ULisboa: Recognition and Normalization of Medical Concepts

Abstract

This paper describes a system developed for the disorder identification subtask within task 14 of SemEval 2015. The developed system is based on a chain of two modules, one for recognition and another for normalization. The recognition module is based on an adapted version of the Stanford NER system to train CRF models in order to recognize disorder mentions. CRF models were build based on a novel encoding of entity spans as token classifications to also consider non-continuous entities, along with a rich set of features based on (i) domain lexicons and (ii) Brown clusters inferred from a large collection of clinical texts. For disorder normalization, we (i) generated a non ambiguous dictionary of abbreviations from the labelled files, using it together with (ii) an heuristic method based on similarity search and (iii) a comparison method based on the information content of each disorder. The system achieved an F-measure of 0.740 (the second best), with a precision of 0.779, a recall of 0.705.

Efficient Reduction of Overgeneration Errors for Automatic Controlled Indexing with an Application to the Biomedical Domain

“…Such approach can be used to reduce over-generation errors. Since ambiguous concept mention can be mapped to multiple concepts in the referenced ontology (UMLS) depending on the context, one of the main challenges in the concept normalization task consists in the disambiguation of these cases [9]. www.ijacsa.thesai.org…”

IxaMed at PharmacoNER Challenge 2019

“…Regarding Concept Indexing, they used basically customized look-ups, like Dictionary look-up (exact match of entity word permutations, LVG), Customized Dictionary lookup (split UMLS entities by function words), and Customized Dictionary look-up (list of possible UMLS spans and application of Levenshtein distance). The second highest ranked team (Leal et al, 2015) obtained, for strict evaluation, an Fscore of 74 and in the relaxed one 76.5. They employed a CRF to identify entities (also discontinuous entities), and for Concept Indexing they applied exact match on the terminology content of the Systematized Nomenclature of Medicine -Clinical Terms (SNOMED-CT) enriching it with an abbreviation dictionary built on the training set.…”

SemEval-2015 Task 14: Analysis of Clinical Text

“…For CUI normalization, the best performing teams focused on augmenting existing dictionaries with lists of unambiguous abbreviations (Leal et al, 2015) or by pre-processing UMLS and breaking down existing lexical variants to account for high paraphrasing power of disorder terms (Pathak et al, 2015).…”

“…The best-performing teams made use of the large unannotated corpus of clinical notes provided in the challenge (Pathak et al, 2015;Leal et al, 2015;Xu et al, 2015). Teams explored the use of Brown clusters (Brown et al, 1992) and word embeddings (Collobert et al, 2011).…”