Novel Cardiac Risk Factor Stratification Using Neuro-fuzzy Tool

Cardiac risk factor assessment requires a classification system that is robust to the interaction and uncertainty of input factors, as well as being interpretable on the decision made. To meet the requirements, we made use of neuro-fuzzy methods, a certain novelty in cardiac risk assessment.Statistic data of 165 patients including sex, age, LDL, blood pressure, and Myocard-brain Creatinine Phosphokinase enzyme were collected. The intensity of infarction was determined according to the amount of the enzyme. A simplified cardiac risk stratification model was developed. Sex, age, LDL, and blood pressure were considered as the input and infarction intensity as the output. To draw the input-output mapping of each group, two hybrid neuro-fuzzy classifiers, IRIDIA method for neuro-fuzzy Identification and data analysis and adaptive network-based fuzzy inference system (ANFIS), were used. The application of neuro-fuzzy methods led us to consider significant distinctions between males and females and among subjects of different cities in cardiac risk stratification.