Radiotherapy is a widely used cancer treatment, however some patients suffer side effects. In breast cancer, side effects can include breast atrophy, arm lymphedema, and heart damage. Some factors that increase risk for side effects are known, but current approaches do not use all available complex imaging and genomics data. The time is now ripe to leverage the huge potential of AI towards prediction of side effects. This project will use rich datasets from three patient cohorts to design and implement an AI tool that predicts the risk of side effects, including arm lymphedema in breast cancer patients and provides an easily understood explanation to support shared decision-making between the patient and physician. The PRE-ACT consortium combines the expertise in computing (MDW, AUEB-RC), AI (HES-SO, CENTAI), radiation oncology (MAASTRO, UNICANCER), medical physics (THERA), genetics (ULEIC), psychology (CNR) and health economics (UM) that is necessary to tackle this problem. The project will integrate data from the three cohorts and build AI predictive models with built-in explainability for each of the key side effects of breast cancer radiotherapy. These AI models will be incorporated into an existing commercial radiotherapy software platform to create a world-leading product. The extended platform will be validated in a clinical trial to support treatment decisions regarding the irradiation of lymph nodes. The trial will adopt an innovative design in which the patients and medical team in the test arm will receive the risk prediction, but those in the control arm will not. A communication package built with a co-design methodology will ensure that AI outcomes are tailored to stakeholders effectively. The trial will evaluate whether using the AI platform changed the arm lymphedema rate and impacted treatment decisions and quality-of-life. Generalizability of the AI models for other types of cancer will be sought through transfer learning techniques.

Difficult-to-treat rheumatoid arthritis (D2T RA) is an area of huge unmet medical need with major socio-economic consequences for patients and society. Contributing factors have been identified including co-morbidities, drug-related, biological and behavioral factors. However, identifying these patients with specific underlying and overlapping problems, or patients at risk, is a big challenge in practice. Currently, treatment decisions are random and not sufficiently patient tailored nor data-driven. Therefore, the STRATA-FIT consortium sets out to develop and validate computational models to identify and stratify D2T RA patients into clinically relevant phenotypes using real world clinical data. We will also measure biomarkers of inflammation to further characterise these phenotypes. Subsequently, we will execute a pilot study with a clinical decision aid based on our models to assess the effectiveness of personalised treatment strategies. In parallel we will develop a computational model to identify early RA patients at risk of developing D2T RA. By doing so, not only will we provide better treatment for patients with D2T RA, but also work towards its prevention in early RA patients. STRATA-FIT will establish a unique European Learning Healthcare System, using a privacy-proof, state-of-the-art federated learning infrastructure in which patients with, or at risk of D2T RA are identified, stratified and treated in a personalised manner. STRATA-FIT builds on previous work by consortium partners, who initiated and lead the European Task Force on developing points to consider for managing D2T RA. It brings together clinical experts, patient research partners and clinical-, biological-, data- and computer-scientists to tackle this major clinical challenge. When successful, STRATA-FIT will lead to more (cost-) effective D2T RA care and will greatly improve the quality of life of D2T RA patients while lowering the burden of D2T RA on Europe’s health care systems and society.