Secure Healthcare Data for Personalised Medicine

Secure big data management and informatics platforms maximise use of clinical data 

Unlocking the potential of personal healthcare data

Secure access to patient data and analysis tools to run on that data is revolutionizing the treatment of a wide range of diseases, by using advanced data analysis and simulation techniques to underpin the clinical decision making process. The problem of sharing clinical data presents a major hurdle if patient specific data analytics and computer simulation are to be incorporated into clinical practice, and for the facilitation of research using that data.

The data sources held by hospitals represent a major resource that is currently not adequately exploited, either by researchers or clinicians. Patient data collected as part of routine clinical practice, and which can be used as input to a wide range of analytics techniques, initially resides in information systems based within the hospital where the data was obtained. This data includes medical images obtained through techniques such as magnetic resonance imaging (MRI) or computed tomography (CT), biopsy microphotographs, DNA and RNA sequence data, and records of clinical treatment regimes.

The data held by clinical data systems can be used in two different ways: (1) to compose large, (pseudo)-anonymized datasets from multiple sources, to perform inductive reasoning and to structure and support clinical trials; (2) from a single patient to run a workflow in support of a clinical decision making process.

At the heart of our work in the field of personalised medical research is the need to gain access to these distributed data sources in a routine, transparent way, following appropriate anonymization and security procedures.

The solution: IMENSE and AmpoulePi

We developed the open source Individualized MEdiciNe Simulation Environment (IMENSE), which provides a platform to securely manage the foregoing diverse clinical data types, and to perform wide ranging analysis on that data, ultimately with the intention of enhancing clinical decision making with direct impact on patient health care.  Our original area of application was for treatment of lung cancers and gliomas, but the solution is much more widely applicable across disease cases. The software environment allows clinicians to assess the condition of a patient and to organise appropriate personalised treatment; for example, based on a patient’s particular genetic variant(s), we can perform molecular simulations that indicate which of a range of existing drugs should be administered.

A more recent development extends the capabilities of IMENSE into a more powerful and geographically distributed data warehouse, called AmpoulePi, into which data sources from multiple hospitals can be aggregated to generate substantially larger data collections upon which more comprehensive data analytics can be performed. AmpoulePi is currently being used to store and manage data from a range of international cancer clinical trials, and for cardiovascular outcomes research within UK.

New capabilities for personalised medicine

The benefit of these informatics platforms is clear: not only do our solutions allow data from diverse sources to be linked and integrated, they also provide a common platform that researchers can use to initiate analytics workflows based on that data, as they offer standards compliant interfaces and APIs into which many existing and future tools and services can be plugged. These capabilities are key to meeting the needs of the new and rapidly growing field of personalised medicine.

Publications

S. J. Zasada , T. Wang , A. Haidar , E. Liu, B. Graf, G. Clapworthy, S. Manos, P. V. Coveney, “IMENSE: An e-Infrastructure Environment for Patient Specific Multiscale Modelling and Treatment”, Journal of Computational Science, 3, 314-327, (2012), DOI: 10.1016/j.jocs.2011.07.001

B. Jefferys, I. Nwankwo, E. Neri, D. Chang, L. Shamardin, S. Hänold, N. Graf, N. Forgo and P.V. Coveney, “Navigating legal constraints in clinical data warehousing: a case study in personalised medicine”, Journal of the Royal Society Interface Focus, 3 (2), (2013), DOI: 10.1098/rsfs.2012.0088

S. Wan, D. Wright, P. V. Coveney, “Mechanism of Drug Efficacy within the Epidermal Growth Factor Receptor Revealed by Microsecond Molecular Dynamics Simulation”, Molecular Cancer Therapeutics, 11(11), 2394-400, (2012), DOI: 10.1158/1535-7163.MCT-12-0644-T