The amount of knowledge represented in the Health Level 7 International (HL7) information models is very large. The sheer size of those models makes them very useful for the communities for which they are developed. However, the size of the models and their overall organization makes it difficult to manually extract knowledge from them. We propose to extract that knowledge by using a novel filtering method that we have developed. Our method is based on the concept of class interest as a combination of class importance and class closeness. The application of our method automatically obtains a filtered information model of the whole HL7 models according to the user preferences. We show that the use of a prototype tool that implements that method and produces such filtered model improves the usability of the HL7 models due to its high precision and low computational time.