In the era of data-driven science, corpus-based language technology is an essential part of cyber physical systems. In this chapter, the authors describe the design and the development of an extensible domain-specific web corpus to be used in a distributed social application for the care of the elderly at home. The domain of interest is the medical field of chronic diseases. The corpus is conceived as a flexible and extensible textual resource, where additional documents and additional languages will be appended over time. The main purpose of the corpus is to be used for building and training language technology applications for the “layfication” of the specialized medical jargon. “Layfication” refers to the automatic identification of more intuitive linguistic expressions that can help laypeople (e.g., patients, family caregivers, and home care aides) understand medical terms, which often appear opaque. Exploratory experiments are presented and discussed.

Web corpora are a cornerstone of modern Language Technology. Corpora built from the web are convenient because their creation is fast and inexpensive. Several studies have been carried out to assess the representativeness of general-purpose web corpora by comparing them to traditional corpora. Less attention has been paid to assess the representativeness of specialized or domain-specific web corpora. In this paper, we focus on the assessment of domain representativeness of web corpora and we claim that it is possible to assess the degree of domain-specificity, or domainhood, of web corpora. We present a case study where we explore the effectiveness of different measures - namely the Mann-Withney-Wilcoxon Test, Kendall correlation coefficient, Kullback–Leibler divergence, log-likelihood and burstiness - to gauge domainhood. Our findings indicate that burstiness is the most suitable measure to single out domain-specific words from a specialized corpus and to allow for the quantification of domainhood.

In this position paper we briefly introduce SmartEnv ontology which relies on SEmantic Sensor Network (SSN) ontology and is used to represent different aspects of smart and sensorized environments. We will also talk about E-carehome project aiming at providing an IoT-based health-care system for elderly people at their homes. Furthermore, we refer to the role of SmartEnv in Ecarehome and how it needs to be further extended to achieve semantic interoperability as one of the challenges in development of autonomous health care systems at home.

In this position paper, we put forward two claims: 1) it is possible to design a dynamic and extensible corpus without running the risk of getting into scalability problems; 2) it is possible to devise noise-resistant Language Technology applications without affecting performance. To support our claims, we describe the design, construction and limitations of a very specialized medical web corpus, called eCare_Sv_01, and we present two experiments on lay-specialized text classification. eCare_Sv_01 is a small corpus of web documents written in Swedish. The corpus contains documents about chronic diseases. The sublanguage used in each document has been labelled as “lay” or “specialized” by a lay annotator. The corpus is designed as a flexible text resource, where additional medical documents will be appended over time. Experiments show that the lay-specialized labels assigned by the lay annotator are reliably learned by standard classifiers. More specifically, Experiment 1 shows that scalability is not an issue when increasing the size of the datasets to be learned from 156 up to 801 documents. Experiment 2 shows that lay-specialized labels can be learned regardless of the large amount of disturbing factors, such as machine translated documents or low-quality texts that are numerous in the corpus

In this position paper, we put forward two claims: 1) it is possible to design a dynamic and extensible corpus without running the risk of getting into scalability problems; 2) it is possible to devise noise-resistant Language Technology applications without affecting performance. To support our claims, we describe the design, construction and limitations of a very specialized medical web corpus, called eCare_Sv_01, and we present two experiments on lay-specialized text classification. eCare_Sv_01 is a small corpus of web documents written in Swedish. The corpus contains documents about chronic diseases. The sublanguage used in each document has been labelled as “lay” or “specialized” by a lay annotator. The corpus is designed as a flexible text resource, where additional medical documents will be appended over time. Experiments show that the lay-specialized labels assigned by the lay annotator are reliably learned by standard classifiers. More specifically, Experiment 1 shows that scalability is not an issue when increasing the size of the datasets to be learned from 156 up to 801 documents. Experiment 2 shows that lay-specialized labels can be learned regardless of the large amount of disturbing factors, such as machine translated documents or low-quality texts that are numerous in the corpus

Det är glädjande att myndigheter nu äntligen tittar mer på internationellt delade detaljerade dokumentationsmodeller för innehåll i journaler. Vi hoppas att de ger tillräckligt kraftfulla och tydliga budskap så att de upphandlande vårdgivarna också ser vikten av detta. Om vi ska bli världsbäst på eHälsa krävs internationellt samarbete, skriver flera forskare i medicinsk informatik.

National eHealth – the strategy for accessible and secure information in health and social care – is a Swedish initiative aiming at improving information management within the healthcare and social services sector. SNOMED CT is one tool in this strategy. To gain experience from SNOMED CT implementation, the National Board of Health and Welfare (host of the National Release Center of SNOMED CT) funded a number of pilot projects during 2013. Our project was one of these, focusing on facilitation of information sharing by using SNOMED CT in two application areas as described below. Furthermore, the project initiated a dialog with the EHR vendor concerning future SNOMED CT implementation.

One area was transfer of discharge summaries from hospital care at Östergötland County Council to municipal home care. A discharge summary consists of a template with encoded headings, associated free text fields, and instructions about intended content. These headings were mapped to SNOMED CT.

The other area was transfer of information from the EHR system at hospitals in three counties to the Swedish Stroke Register, a national quality register. The specification of information requested by the register was analyzed. Then, an EHR template was outlined, taking into account the clinical stroke process requirements, quality register requirements, and the information model of the EHR system. The draft template was based on mappings to SNOMED CT to facilitate a mutually agreed template. That means a template common for the three county councils, as well as information transfer to the register, and at the same time reduce the need for double documentation, information searching and other manual routines.

Lessons learned include that mapping EHR template components and other EHR objects to SNOMED CT concepts holds potential benefits, regardless of whether one’s EHR system can handle mappings. Mapping activities may aid review and management of existing and development of new templates. Furthermore, mappings may be used as a common point of reference when information is shared. Mapping ambiguous template headings to SNOMED CT concepts was found to be time consuming and uncertain and mapping seems to be most useful when EHR contents are structured. These mapping source prerequisites imply that existing documentation practice needs to be revised and that organizations must support end users in that process. The project also concluded that mappings would be even more advantageous if EHR systems can handle mappings of different objects types. Organizations also need to allocate adequate resources for managing its own mappings as well as contributing to the development of SNOMED CT as such.

Finally, the project found that training of mapping personnel benefits from integrating theoretical instruction and practical use of SNOMED CT, and that finding the correct concept in SNOMED CT calls for clinical expertise in order to be successful.

Background

The openEHR project and the closely related ISO 13606 standard have defined structures supporting the content of Electronic Health Records (EHRs). However, there is not yet any finalized openEHR specification of a service interface to aid application developers in creating, accessing, and storing the EHR content.

The aim of this paper is to explore how the Representational State Transfer (REST) architectural style can be used as a basis for a platform-independent, HTTP-based openEHR service interface. Associated benefits and tradeoffs of such a design are also explored.

Results

The main contribution is the formalization of the openEHR storage, retrieval, and version-handling semantics and related services into an implementable HTTP-based service interface. The modular design makes it possible to prototype, test, replicate, distribute, cache, and load-balance the system using ordinary web technology. Other contributions are approaches to query and retrieval of the EHR content that takes caching, logging, and distribution into account. Triggering on EHR change events is also explored.

A final contribution is an open source openEHR implementation using the above-mentioned approaches to create LiU EEE, an educational EHR environment intended to help newcomers and developers experiment with and learn about the archetype-based EHR approach and enable rapid prototyping.

Conclusions

Using REST addressed many architectural concerns in a successful way, but an additional messaging component was needed to address some architectural aspects. Many of our approaches are likely of value to other archetype-based EHR implementations and may contribute to associated service model specifications.

The possibility of post-coordination of SNOMED CT concepts, especially by clinical users, is both an asset and a challenge for SNOMED CT implementation. To get insight in the applicability of post-coordination, we analyzed scenarios for user-directed coordination that are described in the documentation of SNOMED CT. The analyses were based on experiences from previous and ongoing research and implementation work, including national mapping projects, and investigations on collection of data for multiple uses. These scenarios show various usability and representation problems: high number of relationships for refinement and qualification, improper options for refinement, incorrect formal definitions, and lack of support for applying editorial rules. Improved user-directed coordination in SNOMED CT in real practice requires advanced sanctioning, increased consistency of definitions of concepts in SNOMED CT, and real-time analysis of the post-coordinate expression.