AVERT-IT · Advanced Arterial Hypotension Adverse Event prediction through a Novel Bayesian Neural Network

Hypotension (sub-normal blood pressure) adverse events (AE's) occur commonly in patients managed in intensive care and high dependency units. Health care technology which could reduce the burden of these events by as little as ten percent would equate to at least five billion Euros p.a. saved by European healthcare organisations for use in other treatment regimens<br/>The AVERT-IT project will create a novel bed-side monitoring and alerting system dedicated to the prediction of variations in the condition of the patient that are likely to lead to hypotension without appropriate clinical intervention. A world-class consortium consisting of an SME software developer (C3 Global), renown clinical experts (www.brainit.org), Philips medical and Grid experts in secure access to distributed medical datasets will develop and validate the innovative technology using access to a unique and large repository of detailed multi-media patient data drawn from 22 clinical centres in 11 countries created through two recent EC funded projects.<br/>A systematic work programme will select appropriate clinical and monitoring inputs (via undertaking data mining and robust statistical analysis of this unique database and other electronic health record systems) to train a novel Bayesian Artificial Neural Network (BANN) to predict subsequent hypotension AE's. The BANN will form the engine of a novel IT-based decision support system (HypoPredict") which will be prospectively validated in 6 clinical intensive care centres using a phase II clinical trial design.<br/>The AVERT-IT project will produce a step-change in arterial hypotension prediction within the critical, intensive and high-dependency care environment with a major impact upon health care costs in terms of reduced corrective care, obviated as a consequence of the improved prediction of, and earlier intervention in, hypotension adverse events, and in improved patient outcome with associated reduction in carer-burden."