Towards ease of building legos in assessing ehealth language technologies

Abstract

More and more scientific literature, care guidelines, health records, social media, and other textual eHealth information are electronically available. Language technologies provide a way to analyse these documents for the bene-fit of both individuals and populations. In order to catalyse the development of eHealth language technologies, we propose a virtual laboratory with a standardised platform for easy building and assessment of the systems from the "lego" bricks of shared data, resources, and software. Our aim is to address specific needs in eHealth: governance and shar-ing of private data; provenance and sharing of resources and software; system-atic benchmarking and quality control of systems and their components; and collaboration of eHealth language technology developers and users across healthcare services, academia, industry, and government. The Epicure virtual laboratory is intended to be used for software and re-source evaluation and development as well as for data analysis if data subjects' privacy is ensured. Epicure is a meta-framework in the sense of abstracting over existing frameworks. Its five roles for clients are data or resource provider, ap-plication assembler, application user, software developer, and sys-tem administrator. We have implemented Epicure based on publicly available software. Its con-trol layer is a Glassfish JavaEE server, providing a RESTful (REpresentational State Transfer) application programming interface; web interface for accessing and installing third-party platforms; and easy operation via standard web com-mands. After proper user authentication and authorisation of incoming requests, it builds applications, analyses data and assesses outcomes by orchestrating storage and execution layers. The storage layer of Epicure uses a CouchDB-based repository for centralised storage of data, resources, and software. It ena-bles controlling document access on the level of documents; tracking all chang-es; recording these revisions; storing all analysis outcomes; and associating the outcomes with the data, resources and software used in their generation. The execution layer of Epicure provides a runtime environment for executing data analysis tasks and installing third party platforms. It invokes tools as simple commands. A tool must be specify its input format, output formats, parameters, and their possible values as a file and be executable on a command line. Tools do not need to be installed within Epicure itself but instead be accessed via a network interface and wrapper, which provides access from Epicure to this re-mote service. Show more