|English: Map Summarizing Rosacea, It was created by the author and Reem Al-Qudah using Clinical dermatology book Dahl, Mark V.; Weller, Richard E.; Hunter, John G.; Savin, John (2008). Clinical Dermatology. Wiley-Blackwell. Reference (Photo credit: Wikipedia)
For the last few weeks I have been working on DermKnowledgeBASE (DKB) that I believe is the first RDF knowledgebase for dermatology. It implements RDFS using RAP library for php. The terminology in dermatology facilitate the diagnostic process because many skin disorders have distinct features that can be represented by appropriate categories of terms. But dermatological terms are different from the traditional medical linguistics. Hence DKB is not rooted on MeSH or any popular medical ontologies but on ONTODerm, the ontology I started developing for dermatology. I wrote about an offshoot of this project called slise before. DKB makes use of eutil webservices and whatizit from EBI. It is semi automated and can learn most of the relations on its own. But it relies on curators for confirming difficult rules. Its focus is on providing diagnostic support. Hence curators can add further information about the relevance of each feature in a particular disease. Features can be classified as pathognomonic, common, important, rare etc which helps in streamlining diagnostic accuracy. It provides a range of functions and SOAP web services in addition to a ‘consult’ function to obtain differential diagnosis based on the description of clinical findings. It is still early days, but hopefully it may evolve into a very useful application for dermatology.
Click the banner below to access DermKnowledgeBASE:
- Medprompt: How to architect LLM solutions for healthcare. - December 6, 2023
- Named Entity Recognition using LLMs: a cTakes alternative? - September 1, 2023
- Distilling LLMs to small task-specific models - August 24, 2023