy higher than 90% with statistical significance (p < 0.05). The Kappa coefficient values were higher than 0.9, showing that the device has a good predictive capacity which would allow the screening process of type 2 diabetes. This development contributes to preventive medicine and makes it possible to determine at a low cost, comfortably, without medical preparation, and in less than 2 minutes whether a person has type 2 diabetes.
Copyright © 2021 Javier Ferney Castillo García et al.