There's a corpus of anonymised records to do with<div>radiology freely available at<div><br class="webkit-block-placeholder"></div><div><a href="http://www.computationalmedicine.org/catalog/index.php">http://www.computationalmedicine.org/catalog/index.php
</a></div><div><br class="webkit-block-placeholder"></div><div>This is primarily due to the work of John Pestian and colleagues</div><div>in Cincinnati. John did much of the hard work on clearing the anonymization</div><div>
through the Institutional Review Board. </div><div><br class="webkit-block-placeholder"></div><div>We (John and collaborators from Colorado, Poland and Ohio State) used it as the basis for a shared task at BioNLP 07.</div>
<div><br class="webkit-block-placeholder"></div><div>The idea is that it should be a resource for ongoing research. I'm</div><div>hopeful it will also lead to other people being able to publish similar</div><div>things for research use.
</div><div><br class="webkit-block-placeholder"></div><div>Chris</div><div><br><br><div><span class="gmail_quote">On 20/09/2007, <b class="gmail_sendername">Angus Roberts</b> <<a href="mailto:a.roberts@dcs.shef.ac.uk">
a.roberts@dcs.shef.ac.uk</a>> wrote:</span><blockquote class="gmail_quote" style="margin:0;margin-left:0.8ex;border-left:1px #ccc solid;padding-left:1ex">Hello John<br><br>Your colleague might have heard of the CLEF corpus of medical records,
<br>it is mentioned in a couple of papers [e.g. 1]. CLEF is a UK Medical<br>Research Council project [2, 3]. The corpus consists of the medical<br>records of deceased patients from a UK cancer hospital. The corpus was<br>
established under an ethics committee approval. The fact that the<br>records are from deceased patient made it easier to get the ethics<br>committee approval. However, the approval does not allow the corpus to<br>be used outside of the CLEF project consortium.
<br><br>There has been some discussion about how the corpus might be made<br>available to others, in some controlled fashion, once the CLEF project<br>ends. This would, however, require further ethics committee discussions
<br>and approval, and is likely to take some time.<br><br>If you hear of other such corpora, I would be most interested to know of<br>them. As you say, such corpora are very hard to come by.<br><br>thanks<br>Angus<br><br>
[1] The CLEF Corpus: Semantic Annotation of Clinical Text. Angus<br>Roberts, Robert Gaizauskas, Mark Hepple et al. Proceedings of the 2007<br>American Medical Informatics Association Annual Symposium (AMIA 2007).<br>To appear. (let me know if you want a copy)
<br><br>[2] <a href="http://www.clinical-escience">http://www.clinical-escience</a>.org/<br><br>[3] <a href="http://www.clef-user.com/">http://www.clef-user.com/</a><br><br><br>John Aberdeen wrote:<br>> Greetings,<br>>
<br>> I'm seeking English-language text corpora of medical records.<br>> Typically medical records are unavailable to researchers due to<br>> privacy laws. However, medical records of deceased individuals are
<br>> sometimes available without restriction. One of my colleagues<br>> believes she has heard of a corpus originating in the UK consisting<br>> of the medical records of deceased persons, but does not know the<br>
> details. Does anyone know about this corpus, or similar corpora of<br>> medical records that are available for research purposes?<br>><br>> Thanks,<br>> John<br>><br>><br>> ______________________________
_________________<br>> Corpora mailing list<br>> <a href="mailto:Corpora@uib.no">Corpora@uib.no</a><br>> <a href="http://mailman.uib.no/listinfo">http://mailman.uib.no/listinfo</a>/corpora<br>><br><br>______________________________
_________________<br>Corpora mailing list<br><a href="mailto:Corpora@uib.no">Corpora@uib.no</a><br><a href="http://mailman.uib.no/listinfo">http://mailman.uib.no/listinfo</a>/corpora<br></blockquote></div><br></div></div>