A Genetic Algorithm based Approach in Predicting and Optimizing Sickle Cell Anaemia

A good amount of information is hidden in medical data which can be analyzed using various computational techniques. Metaheuristics play a vital role in producing optimal or near optimal results to complex problems. Genetic algorithms are a robust adaptive optimization method based on biological principles. The research is important because it is necessary to detect and cure certain diseases like Sickle Cell Anaemia which prove to be fatal many a times, if not taken care of. In the proposed work we present the application of genetic algorithm (differential evolution) to predict sickle cell anaemia and optimize the results. We also propose a new crossover operator in differential evolution. The algorithm gives us optimized values of the following blood components (parameters)- HB, RBC and MCH. With these values it can be shown that patients whose functional value is less than or equal to the best value suffer from sickle cell anaemia. With such an approach for data analysis these patients can be cured on time. Further we conclude that data mining algorithms can make it easier and less time consuming to predict and optimize the parameters.