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

IntroductionMaintaining a large diagnostic knowledge base (KB) is a demanding task for any person or organization. Future clinical decision support system (CDSS) may rely on multiple, smaller and more focused KBs developed and maintained at different locations that work together seamlessly. A cross-domain inference tool has great clinical import and utility.MethodsWe developed a modified multi-membership Bayes formulation to facilitate the cross-domain probabilistic inferencing among KBs with overlapping diseases. Two KBs developed for evaluation were non-infectious generalized blistering diseases (GBD) and autoimmune diseases (AID). After the KBs were finalized, they were evaluated separately for validity.ResultTen cases from medical journal case reports were used to evaluate this “cross-domain” inference across the two KBs. The resultant non-error rate (NER) was 90%, and the average of probabilities assigned to the correct diagnosis (AVP) was 64.8% for cross-domain consultations.ConclusionA novel formulation is now available to deal with problems occurring in a clinical diagnostic decision support system with multi-domain KBs. The utilization of this formulation will help in the development of more integrated KBs with greater focused knowledge domains.

► 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.