Objectives

The primary objective of our research is providing clinicians with advanced notice of upcoming hypotensive episodes.

In order to achieve this result we’re needing to solve a number of issues:

* Agree a common definition of hypotensive episode – all six of our centres currently work to different definitions
* Build a software interface which collects data from patient monitoring devices – all centres have different equipment
* Find a way of transmitting patient data from the research centres to our data warehouse
* Build software which collects observation, treatment and outcome data at the bedside
* Build a Bayesian Artificial Neural Network and train it to recognise patterns which precede hypotensive episodes
* Build software to enable researchers to analyse actual data, identifying circumstances in which the BANN achieves an accurate prediction and those in which if provides false positives
* Build software which alerts clinicians to potential upcoming episodes.
* Multi stage clinical trial.

In parallel the project includes the need for multi stage ethics approval, support from IT staff in each of the centres, identification and protection of foreground IPR, and multiple routes to market.

We’re also required to promote Framework 7 research and collaborate with other FP7 projects as appropriate.

Results

The starting point for our research has been a database of patient care data amassed as part of the Brain IT project, previously funded under Frameworks 4 and 5. This data is minute by minute readings from monitors, and comprises more than 200 patients with traumatic brain injuries. In some cases the data is incomplete and possibly inaccurate.

In the first stage we analysed the legacy data testing the various definitions of hypotension used by the research centres. Comparison of the definitions and events indicated by them enabled us to agree between all six centres a common definition, on which we could train the BANN.

In the second stage the BANN was used to examine patterns of parameters preceding episodes. Subsequent monitoring of those patterns suggested approximately 35% of future episodes could be identified as outputs from the pattern recognition. In addition some false positive predictions indicated ways the monitored parameters and definitions could be refined to improve accuracy.

In the third stage, working with IT staff at the centres data capture and transmission software has been built and installed. Software for collecting data at the bedside has been built in conjunction with clinical staff and installed. Software enabling researchers to monitor and enhance the accuracy of the prediction engine has been installed and is now in production use.

in the fourth stage we’ll be monitoring and enhancing the BANN prediction capabilities, preparing data which will support our application for ethics approval for stage five – live monitoring and alerting of upcoming episodes.

Throughout the project we’ve been researching questions related to the protection of IPR in the worlds major markets. As of yet we’ve made no application for patent – because we haven’t finished the research. We’re still refining our understanding of monitored parameters and which patterns offer which levels of accurate prediction.

We’ve also collaborated with multiple public bodies, promoting FP7 and offering guidance to potential applicants.

The Avert-IT project has been selected by the Use and Diffuse project as an example of best practice and features in the projects publications.

Over the weekend we had a chance to get the whole team together and review our progress.

Vilnius isn’t the easiest place to get to, for most of us at least, which helps us understand how difficult it can be for Arminas to join us in other parts of Europe.

But the real benefit of his hosting the meeting was we all got to experience Vilnius, a really interesting city in glorious autumn sunshine.

Rightly, the tourism was a side show to the main event – our project review.

The old town is steeped in history, full of character and a lot of fun. Lithuanian cuisine offers an exciting blend of gourmet and country cooking and there are dozens of quality restaurants where it can be enjoyed.

We aren’t ready to announce results to the world at large yet, but can confirm we’re heading in the right direction. We already have minute by minute parameter data collecting from multiple, international, sites and we are predicting upcoming hypotensive events.

Quite how we’re doing this is, for the moment, understood only by some very special people. Bayesian Artificial Neural Network technology is designed to find out stuff the human brain can’t cope with and in our case it is.

The project is still a year away from sharing its results, during which time some other very special people, will be managing the clinical trial.

The Use and Diffuse Project is funded by the EU under the FP7 research grant programme. The project will shortly publish its report, guiding Universities and SMEs on how to apply for, manage and exploit EU grants for research.

The report quotes four projects and profiles them as case studies of best practice in order that others may be better equipped to take advantage of EU support.

Happily Avert-IT is one of the four case studies. Here’s the foreword from the draft report, soon to be published.

Foreword
This Guide is intended to provide Small and Medium Sized Enterprises (SMEs), as well as Universities, Institutes and other Research Technology Development organisations (RTDs) with practical, useful and easy to follow advice on how to maximize the impact of Research and Development projects involving SMEs by ensuring that the results are effectively used and disseminated.

The Guide has been produced as part of Coordination and Support Activities being carried in the “USEandDIFFUSE” Project (Support of dissemination and exploitation of results obtained in research projects realized with the participation of the SME sector), that is funded under the European Commission’s 7th Framework Programme (FP7), and more specifically under “Research for the Benefit of SMEs”.

Input for the manual has been based on 2008 research conducted on Research and Development projects carried out in Health and ICT sectors. Although it has not been explicitly validated, it is likely that these findings are equally applicable for other sectors too. Neither the authors nor any person acting on their behalf may be held responsible for the use that may be made of the information contained therein.

The USEandDIFFUSE project…

aims to support the dissemination and exploitation of results of research projects involving SMEs, based on an analysis of current practices in the use of RTD results in projects involving SMEs in order to draw upon best practice and guidelines that can be carried forward and disseminated to benefit existing and future R+D efforts involving industry.

In addition to this Guide, the project website http://www.useanddiffuse.eu offers a good source of information about using and disseminating RTD results and also provides the contact details of the Project Coordinator and the consortium of partners.

Richard Sinnott will be presenting a paper entitled “e-Infrastructure Supporting Secure, Process-oriented Clinical Data Linkage” to the International Conference on Exploiting Existing Data for Health Research
which will be held at St Andrews, Scotland, September 2009.

June 14th and 15th Anthony Stell presented to this workshop at Manchester University

The talk was called “Clinical Projects at NeSC” covering a number of projects bu mostly focused on Avert-IT. The workshop was funded by EPSRC.

For more details goto DReSNet

During the first half of 2009 member of the research team have shared the work involved in the project in the form of publications and presentations, as follows:

Journals

A.J. Stell, R.O. Sinnott, J. Jiang, R. Donald, I. Chambers, G. Citerio, P. Enblad, B. Gregson, T. Howells, K. Kiening, P. Nilsson, A. Ragauskas, J. Sahuquillo, I. Piper, Federating Distributed Clinical Data for the Prediction of Adverse Hypotensive Events Journal of the Philosophical Transactions of the Royal Society A, July 2009, 367:2679-2690.

P. Enblad, I. Piper, R.O. Sinnott, Information Processing, Data Acquisition and Storage, Computers, Engineering and the future (Section VII), Monitoring in Neurocritical Care, eds. Le Roux, Levine, Kofke, 2009.

I. Piper, I. Chambers, G. Citerio, P. Enblad, B. Gregson, T. Howells, K. Kiening, J. Mattern, P. Nilsson, A. Ragauskas, J. Sahuquillo, R. Donald, R.O. Sinnott, A. Stell, The Brain Monitoring with Information Technology (BrainIT) collaborative network: EC Feasibility Study Results, submitted to Acta Neurochirurgica, 2009.

R.O. Sinnott, I. Piper, e-Infrastructures Fostering Multi-Centre Collaborative Research into the Intensive Care Management of Patients with Brain Injury, Handbook on Research on Information Technology, November 2008. [Book Chapter]

Refereed Conference Papers

A.J. Stell, R.O. Sinnott, O. Ajayi, Security Oriented e-Infrastructures Supporting Neurological Research and Clinical Trials, 2nd International Conference on Availability, Reliability and Security, (ARES’07), Vienna, Austria, April, 2007.

A.J. Stell, R.O. Sinnott, O. Ajayi, Supporting Nationwide e-Clinical Trials and Studies, Proceedings of 15th Mardi Gras Conference, Baton Rouge, USA, February 2008.

A. Stell, R.O. Sinnott, J. Jiang, I. Piper, A Clinical Grid Infrastructure Supporting Adverse Hypotensive Event Prediction, HealthGrid workshop, CCGrid 2009, Shanghai, China, May 2009.

R.O. Sinnott, O. Ajayi, A.J. Stell. Data Privacy by Design: Digital Infrastructures for Clinical Collaborations, International Conference on Security and Privacy, Orlando, USA, July 2009.

A.J. Stell, R.O. Sinnott, J. Jiang, I. Piper, R. Donald, Federating Distributed Clinical Data for the Prediction of Adverse Hypotensive Events, UK e-Science All Hands Meeting conference, Edinburgh, September 2008.

A.J. Stell, R.O. Sinnott, J. Jiang, A Federated Data Collection Application for the Prediction of Adverse Hypotensive Events, submitted to first International Workshop on Information Technology for Patient Safety (ITPS 2009), Cyprus, November 2009.

Talks/Presentations (some touch on AvertIT as an example)

R.O. Sinnott, Usability and Interoperability for Grid Security, invited talk given Trust and Security Workshop, Oxford, May 2008.

R.O. Sinnott, BioGrids and Beyond, invited talk at the International HealthGrid 2008 conference, Chicago, USA, June 2008.

R.O. Sinnott, Lessons Learned in Developing and Supporting e-Biomedical Research, invited talk given at Workshop on Building the e-Library, the University Health and Medical Librarians Group, Kelvin Conference Centre, Glasgow, Scotland, June 2008.

R.O. Sinnott, The digital infrastructure security perspective: a brief overview of current and anticipated developments in e-Infrastructure security, National Centre for e-Social Science workshop on Secure Access to Confidential Data, Manchester, UK, June 2008.

R.O. Sinnott, Access, Use and Re-Use, presented at Data Curation Centre (DCC-101) training course, Edinburgh, UK, October 2008.

R.O. Sinnott, e-Infrastructure Security and Data Archives, Invited Talk to UK Data Archives, University of Essex at Colchester, UK, November 2008.

R.O. Sinnott, Requirements for Repository Environments: Supporting User and Provider Friendly Single Sign-On Models, Invited Talk to Repository Curation Service Environments (RECURSE) Workshop at the Digital Curation Conference (DCC), Edinburgh, UK, December, 2008.

R.O. Sinnott, VPman and SPAM-GP (the Directors Cut), Invited Talk at Security-workshop, Daresbury, UK, December, 2008.

R.O. Sinnott, Supporting Collaborative Clinical Research, Invited Talk to Scottish Genetic Anomaly Network, Stirling, UK, March, 2009.

R.O. Sinnott, Access, Use and Reuse, Invited Talk to Digital Curation workshop (DCC), London, UK, March 2009.

R.O. Sinnott, Cloud-based Security Services, Invited Talk at e-Science Institute theme on Web 2.0 and Cloud technologies, March, 2009.

Kaunas (Lithuania) on June 6th, 2009. – Kaunas Lithuania

the 14th Congress – Euroacademia Multidisciplinaria Neurotraumatologica

Karl Kiening presented our work in Avert-IT as part of the ICU Monitoring sessions.

Arminas Ragauskas presented a paper on Non Invasive ICP Monitoring and displayed a poster promoting the work of the project.

ragauskas emn2009 AverIT v4

23 -25 June in Dublin, Ireland.

The Sixth International Conference on Condition Monitoring and Machinery Failure Prevention
Technologies

Iain Chambers presented the Avert-IT project and it’s work in the area of monitoring injured brains.

As a result of the presentation Iain has been asked to publish a paper detailing the research and the possibilities of extending the BANN technology to the condition monitoring sector.

June 1st 2009

The Royal Society today published a paper presented by our colleagues as follows:

Federating distributed clinical data for the prediction of adverse hypotensive events

Abstract

The ability to predict adverse hypotensive events, where a patient’s arterial blood pressure drops to abnormally low (and dangerous) levels, would be of major benefit to the fields of primary and secondary health care, and especially to the traumatic brain injury domain. A wealth of data exist in health care systems providing information on the major health indicators of patients in hospitals (blood pressure, temperature, heart rate, etc.). It is believed that if enough of these data could be drawn together and analysed in a systematic way, then a system could be built that will trigger an alarm predicting the onset of a hypotensive event over a useful time scale, e.g. half an hour in advance. In such circumstances, avoidance measures can be taken to prevent such events arising. This is the basis for the Avert-IT project (http://www.avert-it.org), a collaborative EU-funded project involving the construction of a hypotension alarm system exploiting Bayesian neural networks using techniques of data federation to bring together the relevant information for study and system development.

The full text and of names of contributors can be accessed Here

All the clinicians involved in our project are specialists in neurosurgery. Hypotensive events are a key issue for them, because of the damage caused to the brain.

But a major question for us has been will our research result in a technology which could apply in general intensive care. Specialist neurosurgery units account for only a small proportion of the total ICU beds. We’ll find it much easier to justify a commercial operation if all ICU beds are potential installations.

Great News – Physionet based at MIT and funded by the National Institutes of Health’s NIBIB and NIGMS, recently announced its “challenge” for 2009 – Predicting Acute Hypotensive Episodes.

As a basis for the challenge Physionet provides a data set collected during intensive care of cardiology patients. The challenge itself isn’t appropriate for our research – we’re targeting a different definition of episode -but the instructions for the challenge provides an interesting perspective. Here’s and extract.

“Among the most critical events that occur in intensive care units (ICUs), acute hypotensive episodes require effective, prompt intervention. Left untreated, such episodes may result in irreversible organ damage and death. Timely and appropriate interventions can reduce these risks. Determining what intervention is appropriate in any given case depends on diagnosing the cause of the episode, which might be sepsis, myocardial infarction, cardiac arrhythmia, pulmonary embolism, hemorrhage, dehydration, anaphylaxis, effects of medication, or any of a wide variety of other causes of hypovolemia, insufficient cardiac output, or vasodilatory shock. Often the best choice may be a suboptimal but relatively safe intervention, simply to buy enough time to select a more effective treatment without exposing the patient to the additional risks of delaying treatment.

Of the 2320 patients whose monitored waveforms and accompanying clinical data were included in the MIMIC II Database as of December 2008, arterial blood pressure was recorded in 1237 (53%); among these 1237 patients, 511 (41%) experienced recorded episodes of acute hypotension (as defined below) during their ICU stays. The mortality rate for these 511 patients is more than twice that of the MIMIC II population as a whole. To the extent that one might forecast acute hypotensive episodes in the ICU, there is a possibility of improving care and survival of patients at risk of these events. “