Named Entities in Medical Case Reports: Corpus and Experiments

Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), pages 4495–4500 Marseille, 11–16 May 2020 c⃝ European Language Resources Association (ELRA), licensed under CC-BY-NC 4495 Named Entities in Medical Case Reports: Corpus and Experiments Sarah Schulz1, Jurica Ševa1, Samuel Rodriguez1, Malte Ostendorff2, Georg Rehm2 1Ada Health GmbH, Karl-Liebknecht-Str. 1, 10178 Berlin, Germany {first.lastname}@ada.com 2DFKI GmbH, Alt-Moabit 91c, 10559 Berlin, Germany {first.lastname}@dfki.de Abstract We present a new corpus comprising annotations of medical entities in case reports, originating from PubMed Central’s open access library. In the case reports, we annotate cases, conditions, findings, factors and negation modifiers. Moreover, where applicable, we annotate relations between these entities. As such, this is the first corpus of this kind made available to the scientific community in English. It enables the initial investigation of automatic information extraction from case reports through tasks like Named Entity Recognition, Relation Extraction and (sentence/paragraph) relevance detection. Additionally, we present four strong baseline systems for the detection of medical entities made available through the annotated dataset. Keywords: Named Entity Recognition, Case Reports, Corpus 1. Introduction The automatic processing of medical texts and documents plays an increasingly important role in the recent develop- ment of the digital health area. To enable dedicated Natural Language Processing (NLP) that is highly accurate with re- spect to medically relevant categories, manually annotated data from this domain is needed. One category of high interest and relevance are medical entities. Only very few annotated corpora in the medical domain exist. Many of them focus on the relation between chemicals and diseases or proteins and diseases, such as the BC5CDR corpus (Li et al., 2016), the Comparative Toxicogenomics Database1 (Davis et al., 2019), the FSU PRotein GEne corpus2 (Hahn et al., 2010) or the ADE (adverse drug effect) corpus (Gu- rulingappa et al., 2012). The NCBI Disease Corpus (Doğan et al., 2014) contains condition mention annotations along with annotations of symptoms. Several new corpora of an- notated case reports were made available recently. Grouin et al. (2019) presented a corpus with medical entity anno- tations of clinical cases written in French, Ju et al. (2019) presented a corpus focusing on phenotypic information for chronic obstructive pulmonary disease while Smalheiser et al. (2019) presented a corpus focusing on identifying main finding sentences in case reports. The corpus most comparable to ours is the French corpus of clinical case reports by Grouin et al. (2019). Their an- notations are based on UMLS semantic types. Even though there is an overlap in annotated entities, semantic classes are not the same. Lab results are subsumed under findings in our corpus and are not annotated as their own class. Factors extend beyond gender and age and describe any kind of risk factor that contributes to a higher probability of having a cer- tain disease. Our corpus includes additional entity types. We annotate conditions, findings (including medical find- ings such as blood values), factors, and also modifiers which indicate the negation of other entities as well as case enti- ties, i. …

Content truncated to 500 words