Prediction of Gestational Diabetes by Machine Learning Algorithms

Abstract

Diabetes is the most common noncommunicable disease among people in the world due to changes in food habits. Gestational diabetes mellitus (GDM) is most frequently found in women after the birth of a baby. This article describes the prediction of GDM with various machine learning (ML) algorithms demonstrated on the Polyisocyanurate Insulation Manufacturers Association (PIMA) data set. The accuracy of various ML algorithms is validated with metrics. The significance of ML algorithms is demonstrated using a confusion matrix as well as receiver operating characteristic (ROC) and area under the curve (AUC) scores in handling the diabetes PIMA data set.

Ähnliche Arbeiten