Soft computing techniques for early diabetes prediction

Abstract

Diabetes mellitus is a chronic, life-threatening, and complicated condition. Around 1.5 million deaths due to diabetes have been documented, according to a World Health Organization (WHO) estimation in 2019. In the world of medicine, predicting diabetes risk is a difficult and time-consuming task. Many past studies have been conducted to investigate and clarify diabetes symptoms and variables. To solve these persisting issues, however, more critical clinical criteria must be considered. A comparative analysis based on three soft computing strategies for diabetes prediction has been carried out and achieved in this work. Among the computational intelligence methods used in this study are fuzzy analytical hierarchy processes (FAHP), support vector machine (SVM), and artificial neural networks (ANNs). The techniques reveal promising performance in predicting diabetes reliably and effectively in terms of several classification evaluation metrics, according to experimental analysis and assessment conducted on 520 participants using a publicly available dataset.