| The increasing use of Internet is making it possible for individuals to connect with one another for social networking and socially significant reasons. With the advent of electronic health records and the associated medical measurements, individuals will increasingly expect and gain access to their medical information. The availability of this information may serve as the foundation for automatically connecting similar individuals in social health networks (SHN).;Due to the potentially large number of online individuals and the number of medical measurements in an electronic health record, the record and feature space for connecting individuals is large. Therefore, this dissertation proposes a computational model to build SHNs using filtering, data reduction, and similarity coefficients. The filtering and data reduction steps reduce the scale of the problem. Two approaches for computing feature based similarity coefficients are explored.;A simulation of the computational model is demonstrated with two examples. The findings from the simulation demonstrate that the record and feature space can be significantly reduced. Furthermore, this research demonstrates that SHNs can be automatically formed with the defined computational model. |
