Efficient heart disease prediction system using optimization technique

In this modern society where large number of humans follow a sedentary lifestyle following an 8 hour job cycle, cardio vascular diseases or heart diseases is one of the leading causes of mortality worldwide. The computers at the hospitals of the healthcare industries are used to collect huge amounts of information regarding the patients and their ailments. This huge repository of information contains wealth of knowledge. The hidden patterns and relationships in the data is mostly overlooked. Diagnosing cardio vascular diseases in patients is a difficult task and doctors who can accurately predict such diseases are few in number. This research paper focuses on developing a prediction algorithm with the help of data mining and optimization techniques. Data Mining refers to using a variety of techniques to identify information or decision making knowledge in the database and extracting these in a way that they can put to use in areas such as decision support, predictions, forecasting and estimation. We will be using the Particle Swarm Optimization technique which is an inherently distributed algorithm where the solution for a problem emerges from the interactions between many simple individual agents called particles. The data source we have used for experimental testing are commonly used and considered as a de facto standard for heart disease prediction reliability ranking. We will also be using a slightly modified version of PSO with constriction factor called Constricted PSO. The results obtained show that Particle Swarm Data Mining Algorithms are competitive, not only with other evolutionary techniques, but also with industry standard algorithms, and can be successfully applied to heart disease prediction.