Patients at risk or diagnosed with arthritis are constantly assessed by innovative imaging techniques to document the onset or progression of their disease. However, despite their impressive abundance and resolution, these images lack the analysis and interpretation tools necessary to deliver unbiased and precise diagnosis, monitoring and prognosis to the patients. Additionally, some key advanced imaging methodologies such as ultrasound are hardly accessible to most of patients, urging improvements of more accessible imaging methods. The AutoPiX project is an ambitious international multi-stakeholder effort led jointly and synergistically by academic and industry partners to achieve breakthroughs in both the applicability and harnessing of imaging technologies for the benefit of patients by creating new powerful analysis and decision tools. We will first generate tools to transform unstructured images into quantitative biomarkers using artificial intelligence (AI) and machine learning (ML) models, and validate them clinically for their diagnosis, monitoring and prognosis power. This will considerably increase the utility of imaging biomarkers for arthritis and bring them to the same level as laboratory biomarkers. In parallel we will develop accessible imaging strategies such as remote monitoring and robotic-powered point-of-care ultrasound exams for patients to mitigate the often-observed shortage of qualified personnel in real world settings. To achieve this, we will improve the precision and interpretability of these methods and further validate them with clinical, molecular and histological analyses. Our consortium is built on multi-disciplinarity and the constant synergistic interaction of all the actors of arthritis care: rheumatologists, radiologists, patients, researchers, regulators, industries and small- and medium sized enterprises (SMEs). On the long term, AutoPiX will create new clinically-validated methods to achieve a/ more precise, accessible and effective diagnosis, b/ shortened and better-tailored treatment paths and c/ improved treatment response assessments and outcome prediction for patients with arthritis.

Globally 1.Globally 1.71 billion people have musculoskeletal symptoms, the leading contributor to disability. Early disease stratification is important to ensure appropriate care (most suited healthcare provider and best treatment choice). Currently the patient journey to diagnosis and effective treatment is long and inefficient, resulting in persistent disease burden and economical loss. This is due to insufficiently understood relations disease causes and similarities in symptoms between diseases, insufficiently distinguishing tests, trial and error approach in initial treatment. SPIDeRR aims to disentangle the real-life complexity of early diagnosis of rheumatic diseases by considering the complete web of factors influencing patients’ symptoms. SPIDeRR’s approach will go well beyond the state-of-the-art in the following ways: - By identifying different disease groups, requiring different therapies, amongst patients with similar symptoms in contrast to the traditional approach aiming to only capture one disease early. - By integrating all relevant data dimensions from every healthcare level (primary and secondary care and patients seeking advice online). - By translating and applying machine learning techniques from the “omics” field to clinical patient data, which will result in new pipelines for translational data science SPIDERR will deliver three clinical models -a symptom checker for patients -a decision support tool for (primary) care providers providing guiding additional examination and referral decisions -a patient-patient similarity network to optimise diagnostic groups in rheumatology and support treatment decision To achieve this we additionally deliver solutions for data integration and shared analyses though GDPR compliant digital research environment and federated learning pipelines. Finally we will test the acceptability of the models through stakeholders studies and provide an implementation scene tailored to current healthcare in Europe.

The SQUEEZE consortium comprehensively addressed how biomarkers can be used to optimize disease modifying antirheumatic drugs (DMARDs) for rheumatoid arthritis (RA). RA is a chronic immune-mediated disease with enormous health-related quality of life and socioeconomic impact. A broad choice of DMARDs with different targets is up to date available in clinical care, however without sufficient markers indicating the best choice for a particular patient, treatment strategies can be ineffective, cumbersome and expensive. The team of leading academic centres with a first-class record in translational and clinical research, together with patients and small and medium sized enterprises (SMEs) has set out to deliver a collaborative programme to advance the clinical application of biomarkers to improve benefit, safety, and value of approved DMARDs. SQUEEZE utilizes models from data science, clinical trials, translational science, and behavioural science to engage in a complementary, synergistic, and non-overlapping manner addressing the use of biomarkers to improve the ability to select the DMARD with the highest likelihood of fitting the immunophenotypic and clinical profile of the patient, to optimise dose and route of existing DMARDs; and to inform an innovative model of care focusing on patient´s preferences and needs to increase adherence to prescribed drugs. Through nine dedicated work packages SQUEEZE integrates to validate clinical, laboratory, molecular, digital and behavioural biomarkers to enable the recognition of patients with high likelihood of response to treatment and the selection of the drug with highest chance of benefit for an individual patient; and as such improve efficacy and safety of existing therapies (by squeezing the most out of existing drugs) in synergy with other EU-wide activities.

Rheumatoid Arthritis (RA) is the most common, chronic, inflammatory joint disease with a prevalence of about 1% of the adult population (22M patients worldwide and 7M in EU) and estimated to be responsible for 10,000 disability adjusted life years (DALY's) costing EU society €55B annually. Despite aggressive therapy, about a third of patients have to give up work within 5 years of disease onset mainly due to lack of response to multiple disease modifying anti-rheumatic drugs (DMARDs), multi-drug resistance (MDR). Thus, the main objective of this proposal is to define the clinical and molecular phenotypes leading to MDR in RA patients to prevent when possible or, when not possible, optimise the management of these patients. MDR-RA is highly relevant to the program, as these patients are often disabled, unable to work and paying a high personal and societal burden. Moreover, MDR-RA is under-researched and the underlying pathobiological mechanisms for resistance remain unknown, while as we have no predictors of therapeutic response to any of currently available drugs, inevitably treatment is based on trial-and-error. MDR-RA has the ambition of transforming care for these patients and deliver significant advances beyond the state-of-the-art methodologies, as for the first time, molecular pathology will be integrated into clinical, psychosocial, pain perception and imaging profiling in existing clinical cohorts to develop truly holistic predictive models for future clinical use (iCare-RA). The transformative potential of iCare-RA will be tested in a prospective randomised trial in comparison with routine standard of care, while its future implementation potential will be assessed through an early economic modelling. Finally, a strong management and dissemination strategy will facilitate further advancing science in the field, beyond the duration of the project, and future adoption by patients, specialist professional bodies, policy makers and regulatory authorities.