© Bucur; licensee BioMed Central Ltd. 2015
Published: 22 May 2015
Service/tool, patient recruitment, restricted access.
To help enhance the participation of cancer patients in clinical trials we built an application that aims to support recruitment through the automatic evaluation of the eligibility of patients for trials based on matching the characteristics of the patient population required by the trial to the patient data available for instance in the hospital EHR (electronic health record).
The population to be enrolled in a trial is described by a set of free-text eligibility criteria that are both syntactically and semantically complex, which makes their automatic evaluation on the patient data in order to assess the eligibility of that patient for a set of trials a challenging task. The extraction and representation of the semantics of the trial criteria can be made more efficient by detecting structure and patterns in criteria, by information extraction and annotation techniques and by formalization of criteria.
Our approach is generic and flexible, integrating loosely coupled components with well-defined standard interfaces and making use of prominent standards in the healthcare domain, such as HL7 RIM for our Clinical Data Model and BRIDG for the Trial Metadata Repository in which we preserve trial descriptions (e.g. eligibility criteria, associated formalisms and other relevant metadata). We combine the use of formal representations of eligibility criteria with a pragmatic and efficient implementation in which templates are defined, linked to execution logic, and extensively reused. The solution can integrate different formalisms, data representations and models to fit the needs of each new healthcare environment.
Status of development
Version 3 (June 2014). Evaluation and validation at workshop in June 2014, several sessions at clinical sites in September and October 2014.
Oncologists, trial nurses, investigators, clinical researchers.
This article is published under license to BioMed Central Ltd. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated.