Particle Swarm Optimization For Improved Accuracy of Disease Diagnosis

The increasing number of patients suffering from various diseases and the impact high cost medical treatment for community has made government or health communities seek solutions prevention an early age. This valuable information can be found using artificial intelligence data mining. Most are dangerous; if detected adequate diagnosis available, there will a chance cure. main objective this study was to use Particle Swarm Optimization (PSO) improve accuracy several classification methods, namely Naive Bayes, C4.5, Support Vector Machine (SVM), Neural Network (NN) detect heart disease, hepatitis, kidney, breast cancer. method used in research is CRISP-DM model, with 5 stages. were four disease UCI Learning. result that PSO SVM, NN.