The TBIcare project successfully ended in July 2014, delivering a software solution to improve the diagnosis of Traumatic Brain Injuries (TBI) and guide the planning of treatments.
Traumatic brain injury (TBI) occurs when a sudden trauma causes damage to the brain – it is a major health problem and the most common cause of permanent disability in people under the age of 40 years. The yearly cost from TBI in Europe exceeds 100 billion Euros. Yet, treating TBI patients is particularly difficult due to the complex nature of the brain, and the individual nature of each injury.
The TBIcare consortium set out to provide an objective and evidence-based solution for management of TBI by improving diagnostics and treatment decisions for an individual patient. The consortium had the objectives of developing: 1) a methodology for finding efficient combinations of multi-modal biomarkers used in statistical models to objectively diagnose and assess an individual TBI patient, and 2) a model for objectively predicting outcome of the planned treatment of an individual TBI patient.
The TBIcare team worked towards these objectives by realisation of: a software solution to be used in daily practice to diagnose TBI and plan treatments; new approaches for extracting information from multi-source and multi-scale physiological databases for management of an extremely heterogeneous disease; and innovative data quantification methods for the clinical TBI environment.
The project work started with retrospective data for analysis, and in parallel collected a large prospective multi-variate database of TBI cases (201 cases in Turku and 193 in Cambridge) containing, amongst others, clinical variables, vital signs, imaging data (CT, MRI, and, additionally, PET), proteomics, metabolomics, and EEG. Moreover, new data quantification techniques were developed and validated for extracting TBI-related biomarkers from imaging, electrode-impedance spectroscopy (EIS), and non-invasive intra-cranial pressure measurements (ICP). Lastly, the consortium explored the merits of system dynamics modelling in this new application field, in particular by modelling for evaluating the socio-economic impacts of TBI treatment, rehabilitation, and prevention that encompass the treatment chain and patient flows from incidence to the discharging from rehabilitation or hospital.
The data analysis and modelling work focussed on major clinical questions that were identified in the first phase of the project: prediction of outcome (e.g., favourable vs. non-favourable) at 6 months for moderate/severe cases, and at 3 months for mild cases; and prediction of the need for prolonged ICP monitoring. In continuous co-operation between clinicians, ICT professionals, usability experts, and data-analysts, a decision support software tool was developed that allows a user (a healthcare professional) to address and investigate the above questions for an individual patient. This was done by using an approach in which the current patient data were numerically and visually compared against other patients’ data as present in large multi-variate databases. The models showed similar numerical performance to state-of-the-art classifiers, but with advantages of being easily interpretable, robust against missing data, and extendible for inclusion of new data modalities as they become available. The web-based software tool was validated by clinicians from Turku and Cambridge in a clinical setting
“The
outcomes of TBIcare potentially impact healthcare associated with TBI by way of
increasing the accuracy and 
objectivity of diagnosis of TBI ensuing in an
immediate effect on effectivity and safety” says Dr Mark van Gils, TBIcare
coordinator. “Specifically, it will help less-experienced clinicians in the
field get experience with the intricacies of e.g. TBI outcome prediction using
educational functionality in the software solution. The future of health care
is to have an integrated approach to “diagnose -> treat -> follow-up
(monitor effect of therapy)”. This requires a multidisciplinary approach where
competencies from biology, biophysics, medicine, image processing, chemistry
etc. are needed. TBIcare helped reinforce this type of integrated approach to
disease management, and the path is followed further in continuing research
projects.”
Additional information:
The TBIcare project was co-funded by the European Commission in the 7th framework program (FP7) under the theme Virtual Physiological Human (GA 270259). It ran from February 2011 to July 2014, and the consortium consisted of the following partners: VTT Technical Research Centre of Finland (co-ordinator), GE Healthcare Ltd, Turku University Central Hospital, University of Cambridge, Imperial College London, Complexio SARL, Kaunas University of Technology, and GE Healthcare Finland Oy.
Contacts: Mark van Gils - Co-ordinator
VTT Technical Research Centre of Finland
+358 20 722 3342
Website: www.vph-tbicare.eu
