Integration of real-world data into clinical data for better personalised treatment of breast-cancer patients

Abstract

REBECCA is 4-year project funded under the European Union’s Horizon 2020 research and innovation programme. The project aims to tap into the potential of Real World Data to provide personalised treatment and care to breast cancer patients or cancer survivors. The ultimate goals of REBECCA are to advance clinical research by moving beyond randomised controlled trials and to improve post-treatment in breast cancer to increase patients’ quality of life. 
 REBECCA stands for REsearch on BrEast Cancer induced chronic conditions supported by Causal Analysis of multi-source data. The project is built around two axes: 1) clinical research by analysing data to better understand how treatment affects quality of life, and 2) patient management to improve interventions and care choices at the individual level. 
 Currently, randomised controlled trials (RCT) are the gold standard in clinical research. However, there are several limitations of using RCTs for complex chronic conditions such as breast cancer as patients may suffer from different conditions that are influenced by various variables. Moreover, RCTs usually only include a small population sample and researchers do not have control over the independent variables. REBECCA aims to move beyond RCTs by using real-world, observational data. 
 Real-World Data in REBECCA is collected through sensor and log data retrieved via electronic health records and innovative technical tools developed by the project consortium such as mobile apps and wearable devices (e.g. smartwatches or fitness bands). Patients’ real-life behaviour can thus be monitored, including their physical activity, eating habits, sleep, local environment and information related to their online interaction. Once collected, the real-world data is then processed to extract indicators, which are consequently used to infer causal relationships with PROMS and complex chronic conditions. The causal modelling then indicates causalities and sheds light on confounders.
 Causal modelling will enable health managers and practitioners to measure the safety and effectiveness of breast cancer treatments and measure their impact on the quality of life after breast cancer treatment, to improve clinical outcomes and PROMs, and to help develop personalised recommendations and treatments based on the data collected by each patient, thus increasing the value for patients. 
 The proposed oral poster session aims to demonstrate through evidence how innovative digital tools collecting patients’ data from informal life settings in a non-invasive manner can be integrated to clinical data gathered in formal care settings and how these different sets of data together can support the provision of personalised treatment and care for breast cancer patients. This integrated care method also highlights the benefits of detailed patient monitoring and individualised patient lifestyle consultations in patient care workflows. "