Project description
Personalised approaches for better healthcare
Aiming to increase overall patient safety, the EU-funded SafePolyMed research project seeks to develop innovative tools to help physicians and pharmacists better define, assess and manage drug-drug-gene interactions. Machine learning on large real-world data sets will identify patients at risk, model-based precision dosing tools will optimise treatments for patients, and patient-reported outcome measures will evaluate treatment success. Medication management centres will serve as a hub for patients and healthcare providers to explore underlying causes of poor treatment outcomes and define more personalised treatment plans. By educating citizens and empowering them to participate in self-documenting their therapy, the project seeks to improve the communication between patients and physicians and provide equal access to innovative, sustainable, high-quality healthcare across Europe.
Objective
Polypharmacy, multimorbidity and genetic heterogeneity can affect drug efficacy, raise the risk for adverse drug reactions (ADRs) and increase healthcare costs. ADRs are among the leading causes of death in developed countries and a major cause of hospitalization. Drug-drug interactions (DDIs) and drug-gene interactions (DGIs) are highly interconnected and require a holistic approach to improve safety of our citizens. However, investigations on real-life drug-drug-gene interactions (DDGIs) in clinical trials are unfeasible due to combinatorial explosion, high costs and ethical concerns. Hence, significant knowledge gaps exist. Furthermore, the lack of participation in managing their conditions might be excessively demanding for polymedicated and multimorbid citizens. SafePolyMed will develop a novel and innovative framework to define, assess and manage DDGIs for physicians and individual patients resulting in education and empowerment of citizens as well as in reduced healthcare costs by improving patient safety. The main objectives of SafePolyMed are (1) development of a novel, evidence-based risk scoring system using machine learning on large real-world datasets to identify patients at risk; (2) identification and validation of patient reported outcome measures for multifactorial patient safety in collaboration with European patient organizations;
(3) development of an electronic tool to empower patients by allowing them to properly manage their therapies, check for and educate about DD(G)Is and collect their patient reported outcomes; (4) mathematical modelling of clinically relevant compounds to derive individualized dose adaptations for safe and effective dose regimens in case of DDGIs, accessible via a web-based decision support system with tailored information for either citizens or physicians and (5) validation of the developed safety tools in a ?proof-of-principle? study including representative patient cohorts from different European clinical sites.
Fields of science
- medical and health sciencesbasic medicinepharmacology and pharmacydrug safety
- medical and health scienceshealth sciencespersonalized medicine
- medical and health sciencesbasic medicinepharmacology and pharmacyadverse drug reactions
- natural sciencescomputer and information sciencesartificial intelligencemachine learning
- natural sciencesmathematicsapplied mathematicsmathematical model
Programme(s)
- HORIZON.2.1 - Health Main Programme
- HORIZON.2.1.6 - Health Care Systems
Funding Scheme
HORIZON-RIA - HORIZON Research and Innovation ActionsCoordinator
66123 Saarbrucken
Germany