In this paper, an application of fuzzy-based expert system for respiratory infection diagnostic is introduced. Due to the symptoms of respiratory infections, such as influenza and common cold, are very similar. It¡¦s very difficult to determine if patients got influenza, common cold or other respiratory infections in first stage of exacerbation. In this paper, several fuzzy rules for diagnostic respiratory infection are made according doctor¡¦s experience. The knowledge is adopted and extracted for building expert system. In experiments, 50 virtual patients are generated with different symptoms for testing performance of proposed system. The proposed method exhibits higher accuracy for judging patients¡¦ disease (respiratory infection).