Professor Mark Little

What is the problem PARADISE wants to address? In Europe, 30 million people suffer from an autoimmune disease; it is the third largest cause of morbidity and mortality, after cancer and heart disease, in industrialised countries. At the individual level, the impact of suffering can be immense, at the societal level, a significant health and economic burden. Autoimmune disease affects 10% of adults, most of whom are women, and two of the top five medications with the highest cost globally are used to keep these recurring conditions in remission. These medications suppress the immune system, leaving the patient exposed to increased infection and cancer risk. The general requirement for such treatments, and their side effects, has been raised as a key target for research by the PARADISE consortium patient groups. What is the aim of PARADISE? PARADISE delivers a practical response to this challenge. We aim to develop a personalised prediction tool that accurately defines the patient"s risk of disease recurrence so that medication doses can be tailored and, in some cases, stopped safely. We use systemic vasculitis as a typical autoimmune disease, bringing together clinical, biomarker and smartphone derived wellbeing data to inform predictive algorithms underpinning a physician tool. What exactly will PARADISE do? PARADISE will combine and analyse multi-source heterogeneous data, create a prediction model, and implement it as a physician-facing tool to inform ANCA-associated vasculitis care, ready for a future clinical trial. Such artificial intelligence (AI) applications are coming under intense EU scrutiny, so we will co-develop an "AI transparency notice", which will make explicit and explainable the PARADISE tool clinical outputs.

FAIRVASC is a research project of the European Vasculitis Society (EUVAS) and RITA European Reference Network, bringing together leading scientists, clinicians and patient organisations. The FAIRVASC consortium is made up of 10 partners who represent all of these areas of patient care, also substantial support from VIFOR PHARMA should be acknowledged. There are many important gaps in our knowledge about why and how vasculitis occurs, why some people seem to be more susceptible than others, how the disease process acts inside the body and whether different kinds of vasculitis should be treated in different ways. As the condition is rare, there are relatively few patients in any one European country. We, therefore, need to analyse data at a European level so that we have enough patient data to discover these important missing facts. FAIRVASC will use semantic-web technologies to link vasculitis registries across Europe into a `single European dataset", and thus open the door to new research into these challenging diseases. The programme will ensure that all included registries are FAIR and that the infrastructure developed is aligned with developments in the European Joint Programme. In FAIRVASC, this large new European resource will be analysed to identify features (clinical and physical characteristics, etc.) that predict how a patient"s illness will develop, and what their major health risks are. These markers can, in the future, be developed into new predictive tools that help doctors to choose the best treatment options for the individual patient. Research into the rare condition " Vasculitis (an acquired, immune mediated inflammatory disease involving blood vessels of many tissues and organs), needs sufficiently large quantities of data to enable well-informed conclusions about treatments and possible cures. It is thus essential to combine the databases of patient registries of several countries to build a dataset of sufficient size to enable meaningful research.

We propose a new way of managing chronic diseases that brings the fields of medicine and data science together. We hypothesise that the interaction between individuals with the relapsing and remitting autoimmune kidney disease ANCA vasculitis, and their environment, can be detected and defined by observing the whole system in action and integrating a wide array of data sources. Collaboration with IBM will allow us to take advantage of recent advances in machine learning technology that allows iterative refinement of algorithms to generate a technology readiness level 3 proof of concept physician tool, to present analysis results in a clinically meaningful way. The ultimate goal of this approach is to define the signature of vasculitis relapse and use this to aid in planning and delivery of optimum immunosuppressive therapy at the level of the patient. To achieve this, we will use advanced data science methodologies and Bayesian statistical techniques to develop a data architecture that curates and combines from four sources: Fixed patient-level factors (HLA-DP phenotype, granular clinical dataset obtained at diagnosis), External medical influences (maintenance immunosuppression, antibiotic prescriptions, Hospital Inpatient Enquiry records), External environmental influences, linked to patient location through time (meteorological data streams, community pathogen patterns: readily available as online data streams) and Direct patient-derived data sources (location, patient-reported quality of life and accelerometer defined activity). We expect a 50% rate of relapse after 5 years in a cohort of patients derived from the Rare Kidney Disease registry; we shall describe for the first time the relapse prodrome and define in great detail the environmental influences linking to this event.

HEalth data LInkage for ClinicAL benefit is a training network comprising 17 academic and 9 non-academic/industry partners for early stage researchers in the field of Healthcare Data Linkage in the GDPR era. European researchers have made leading contributions to the large genomic, transcriptomic and clinical datasets from patients with chronic diseases. Advances in information science provide unprecedented opportunities for using these datasets to elucidate the complex biology of these disorders, its influence by environmental triggers, and to personalise their management. Exploitation of these opportunities is limited by a shortage of researchers with the required informatics skills and knowledge of requisite data protection principles. HELICAL addresses this unmet need by developing a trans-sectoral and interdisciplinary programme with training in analysis of large datasets, using autoimmune vasculitis as a paradigm, as comprehensive biological and clinical datasets are already available. The programme will be delivered through a partnership of Academic and Industry researchers with expertise in basic biomedical research, epidemiology, statistics, machine learning, health data governance and ethics. HELICAL exploits recent advances in data science to link research datasets with longitudinal healthcare records, based on the robust ethical foundation required for linkage studies using near-patient data, to address key experimental questions.

This project is focused on development of a novel biomarker test in the diagnosis and monitoring of crescentic glomerulonephritis (CGN), a severe form of inflammatory kidney injury. This test relies upon identification of a single protein in the urine: soluble CD163. This is shed from activated macrophages, the predominant cell in glomerular crescents, which are in direct communication with the urinary space. Extensive experimental work in our laboratory has brought this biomarker to technology readiness level 3. This project will bring it to level 7, laying the foundation for a definitive trial.