Cross-domain probabilistic inference in a clinical decision support system: Examples for dermatology and rheumatology

Highlights ► A clinical decision support system is useful in supporting diagnostic and treatment decisions for physicians, especially when facing a myriad clinical symptoms and laboratory test results. ► Maintaining a large diagnostic knowledge base is a demanding task and a cross-domain inference tool has great clinical importance. ► A modified multi-membership Bayes formulation was developed to facilitate the cross-domain probabilistic inferencing among knowledge bases with overlapping diseases and was proven to be valuable. ► The utilization of the novel formulation will help in the development of more integrated knowledge bases with greater focused knowledge domains.