Improving Readability of Swedish Electronic Health Records through Lexical Simplification: First Results

Abstract

This paper describes part of an ongoing effort to improve the readability of Swedish electronic health records (EHRs). An EHR contains systematic documentation of a single patient's medical history across time, entered by healthcare professionals with the purpose of enabling safe and informed care. Linguistically, medical records exemplify a highly specialised domain, which can be superficially characterised as having telegraphic sentences involving displaced or missing words, abundant abbreviations, spelling variations including misspellings, and terminology. We report results on lexical simplification of Swedish EHRs, by which we mean detecting the unknown, out-ofdictionary words and trying to resolve them either as compounded known words, abbreviations or misspellings.

Swedification patterns of Latin and Greek affixes in clinical text

“…Such characterization is essential for constructing automated language analysis tools that can be used for knowledge extraction from clinical text. It has previously been found that many words and expressions in Swedish clinical free text cannot be automatically identified by vocabulary matching to established terminologies (Skeppstedt et al 2012, Grigonytė et al 2014). This is in part due to medical jargon and the extensive use of ad hoc abbreviations (Kvist & Velupillai 2014), but also misspellings and foreign words.…”

“…For instance, compare two cases: senso ri + n euralt and fiber + rin oskopi . The compound splitting that we employ in this study is based on using a large general language Swedish dictionary (The NST Dictionary 2007) and a medical domain dictionary, resulting in a precision of 83.5%, and is described in more detail in Grigonytė et al (2014).…”

“…In addition to this, there is a strong influence from the English spelling of Latin and Greek, resulting in a mixture of Latin, Greek, English and Swedish spellings, sometimes in the same word. The combinatorics of these influences is enormous, giving rise to huge numbers of spelling variants of the same terms (Grigonytė et al 2014). This in turn constitutes a problem for laypersons trying to look up terms from clinical text and a serious obstacle for automatic language processing for the purpose of simplification, normalization and text mining.…”

On the creation of a clinical gold standard corpus in Spanish: Mining adverse drug reactions

“…We developed FreeLing-Med, a toolkit to analyze documents in the biomedical domain in Spanish and English [26,27]. The resulting domain-adapted FreeLingMed system is able to carry out medical named entity recognition, linking of all the terms in SNOMED CT with their corresponding semantic tag (substances, disorders, procedures, findings), and identification of all the medical abbreviations using the dictionary by Yetano and Alberola [28] as well as the identification of brand-drug names using a drug database called BOTPLUS 5 . In addition, the original FreeLing adds semantic and syntactic pieces of information.…”

“…Furthermore, most NLP work in biomedicine has concerned English (although there are recent efforts that incorporate other languages, such as Spanish [2], French [3,4], Swedish [5], and Finnish [6]). …”