Conference PaperPDF Available

The Integration Challenges in Bridging Patient Care and Clinical Research in a Learning Healthcare System

Authors:

Abstract

Routinely collected clinical data can be reused in a number of research tasks, including cohort identification and pre-population of electronic case report forms. TRANSFoRm adopts a model-based, mediation approach to address the data integration challenges of such reuse and bridge the semantic gap between clinical and research domains.
The Integration Challenges in Bridging
Patient Care and Clinical Research in a
Learning Healthcare System
S.N. LIM CHOI KEUNGa,1, J.-F. ETHIERb, L. ZHAOa, V. CURCINc
and T.N. ARVANITISa
aInstitute of Digital Healthcare, WMG, University of Warwick, UK;
bINSERM UMR_S 872, France;
cDepartment of Primary Care and Public Health, Imperial College London, UK
Abstract Routinely collected clinical data can be reused in a number of research
tasks, including cohort identification and pre-population of electronic case report
forms. TRANSFoRm adopts a model-based, mediation approach to address the
data integration challenges of such reuse and bridge the semantic gap between
clinical and research domains.
Keywords. electronic health records, secondary use, integration
Introduction
The TRANSFoRm project aims to improve patient safety in Europe and increase the
volume of clinical research. A dual-layer modelling approach separates the more stable
domain information from the technical implementations of heterogeneous systems
[1]. We describe the integration challenges in reusing primary care data for pre-
populating electronic case report forms (eCRFs) from electronic health records (eHRs).
1. Methods
The dual-level modelling organises health information into information models that
allow deployment in different technical formats. On Level 1, the Clinical Research
Information Model (CRIM) depicts the workflow and data requirements for the clinical
research task, while the Clinical Data Integration Model (CDIM) ontology presents a
coherent and unified representation of the primary care domain. Level 2 uses
archetypes, defined in openEHR Archetype Definition Language (ADL), for the
individual specifications to represent the data elements. Those can be newly entered or
extracted from eHR systems [1]. CDIM references allow usage of the TRANSFoRm
unified interoperability framework [2]. As part of this framework, Data Source Models
(DSM) are developed to define the data schema of each data source, and DSM
mappings define how the CDIM ontology concepts map to the data source schema. The
1Corresponding Author: Dr Sarah N. Lim Choi Keung; Email: s.n.lim-choi-keung@warwick.ac.uk
DSM and its maps are used to translate the archetypes into a query executable at the
data source, e.g. to retrieve eCRF elements available from the eHR. Archetypes are
embedded into CDISC Operational Data Model (ODM), a standard for clinical research
data collection, to ensure reusability of the approach.
2. Results and Discussion
Figure 1 shows an example of the transformation process that allows eHR data to be
reused in a clinical study. While the DSM definition and maps need to be developed
only once per data source, the correct semantic meaning needs to be precisely modelled
in close collaboration with the data source team. Supplementary study information can
be entered during research visits, without being added to the eHR.
Figure 1. Example of pre-population of comorbidities for a gastro-oesophageal reflux disease (GORD) study.
3. Conclusions
We have presented a dual-level modelling approach to enable semantic interoperability
between clinical research tasks and primary care data sources, that is flexible enough to
handle new archetypes and data sources, while keeping the information model stable.
Acknowledgements
The authors thank all TRANSFoRm project staff for their contribution. The TRANSFoRm project is partially
funded by the European Commission under the 7th Framework Programme (Grant Agreement 247787).
References
[1] S.N. Lim Choi Keung et al. “Detailed Clinical Modelling Approach to Data Extraction from
Heterogeneous Data Sources for Clinical Research”. 2014 AMIA Clinical Research Informatics
Summit, San Francisco, April 2014 (Accepted).
[2] J.-F. Ethier et al. “A unified structural/terminological interoperability framework based on LexEVS:
application to TRANSFoRm”. J Am Med Inform Assoc. 2013;20(5):986–94.
... Firstly, the algorithm calculates the label and node concepts, secondly it computes the conceptual relationship. The Zhao, C. [30] has proposed a multilayer schema matching approach with many layers. The first layer connected with semantic similarity. ...
Article
Full-text available
The reuse of routinely collected clinical data for clinical research is being explored as part of the drive to reduce duplicate data entry and to start making full use of the big data potential in the healthcare domain. Clinical researchers often need to extract data from patient registries and other patient record datasets for data analysis as part of clinical studies. In the TRANSFoRm project, researchers define their study requirements via a Query Formulation Workbench. We use a standardised approach to data extraction to retrieve relevant information from heterogeneous data sources, using semantic interoperability enabled via detailed clinical modelling. This approach is used for data extraction from data sources for analysis and for pre-population of electronic Case Report Forms from electronic health records in primary care clinical systems.
Article
Full-text available
Objective Biomedical research increasingly relies on the integration of information from multiple heterogeneous data sources. Despite the fact that structural and terminological aspects of interoperability are interdependent and rely on a common set of requirements, current efforts typically address them in isolation. We propose a unified ontology-based knowledge framework to facilitate interoperability between heterogeneous sources, and investigate if using the LexEVS terminology server is a viable implementation method. Materials and methods We developed a framework based on an ontology, the general information model (GIM), to unify structural models and terminologies, together with relevant mapping sets. This allowed a uniform access to these resources within LexEVS to facilitate interoperability by various components and data sources from implementing architectures. Results Our unified framework has been tested in the context of the EU Framework Program 7 TRANSFoRm project, where it was used to achieve data integration in a retrospective diabetes cohort study. The GIM was successfully instantiated in TRANSFoRm as the clinical data integration model, and necessary mappings were created to support effective information retrieval for software tools in the project. Conclusions We present a novel, unifying approach to address interoperability challenges in heterogeneous data sources, by representing structural and semantic models in one framework. Systems using this architecture can rely solely on the GIM that abstracts over both the structure and coding. Information models, terminologies and mappings are all stored in LexEVS and can be accessed in a uniform manner (implementing the HL7 CTS2 service functional model). The system is flexible and should reduce the effort needed from data sources personnel for implementing and managing the integration.
Detailed Clinical Modelling Approach to Data Extraction from Heterogeneous Data Sources for Clinical Research
  • S N Lim Choi
  • Keung
S.N. Lim Choi Keung et al. " Detailed Clinical Modelling Approach to Data Extraction from Heterogeneous Data Sources for Clinical Research ". 2014 AMIA Clinical Research Informatics Summit, San Francisco, April 2014 (Accepted).