Early diagnosis of stroke disorder using homogenous logistic regression ensemble classifier

A stroke occurs in the scenario wherein the blood supply to the brain is blocked, leading to a lack of oxygen to the blood. There is a need for the early diagnosis of the stroke to handle the emergency situations of stroke in an efficient manner. Integration of Artificial Intelligence (AI) in the early diagnosis of stroke provides efficiency and flexibility. Artificial Intelligence (AI), which is a mimic of human intelligence has a wide range of applications from small scale systems to high-end enterprise systems. Artificial Intelligence has emerged as an efficient and accurate decision-making system in healthcare systems. Machine Learning (ML) is a subset of Artificial Intelligence (AI). The incorporation of machine learning techniques in stroke diagnosis systems provides faster and precise decisions. The proposed system aims to develop an early diagnosis of stroke disorder using a homogenous logistic regression ensemble classifier. Logistic regression is a linear algorithm that uses maximum likelihood methodology for predictions and a standard machine learning model for two- class problems. The prediction is improved by accumulating the predictions of two or more logistic regression using a bagging ensemble classifier thereby increasing the accuracy of the stroke diagnosis system. The accumulation of prediction of two or more same models is known as a homogenous ensemble classifier. The results obtained show that the proposed homogenous logistic regression ensemble model has higher accuracy than single logistic regression.