Computational Intelligence and Healthcare Informatics

7A Machine Learning–Based Intelligent Computational Framework for the Prediction of Diabetes Disease

Maqsood Hayat*, Yar Muhammad and Muhammad Tahir

Department of Computer Science, Abdul Wali Khan University Mardan, KP, Pakistan

Abstract

In the healthcare system, machine learning performs a vital role because of its high capabilities in the identification and diagnosing of disease. Machine learning hypotheses have been effectively applied in numerous areas of healthcare especially in the diagnosis and prediction of chronic diseases such as Alzheimer’s, heart, stroke, blood pressure, and diabetes, which have no permanent cure. Among these diseases, diabetes is a perilous and rapidly growing disease that increases the death ratio particularly in women across the world. The main causes of diabetes disease are immoral lifestyles, unhealthy food, and less awareness about health impacting factors. In order to avoid diabetes disease, there needs a system that can truly identify and diagnose diabetic patients on time and protect them from more damage. In this study, an intelligent computational predictive system is introduced for the identification and diagnosis of diabetes disease. Here, eight machine learning classification hypotheses are examined for the identification and diagnosis of diabetes disease. Numerous performance measuring metrics such as accuracy, sensitivity, specificity, AUC, F1-score, MCC, and ROC curve are applied to inspect the effectiveness and stability of the ...