Prediction Model for Cardiovascular Disease Risk in Type2 Diabetic Patients Using a Hybrid Artificial Bee Colony Model and Semi-Supervised Learning

Abstract

A significant risk factor for death in people with diabetes is cardiovascular disease (CVD). More than 22% of persons with type 2 diabetes mellitus also have cardiovascular disease, and it is thought that the two conditions are causally related. However, not all of the research put enough emphasis on semi-supervised learning techniques that use feature selection strategies to improve the prediction accuracy of classification techniques. This study was out to better predict outcomes by identifying key CVD variables affecting type 2 diabetes management. Patient data is preprocessed and dimensionality reduced using Kullback-Leibler divergence (KLD)-principal component analysis (PCA) in the proposed methods; attribute values are measured using kernel density estimation (KDE), which measures attribute values using a probability mass function with a Gaussian kernel function; and feature selection is carried out utilising an artificial bee colony with differential evolution (ABC-DE). Semi-supervised Modified Self-Organizing Feature Map Neural Network (MSOFMNN) classification technique is used to the data after it has been clustered using the Improved Fuzzy C Means (IFCM) clustering algorithm in a hybrid prediction model to verify the selected class label of the input data. With improved prediction accuracy and reduced error rate, the proposed technique investigates the behavioural aspects that lead to CVD risk factors in people with type 2 diabetes (T2D).