Development of a Corpus Annotated with Medications and their Attributes in Psychiatric Health Records

Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), pages 2009–2016 Marseille, 11–16 May 2020 c⃝ European Language Resources Association (ELRA), licensed under CC-BY-NC 2009 Development of a Corpus Annotated with Medications and their Attributes in Psychiatric Health Records Jaya Chaturvedi1, Natalia Viani1, Jyoti Sanyal2, Chloe Tytherleigh1, Idil Hassan3, Kate Baird1, Sumithra Velupillai1, Robert Stewart1,2, Angus Roberts1 1King’s College London, 2South London and Maudsley NHS Foundation Trust, 3University of Leicester 1De Crespigny Road, London SE5 9RS, 2Camberwell, London SE5 8AZ, 3University Rd, Leicester LE1 7RH {jaya.chaturvedi, natalia.viani, chloe.tytherleigh, kate.baird, sumithra.velupillai, robert.stewart, angus.roberts}@kcl.ac.uk jyoti.jyoti@slam.nhs.uk, fah15@student.le.ac.uk Abstract Free text fields within electronic health records (EHRs) contain valuable clinical information which is often missed when conducting research using EHR databases. One such type of information is medications which are not always available in structured fields, especially in mental health records. Most use cases that require medication information also generally require the associated temporal information (e.g. current or past) and attributes (e.g. dose, route, frequency). The purpose of this study is to develop a corpus of medication annotations in mental health records. The aim is to provide a more complete picture behind the mention of medications in the health records, by including additional contextual information around them, and to create a resource for use when developing and evaluating applications for the extraction of medications from EHR text. Thus far, an analysis of temporal information related to medications mentioned in a sample of mental health records has been conducted. The purpose of this analysis was to understand the complexity of medication mentions and their associated temporal information in the free text of EHRs, with a specific focus on the mental health domain. Keywords: Medication, Drug, Natural Language Processing, Electronic Health Records, Temporality, Information Extraction 1. Introduction Electronic health records (EHRs) contain combinations of structured and unstructured (free text) fields. The free text within EHRs contains a large proportion (Stewart et al., 2009) and variety of information about clinical encounters that might go unnoticed if not explored. This is especially true for mental health records where many presentations, contextual factors, interventions and outcomes are not captured in structured fields (such as symptoms, behaviours, and self-reported experiences) so that the extraction of such information from free text generates a more accurate picture (Velupillai et al., 2018). In this domain, it is more likely for information such as drug prescriptions and related context to be available in the text rather than in the structured fields (Kadra et al., 2015). In the UK, many mental health medications are prescribed in primary rather than specialist care and therefore would not be recorded in hospital prescribing systems, even if these were in use. Consequently, hospital clinicians will routinely ask patients to list their medications and record these as free text in their clinical notes. There is unlimited value in being able to automatically extract information on medications for a variety of research purposes, and this is the main motivation for this particular study. Medication information is essential for …

Content truncated to 500 words