This paper presents a new method that can track the source origins of indoor viruses based on the number and location of infected cases observed in an enclosed environment. This probability-concept-based prediction uses the convective transfer mechanism of airborne viruses to track inversely the most probable locations of indoor infection sources. A new approach has been proposed to convert the number of infection cases to the concentration values of virus that can be used for prediction. The sourcetracking method is demonstrated and verified by using the SARS infection cases of medical students in a hospital ward outbreak in Hong Kong, 2003. The model successfully predicts the location of the virus origin, the clinically identified SARS patient's bed in the outbreak. The method shows great potential for quickly identifying the index patient location during an airborne disease outbreak, as well as confirming the airborne transmission mechanism and path of indoor virus and bacteria.