Cross-lingual Unified Medical Language System entity linking in online health communities

Abstract

Objective In Hebrew online health communities, participants commonly write medical terms that appear as transliterated forms of a source term in English. Such transliterations introduce high variability in text and challenge text-analytics methods. To reduce their variability, medical terms must be normalized, such as linking them to Unified Medical Language System (UMLS) concepts. We present a method to identify both transliterated and translated Hebrew medical terms and link them with UMLS entities. Materials and Methods We investigate the effect of linking terms in Camoni, a popular Israeli online health community in Hebrew. Our method, MDTEL (Medical Deep Transliteration Entity Linking), includes (1) an attention-based recurrent neural network encoder-decoder to transliterate words and mapping UMLS from English to Hebrew, (2) an unsupervised method for creating a transliteration dataset in any language without manually labeled data, and (3) an efficient way to identify and link medical entities in the Hebrew corpus to UMLS concepts, by producing a high-recall list of candidate medical terms in the corpus, and then filtering the candidates to relevant medical terms. Results We carry out experiments on 3 disease-specific communities: diabetes, multiple sclerosis, and depression. MDTEL tagging and normalizing on Camoni posts achieved 99% accuracy, 92% recall, and 87% precision. When tagging and normalizing terms in queries from the Camoni search logs, UMLS-normalized queries improved search results in 46% of the cases. Conclusions Cross-lingual UMLS entity linking from Hebrew is possible and improves search performance across communities. Annotated datasets, annotation guidelines, and code are made available online (https://github.com/yonatanbitton/mdtel).

Controllable Contrastive Generation for Multilingual Biomedical Entity Linking

“…Multilingual biomedical entity linking (MBEL) task is an extended version of monolingual biomedical entity linking (Zhu et al, 2022;Liu et al, 2021a; and cross-lingual biomedical entity linking (XBEL) (Rijhwani et al, 2019;Bitton et al, 2020), which focuses on mapping an input mention from biomedical text in a specific language to its associated entity in a curated multilingual KB. In monolingual biomedical entity linking, mentions always match the KB language, and entities in other languages are discarded.…”

“…Although promising breakthroughs have been achieved in monolingual biomedical entity linking (typically English) (Bitton et al, 2020;Liu et al, 2021a;Zhu et al, 2022), these approaches cannot be effectively applied to other languages due to the huge discrepancies between multilingual and monolingual versions of the biomedical entity linking (BEL) task. Firstly, resources for non-English BEL are scarce, hindering the development of multilingual research.…”

The UMLS knowledge sources at 30: indispensable to current research and applications in biomedical informatics

“…32 Rasmy et al found the UMLS useful in representing electronic health record (EHR) data in predictive modeling. 33 Bitton et al mapped transliterated terms to UMLS concepts to improve retrieval in a Hebrew online health community, 34 an example of using the UMLS both to extract information from social media and to aid interpretation of non-English text.…”

Mapping Chinese Medical Entities to the Unified Medical Language System

“…Only 10% of medical terms in UMLS are in Spanish. The ratio of French medical terms in the UMLS is approximately 2.7%, and only 485 Hebrew medical terms are collected in the UMLS [ 8 ]. The simplified Chinese version LOINC is the only Chinese vocabulary that has been included in the UMLS.…”

“…Spanish medical entities recognized from electronic health records were normalized as the UMLS concepts. Bitton et al [ 8 ] transliterated the UMLS terms into a variety of candidate Hebrew sequences using a transliteration model. Then, medical entities extracted from online Hebrew health communities were linked to the UMLS concepts based on Hebrew transliterations.…”