BD2Decide aims to develop a more precise prognostic prediction than the ones currently used in Cancers of Head and Neck Region (HNC), which targets to implement the first-line treatment in order to maximise the therapeutic results and minimise the impacts of HNC therapy. Currently, the adopted treatment decision method is based on prognostic systems, which consider only a few risk factors and result in late diagnosis of relevant cases in in advanced Stage. A more precise validated prognostic prediction than the current TNM system, would allow to implement the firstline treatment that maximizes the therapeutic result and minimizes the impacts of therapy in term of functional impairment and toxicity and to involve the patient in the decision through individualized co-decision aids.
BD2Decide introduces a Decision Support System (DSS), which provides clinicians with the "means" and all the necessary information to tailor treatment and care delivery pathway to each and any HNC patient during their usual practice, in contrast to current “one-size-fits-all approach”. This project, co-funded by the EU under the H2020-PHC-2015 program, realizes and validates an Integrated Decision Support System that links population-specific epidemiology and behavioral data, patient-specific genomic, pathology, clinical and imaging data with big data techniques, multi-scale prognostic models. BD2Decide will improve the clinical decision process, uncover new patient-specific patterns that can improve care, and create a virtuous circle of learning. A multi-centric clinical study with more than 1.000 patients will be used to validate the system.
BD2Decide will develop a virtual DSS environment that combines existing data and advances existing personalized prognostic models and visualization and data representation technologies (Virtual Patient paradigm) for personalised prognosis and treatment decision-making for HNC. BD2Decide is thought to help clinicians decide in these challenging situations as it produces not only information from evidence medicine but also prognostic information derived by the embedded models, but especially supporting data and scored prognostic factors, specific for each individual and for the reference populations. Thus, clinicians can better apply guidelines, because they know more about the disease in that specific patient and visualize in a chart how the patient is positioned with respect to the reference population. Additionally, through data analytics techniques, the system proposes the evidence-based data of similar cases, that can be inspected by selecting them in the chart.