Title: Mining the risk of heart attack: a comprehensive study
Author: Subhagata Chattopadhyay
Address: Department of Computer Science and Engineering, Camellia Institute of Engineering, Digberia, Madhyamgram 700129, Kolkata, WB, India
Journal: Int. J. of Biomedical Engineering and Technology, 2013 Vol.11, No.4, pp.394 - 410
Abstract: This paper attempts to mine important predisposing risk factors of heart attack from a sample of 300 real-world cases, each having 12 predisposing factors. Initially ranking of the factors are made according to the medical doctors. According to the risk level (i.e. mild, moderate, and severe) the sample has been clustered using Divisive Hierarchical Clustering (DHC) techniques with 'single', 'average', and 'complete' linkages. It also observes that High Blood Cholesterol (HBC), Intake of Alcohol (IA), and Passive Smoking (PS) play the most crucial role on 'severe', 'moderate' and 'mild' cardiac risks, respectively, which matches the result of Andrews plot. The study also observes that 'males' with age group of 48-60 years (mean age 53.45 years) are more prone to suffer 'severe' and 'moderate' heart attack risk, while females over 50 years (mean 53.23 years) are affected mostly with 'mild' risk.
Keywords: cardiac risk; predisposing factors; data mining; statistics; divisive hierarchical clustering; Andrews plot; heart attacks; risk assessment; high blood cholesterol; alcohol intake; passive smoking; predisposition.