Longer life expectancy and changes in our lifestyles are leading to an increase in the prevalence of complex pathologies such as cardiovascular diseases, cancers, metabolic diseases (diabetes), neurological diseases (Parkinson’s, Alzheimer’s, mood disorders, addictions) and infectious diseases. The rising costs of treating these diseases, the frequent lack of response to treatment, and the appearance of undesirable side-effects are becoming unsustainable for our economic and healthcare system, and could jeopardise the fundamental right of access to high-quality medical care. In this context, the major challenge facing medicine is to develop a personalised approach to pathologies, based on a better understanding of the unique characteristics of each patient, in order to improve their care.
Our Ambition:
The MedReSyst initiative aims to develop the tools needed to establish network and systems medicine, enabling patients to be approached as a whole and improving their care from screening to treatment.
The key players in the initiative:
MedReSyst brings together the 5 French-speaking universities (UCLouvain, ULB, ULiège, UMons, UNamur), the Multitel and Cetic research centres and a number of key hospitals.
The key players in the initiative:
MedReSyst brings together the 5 French-speaking universities (UCLouvain, ULB, ULiège, UMons, UNamur), the Multitel and Cetic research centres and a number of key hospitals.
Ceci est une idée pour faire descendre l’image dans le bloc
Our main area of work:
The MedReSyst initiative is intended to develop network and systems medicine based on a holistic approach (i.e. taking into account the patient as a whole), drawing on biological data (i.e. DNA, RNA, proteins and metabolites), exposomic data (environmental factors to which the patient has been exposed) and clinical data. It draws on biological data (i.e. DNA, RNA, proteins and metabolites), exposomic data (environmental factors to which the patient has been exposed) and detailed clinical data, as well as on artificial intelligence (AI) to establish an individual map of the risk factors and protective elements of a person’s health, and to predict the risk of developing a disease and the response to treatments in a personalised manner.
Models developed using AI are not widely used in clinical practice today, as they are often rigid, black-box decision-making systems. By deploying continuous learning models, fed by data and expertise from multidisciplinary coalitions of experts within hospitals (learning coalitions), the experts interact continuously with the AI model. The data and annotations provided are regularly revised by peers, based on the progress of patients and cases encountered. This innovative approach will help to put in place processes where digital and healthcare staff reinforce each other in a virtuous circle, as well as building trust in AI in the medical sector. This initiative is part of the “Innovations for better health” strategic innovation area (diagnostic and medical technologies, e-health and the hospital of the future).