Medical diagnosis is one of the most important issues in healthcare. Computer aided systems have been developed in order to diagnose diseases by examining the internal human organs through medical images captured by MRI, CT scan etc. Many techniques have been utilized in order to develop these systems. In this paper, a short review on artificial neural network, fuzzy logic and genetic algorithm techniques in medical diagnostic applications is presented. The purpose of this review is to select the most suitable soft computing methodology to build a disease diagnosis system with high capabilities. The combination of artificial neural network, fuzzy logic and genetic algorithm in one methodology was reported to have a great advantage in producing systems with better performance. © 2011 IEEE.