A manual corpus of annotated main findings of clinical case reports

Clinical case reports are the `eyewitness reports' of medicine and provide a valuable, unique, albeit noisy and underutilized type of evidence. Generally a case report has a single main finding that represents the reason for writing up the report in the first place. In the present study, we present the results of manual annotation carried out by two individuals on 500 randomly sampled case reports. This corpus contains main finding sentences extracted from title, abstract and full-text of the same article that can be regarded as semantically related and are often paraphrases. The final reconciled corpus of 416 articles comprises an open resource for further study. This is the first step in establishing text mining models and tools that can identify main finding sentences in an automated fashion, and in measuring quantitatively how similar any two main findings are. We envision that case reports in PubMed may be automatically indexed by main finding, so that users can carry out information queries for specific main findings (rather than general topics)-and given one case report, a user can retrieve those having the most similar main findings. The metric of main finding similarity may also potentially be relevant to the modeling of paraphrasing, summarization and entailment within the biomedical literature.