Enriching knowledge and enhancing care through health data

TRANSFoRm

Introduction

The European Commission FP7 sponsored project TRANSFoRm 2010-15 sought to develop, pilot and evaluate a core information architecture for the Learning Health System (LHS) in Europe. The single richest source of routine healthcare data lies within the records of Europe’s General Practitioners. Primary Care is responsible for first contact, continuing, and generalist care of the entire population from birth to death. Any project that aims to comprehensively support the integration of clinical and research data should begin with Primary Care.

Taking as its core the consultation, the premise was that only by interacting in real time, via the electronic health record, with the workflow of the consultation, can a LHS be achieved. The conjunction of a key reason to enter data (decision support) is essential, as data quality in clinical settings cannot be maintained by research requirements alone, but needs to meet a clinical practice need. TRANSFoRm aimed to develop a core, common technology for the semantic mediation of research and clinical data at the point of care, and the presentation of research workflow, and clinical prediction rules for diagnosis. Other than the theoretical aspect of supporting both parts of a learning healthcare system, there was a deep integration of the underlying technical work packages (5, 6, & 7) in the development of a common set of models, ontologies, methods and tools for delivering both aspects of the project. This is illustrated in the figure below:

 

TRANSFoRm aimed to develop the digital infrastructure for the LHS driven by advanced computational infrastructure that can improve both patient safety and the conduct and volume of clinical research in Europe. The EU policy framework for information society and media, i2010, identifies eHealth as one of the principal areas where advances in ICT can create better quality of life for Europe’s citizens. ICT has important roles in communication, decision-making, monitoring and learning in the healthcare setting. TRANSFoRm recognised the need to advance the underpinning information and computer science to address these issues in a European and international context. Providing interoperability between different clinical systems, across national boundaries, and integration of clinical systems and research systems lies at the heart of the eHealth Action Plan 2004.

TRANSFoRm sought to deliver interoperability between clinical and research systems for specific key ‘blocks’ in the research process: feasibility, subject identification, eSource and follow up. In both domains, fragmentation of records and proprietary systems that do not adhere to standards within the domain are as much of a challenge as the legal and ethical issues that complicate access to clinical data for researchers. However, significant advances in international standards and in computational technology to support interoperability offer a way to overcome these challenges. Furthermore, advances in the understanding of clinical judgment and decision making, and the possible ways of supporting them via ICT can inform the design of more ‘intelligent’ electronic health record systems.

TRANSFoRm has developed the LHS in the following three areas:

  1. Using CDISC standards and a common clinical ontology to create a fully functioning eSource system for clinical trials, evaluated in five EHR systems in four member states. This is being developed and made available as open-source via CDISC and i~HD.
  2. Demonstrating a method for deploying distributed phenotype-genotype queries against secure, private and disparate data sources. This will be made available via i~HD.
  3. Developing a prototype LHS for supporting diagnosis in primary care. This will be taken forward by TRANSFoRm consortium partners and a group of EHR vendors.

 

The following page contains the project deliverables as approved by the EC, presentations and publications relating to the project.

Queries about future developments, access to tools and models should be addressed in the first instance to the project Scientific Director, Prof Brendan Delaney, Chair in Medical Informatics and Decision Making, Imperial College London. brendan.delaney@imperial.ac.uk

The Transform project deliverables as approved by the EC, presentations and publications can be found here:

 
Published on: 01 August 2016