Matching Medical Websites to Medical Guidelines through Clinical Vocabularies in View of Website Quality Assessment

The quality of medical texts provided to general public on the Internet is a serious issue nowadays. Unfortunately the only feasible way to approve the adequacy of the medical information content is human verification today. Best practices in medicine are systematically captured by medical guidelines (MGLs), which are provided by renowned medical societies. We propose a simple approach to exploiting MGL content as ’gold standard’ for the assessment of content quality in medical web sites (WS), based on the idea that the information content is reflected in the domain terminology used. Concept candidates discovered in a MGL and in the tested web pages are matched to the UMLS terminological system. In a small case study, MGLs and WSs have been analyzed for similarity at term and concept level. The research is a step towards automated evaluation of WS content on the basis of MGLs as the quality standard.