High quality, integrated clinical information is at the intersection of clinical research, evidence-based health care and the clinical application of genetic and genomic research. A coherent clinical information framework is required to meet the needs of patients, their families and carers, clinical professionals and biomedical scientists, health care enterprises and the public at large.
Capture, integration, and presentation of descriptive information is a major barrier to achieving such a framework. Clinical histories, radiology and pathology reports, annotations on genomic and image databases, technical literature and Web based resources all typically originate as text. Often they are dictated and then typed; alternatively they are laboriously coded or annotated manually, usually in incompatible formats that lack rigour and hence cannot be scaled up or aggregated effectively. We thus face an escalating imbalance between the richness of our ability to collect very large sets of genomic, image, and other technical information, and the poverty of our means to describe the scientific and clinical significance of that information. This same inability to deal effectively with clinical information is a key limitation to our using informatics to support safe, evidence-based healthcare and to gather the information needed to deliver clinical governance and other strategic goals of the NHS.
The technologies now exist for a concerted approach to removing this barrier, thereby facilitating clinical applications of eScience and GRID developments. CLEF aims to create a scalable, generic architecture for capture and management of clinical and other descriptive data, integrated with genomic data and images and linked to literature and web resources.
Conceptually, the project places patients and their histories at the centre of clinical practice and research. It seeks to enable partnerships between clinical and basic scientists, healthcare professionals, patients and public. Clinically, the project addresses areas where collaboration and shared care are critical, and where genomic and image data are providing powerful new tools - studies of the ageing brain and clinical and genomic determinants in cancer treatment. Organisationally, it focuses on sharing and pooling information and knowledge - issues such as confidentiality and security and barriers to the realisation of clinical benefits from available and emerging GRID technologies. Technically, it brings together recent developments in information integration, knowledge representation, medical records and computational linguistics, and state of the art expertise in health informatics across the UK, Europe and internationally, as well as key industrial partnerships and participation in international standards organisations. Tactically it concentrates on sharing information and creating repositories for clinical research, but it looks forward, when the technology is sufficiently mature to meet the stringent time limitations of clinical practice, to direct support for health care professionals for clinical governance, evidence-based medicine, and clinical decision support. It concentrates on issues of clinical language and information representation in texts, but looks forward to direct speech input as that technology improves.
The clinical exemplars chosen share several requirements: integration of distributed heterogeneous databases of descriptive text, image, genomic, and quantitative information; large populations requiring shared care and multicentre trials; intense research on genetic and genomic factors; major impact on population health and NHS resources. The domains are large enough to test the methods but sufficiently focused to be manageable. Each has near term needs, but major advance requires sustained research.
The outcomes of the project will be:
By the end of the project, the gap between our ability to manage and integrate clinical information and our ability to manage image and genomic information will have been significantly narrowed so that effective use can be made of the broader eScience framework to benefit clinical research, patients, and public alike.