Andy: this is very interesting and exciting.
I hacked out a script that makes a visually appealing representation of the aggregate pipeline in d3js that, at least for a clinician, is a nice overall summary of the meta data generated from the pipeline. Its really no more than a parser of the xml through the type system spitted out into json, but when I was talking to my informatics department who didnt know much at all about ctakes, it was a great visual summary. Its in python. I dont know if youd want it but it might be worth having the "demo site" spit out a visually appealing graphic like this automatically. If not in python it might be worth adapting it to whatever your using for a platform to spit out the json for the d3js graphic im using. John — Sent from Mailbox for iPhone On Thu, Mar 20, 2014 at 5:31 AM, andy mcmurry <mcmurry.a...@gmail.com> wrote: > Yes! I have been working full time on the "apt-get install" task specific > to medical genetics: http://www.ncbi.nlm.nih.gov/medgen > Right now, millions of $$$ are invested in getting phenotype concepts -- > indications, diseases, problem lists -- linked to patient test results > including DNA / RNA / etc. In industry, most of the curation work is done > manually because platforms like cTAKES are not yet immediately accessible. > I have written code to > A) start automating the installer tasks for cTAKES on Ubuntu 13 > B) install UMLS NLP tools metamap, semrep, semmed > C) mirror NLM content that extends UMLS annotation > *SO THAT : * > Mentions of diseases relationships -- SNOMED-CT, HPO, OMIM, GTR, UMLS -- > reference the same semantic relationships in UMLS Clinical Terms and > Genetic Test Reference. This is powerful and all credit to the NLM for > creating MedGen and GTR, new crucial additions to the UMLS. To my > knowledge, these new sources have not been fully utilized by the medical > NLP community. > *I'm strongly advocating for a cTAKES VM that indexes UMLS concepts in the > same say that NCBI indexes UMLS linked Medical Genetics terms.* > Towards this goal, if other committers are interested, I'm 100% time > committed to this problem. > *TL;DR*: at minimum, having a demo site makes cTAKES more accessible. We > should demonstrate rather than explain every feature of cTAKES. I'm working > 100% on the Clinical Text +BioNLP problem. If that interests you, let me > know I'm convinced this area has huge, understudied potential. > --AndyMC > On Tue, Mar 18, 2014 at 8:15 AM, Pei Chen <chen...@apache.org> wrote: >> FYI: >> ASF Infra is setting up our VM for demo purposes. >> INFRA-7451 >> >> If you need access, feel free to let us now. >> Initial maintainers: james-masanz, andymc,chenpei >> --Pei >>
