Copy the page URI to the clipboard
Ahlfeldt, Hans; Borin, Lars; Daumke, Philipp; Grabar, Natalia; Hallett, Catalina; Hardcastle, David; Kokkinakis, Dimitrios; Mancini, Clara; Marko, Kornel; Merkel, Magnus; Pietsch, Christian; Power, Richard; Scott, Donia; Silvervarg, Annika; Gronostaj, Maria Toporowska; Williams, Sandra and Willis, Alistair (2006). Literature Review on Patient-Friendly Documentation Systems. Technical Report 2006/04; Department of Computing, The Open University.
DOI: https://doi.org/10.21954/ou.ro.0001603e
Abstract
This literature review forms a deliverable in the European Network of Excellence on Semantic Interoperability and Data Mining in Biomedicine. More specifically, it is part of a work package (wp27) which aims to develop and evaluate generic methods and tools for assisting patients to understand their health and healthcare by generating patient-friendly readable texts that paraphrase the content of their electronic health records. We have reviewed the literature in topics that we consider to be relevant to this work package. When appropriate, we cover variations in conditions in the four countries of the collaborating research groups (France, Germany, Sweden and the UK) and we cover corpora, tools and language technologies for the European languages of interest to these groups.First, we consider legal issues involved in patients gaining access to their medical records. Who can view the records? What data do they have the right to access? Are there any data that patients cannot access? Who can access records of dead patients?What about security and data protection? See chapter 2 for brief surveys of the current state of affairs in France, Sweden and the UK. Patient records are packed with jargon, acronyms and medical terms that clinical staff know and understand. Often there is a learning curve before patients become familiar with medical terms associated with their own particular illnesses and they may require more familiar words and phrases to describe medical concepts in an accessible form. The development of largescale medical term banks, thesauri and lexicons (e.g. ums specialist and Metathesaurus) enable Language Technology developers to generate reports for medical staff, but how can we communicate the same concepts to patients? We review the current literature on communicating technical medical terms in everyday language for patients and related issues. See chapter 3.Our survey on computational methodologies for generating patient-friendly texts included the following topics: extraction of terminologies from corpora, comparison of terms from different sources, automatic analysis of patient records, use of ontologies, logics to model terminological use and changes, text simplification and dialogue systems. See chapter 4. There have been many past nlg systems that generated output aimed at patients or doctors.We present an overview of these systems and compare them in 5dimensions:1. application area,2. knowledge used (domain knowledge, generic medical knowledge and linguistic knowledge), 3. user models and personalisation, 4. system evaluation, 5. use of hypertext See chapter 5.We have reviewed work, particularly in medical informatics, on automatic translation of technical medical language into language aimed at patients. Chapter 6 presents a survey of such systems.A number of empirical studies with patients have focused on the question of whether the provision of personalised information for patients is superior in various ways to general information.Will personalising information help patients be better-informed? Will it help them manage their illnesses better and comply with medical guidelines? Will it help them to take their medication in the correct manner? Will such information ultimately reduce hospital admissions? See chapter 7 for a survey of this literature.Our survey of existing corpus annotation tools, see chapter 8, describes existing tools and what they do. It also includes their availability, the languages they cover, their formats, platforms and locations. The tools are classified into:1. Tools for orthographic annotations (document information and document structure), 2. Tools for linguistic annotations (e.g. tokenization, stemming, morphology, pos, syntax), 3. Tools for semantic annotations (discourse-level, semantic tags and umls tags), 4. Workbench and ide tools.Our survey of existing corpora of patient information addressing patient information needs includes corpora that language engineers have used in the past in building systems as well as general linguistic corpora, medical corpora and others. See chapter 9.Chapter 10 surveys the Internet as a corpus, including access to and potential use of the web, Usenet, email and Internet relay chat. See chapter 10.
CORE (COnnecting REpositories)
CORE (COnnecting REpositories)
