|
| EPSRC Reference: |
EP/F059345/1 |
| Title: |
Evolving Health Informatics: semantic frameworks and metadata-driven architectures |
| Principal Investigator: |
Professor J Davies |
| Other Investigators: |
|
| Researcher Co-investigator: |
|
| Project Partner: |
|
| Department: |
Computing Laboratory |
| Organisation: |
University of Oxford |
| Scheme: |
Standard Research |
| Starts: |
01 April 2008 |
Ends: |
30 September 2009 |
Value (£): |
201,679
|
| EPSRC Research Topic Classifications: |
| Intelligent and Expert Systems |
Medical Modelling and Simulation |
| Software Engineering |
|
|
| EPSRC Industrial Sector Classifications: |
|
| Related Grants: |
|
| Panel History: |
|
|
Summary |
Advances in technology allow us to communicate large amounts of information, almost instantaneously, between any two points on the globe. Advances in analysis and imaging techniques, and progress in genomic, proteomic, and metabonomic science, allow us to obtain detailed information about the health of an individual. Advances in the computerisation of social and business infrastructure allow us to obtain similarly detailed information about other aspects of our lives.
The automatic integration of this data, based upon a computable representation of its meaning or semantics, will revolutionise both medical and clinical research, and the impact on healthcare delivery will be dramatic. Not merely in terms of personalised medicine, informed by the new biology, but also in the very nature of national and international healthcare systems. Agencies will be able to work faster and more effectively in adapting to changes in the circumstances, from advances in the body of medical knowledge to public health emergencies. Their agility will be limited only by the human capacity of ideas and understanding.
As illustrations of what it is realistic to expect, within the next decade, we propose to investigate three simple scenarios, each addressing a different aspect of information-driven health: in on-demand collaboration on clinical trials; in control of infectious diseases; and in improving the efficiency of a portfolio of research.
There has been considerable emphasis upon the computational challenges encountered in the analysis of data, and much progress has been made in this respect: in particular, within the projects funded by the EPSRC and MRC as part of the UK e-Science Programme. However, there is growing recognition that the large-scale sharing and integration of data from dynamic, heterogeneous sources requires computable representations of the semantics of data, and it is here that a significant part of the challenge lies.
Natural language or informal understanding is sufficient for such a semantics only when the concepts are straightforward, the community is small or homogeneous, and the period of time over which understanding must be maintained is short. For problems of any complexity, communities of any size, or initiatives that are intended to last for many years, a more formal approach is required. The semantics has to be amenable to automatic processing, and this processing has to be automatically linked to the processing of the data itself.
This requires an advance in the state of the art of software engineering. It is not enough merely to mandate the use of languages and technologies such as XML and OWL, through funding and procurement policies: these are building blocks in the solution, but not the solution themselves. Rather, we need methods and tools for the creation, maintenance, and deployment of abstract models of information, studies, and processes, sufficient for the automatic generation and configuration of the software systems required to support information-driven health.
These methods and tools underpin most of the information technology needs set out in the "data mining and data fusion" roadmap presented in reports from the recent UK Foresight project on infectious diseases. Their development will require effective collaboration with users and domain experts, as well as advances in semantics- and model-driven software engineering research, above the level of industry-based technological development.
The grand challenge for information-driven health is to make semantics-driven management of data standard practice across the whole spectrum of healthcare and medical research.
|
| Final Report Summary |
The automatic integration of data, based upon a computable
representation of its meaning or semantics, will revolutionise both
medical and clinical research, and the impact on healthcare delivery
will be dramatic. Not merely in terms of personalised medicine,
informed by the new biology, but also in the very nature of national
and international healthcare systems. Agencies will be able to work
faster and more effectively in adapting to changes in the
circumstances, from advances in the body of medical knowledge to
public health emergencies. Their agility will be limited only by the
human capacity of ideas and understanding.
As illustrations of what it is realistic to expect, we have explored
several scenarios in information-driven health. In each case, our
investigations have led to the deployment of new technology in support
of clinical research and healthcare delivery. We are continuing the
work of this project as part of the "Hospital of the Future" grand
challenge, helping to standardise, manage, and integrate information
collected on patients in a hospital environment.
We are applying some of the lessons learnt during the project to the
development of a national data support service for the UK Medical
Research Council, going live in the first half of 2010, and in the
provision of informatics support for vaccine trials in developing
countries, and also in the UK. We are re-using some of the technology
produced in support of a E10m European-wide project on new cancer
therapies; some of this technology has been incorporated in the US
National Cancer Institute's caBIG program.
There has been considerable emphasis upon the computational challenges
encountered in the analysis of data, and much progress has been made
in this respect: in particular, within the projects funded by the
EPSRC and MRC as part of the UK e-Science Programme. However, there
is growing recognition that the large-scale sharing and integration of
data from dynamic, heterogeneous sources requires computable
representations of the semantics of data, and it is here that a
significant part of the challenge lies.
Natural language or informal understanding is sufficient for such a
semantics only when the concepts are straightforward, the community is
small or homogeneous, and the period of time over which understanding
must be maintained is short. For problems of any complexity,
communities of any size, or initiatives that are intended to last for
many years, a more formal approach is required. The semantics has to
be amenable to automatic processing, and this processing has to be
automatically linked to the processing of the data itself.
This requires an advance in the state of the art of software
engineering. It is not enough merely to mandate the use of languages
and technologies such as XML and OWL, through funding and procurement
policies: these are building blocks in the solution, but not the
solution themselves. Rather, we need methods and tools for the
creation, maintenance, and deployment of abstract models of
information, studies, and processes, sufficient for the automatic
generation and configuration of the software systems required to
support information-driven health.
The development of these methods and tools will require effective
collaboration with users and domain experts, as well as advances in
semantics- and model-driven software engineering research, above the
level of industry-based technological development. The wider grand
challenge for information-driven health is to make semantics-driven
management of data standard practice across the whole spectrum of
healthcare and medical research.
|
| Further Information: |
http://www.cancergrid.org |
| Organisation Website: |
http://www.ox.ac.uk |
|
|