Characteristics of Finnish and Swedish intensive care nursing narratives: a comparative analysis to support the development of clinical language technologies

Abstract

BackgroundFree text is helpful for entering information into electronic health records, but reusing it is a challenge. The need for language technology for processing Finnish and Swedish healthcare text is therefore evident; however, Finnish and Swedish are linguistically very dissimilar. In this paper we present a comparison of characteristics in Finnish and Swedish free-text nursing narratives from intensive care. This creates a framework for characterising and comparing clinical text and lays the groundwork for developing clinical language technologies.MethodsOur material included daily nursing narratives from one intensive care unit in Finland and one in Sweden. Inclusion criteria for patients were an inpatient period of least five days and an age of at least 16 years. We performed a comparative analysis as part of a collaborative effort between Finnish- and Swedish-speaking healthcare and language technology professionals that included both qualitative and quantitative aspects. The qualitative analysis addressed the content and structure of three average-sized health records from each country. In the quantitative analysis 514 Finnish and 379 Swedish health records were studied using various language technology tools.ResultsAlthough the two languages are not closely related, nursing narratives in Finland and Sweden had many properties in common. Both made use of specialised jargon and their content was very similar. However, many of these characteristics were challenging regarding development of language technology to support producing and using clinical documentation.ConclusionsThe way Finnish and Swedish intensive care nursing was documented, was not country or language dependent, but shared a common context, principles and structural features and even similar vocabulary elements. Technology solutions are therefore likely to be applicable to a wider range of natural languages, but they need linguistic tailoring.AvailabilityThe Finnish and Swedish data can be found at: http://www.dsv.su.se/hexanord/data/.

Proceedings of the 3rd Workshop on Predicting and Improving Text Readability for Target Reader Populations (PITR)

“…That corpus then has to be targeted towards laymen, as word frequency in texts targeted towards health professionals would favour word replacements with words typical to the professional language. Examples of such patient corpora could be health related web portals for patients (Kokkinakis, 2011). However, as also texts targeted towards patients have been shown to be difficult to understand, the method of searching for familiar words in substrings of medical terms might be relevant for assessing word difficulty also if easy medical corpora would be used.…”

“…Furthermore, a certain word or expression can be shortened in several different ways. For instance, in a Swedish intensive care unit, the drug Noradrenalin was creatively written in 60 different ways by the nurses (Allvin et al, 2011).…”

Overview of the ShARe/CLEF eHealth Evaluation Lab 2013

“…In SNOMED-CT, the CUIs C0003811, C0004096, and C0020461 correspond to synonyms of arrhythmia, asthma, and hyperkalemia, respectively. 1 The patient's and her next-of-kin's understanding of health conditions can be supported not only by these expansions, corrections, and normalisations, but also by linking the words to a patient-centric search on the Internet. Already without electronic linkage with discharge summaries, nearly 70 per cent of search engine users in the USA in 2012 searched for information about health conditions [3].…”

“…However, the law and practice differ substantially [1,2]. The patient and her next of kin are likely to have difficulties in understanding this simple example sentence from a US discharge: "AP: 72 yo f w/ ESRD on HD, CAD, HTN, asthma p/w significant hyperkalemia & associated arrythmias."…”

Adverse Drug Event classification of health records using dictionary based pre-processing and machine learning

“…Unstructured information is mainly free text. Health records are usually long and written by different authors with different writing styles (Allvin et al, 2011;Wijesekera, 2013). To identify entities in a text, to extract meaning and terms, and to consider their context, advanced methods must carried out.…”