Application of fuzzy logic and genetic algorithm in heart disease risk level prediction

• Published in: International journal of system assurance engineering and management 2017-11, Vol.8 (Suppl 2), p.1109-1125
• Main Authors: Sharma, Purushottam, Saxena, Kanak
• Format: Article
• Language: English
• Subjects: Cardiovascular disease; Decision support systems; Engineering; Engineering Economics; Fuzzy logic; Fuzzy systems; Genetic algorithms; Heart; Illnesses; Logistics; Marketing; Organization; Original Article; Patients; Quality Control; Reliability; Risk; Safety and Risk
• ISSN: 0975-6809; 0976-4348
• DOI: 10.1007/s13198-017-0578-8

As individuals have intrigues in their wellbeing now a days, advancement of therapeutic area application has been a standout amongst the most dynamic exploration territories. One case of the restorative area application is the identification framework for coronary illness taking into account. A weighted fuzzy standard based clinical decision support system is displayed for the conclusion of coronary illness, consequently acquiring learning from the clinical information. The proposed heart disease risk level prediction system using fuzzy and genetic for the risk forecast of heart patients comprises of two stages: (1) mechanized methodology for the era of weighted fuzzy rules and (2) building up a fuzzy principle based heart disease risk level prediction using genetic algorithm. At this point, the fuzzy framework is developed as per the weighted fuzzy standards and picked better qualities cases. In this study, a system that can capably locate the fundamentals to anticipate the risk level of patients in perspective of the given parameter about their wellbeing. The principle commitment of this study is to help a non-specialized doctors to settle on right choice about the coronary illness risk level. The framework’s execution is assessed and compared as far as rules precision concerned and the outcomes demonstrates that the framework has incredible potential in foreseeing the coronary illness risk level more precisely.