Psoriatic Arthritis (PsA) is a chronic, inflammatory disease, affecting the peripheral and axial skeleton, with a severe impact on patients’ quality of life. It is estimated that 1-2% of the general population has PsA, i.e., 5 to 10 million people in EU are affected. PsA is associated with psoriasis (PsO) and up to 30% of people living with PsO, i.e., at least 100 million people worldwide (WHO), are expected to develop PsA. The peak onset of PsA usually occurs between the age of 30 and 50 years, with an equal sex distribution. Moreover, according to the Arthritis Foundation, the economic burden of psoriatic diseases like PsA is up to €124 billion a year, with the cost per patient increasing with severity. PsA, as a complex inflammatory disease, has multiple interrelated pathologies, including synovitis, enthesitis, axial disease, and dactylitis. Inflammation results in pain, tenderness, and swelling, which can be localized around a joint or more diffuse and along an entire digit (dactylitis). The symptoms do not only occur in peripheral joints of the hands and feet (pain and deformations), spine and skin, but can also affect other parts of the body, such as the eyes (uveitis), nails, soft tissues around the joint and bowel.
iPROLEPSIS project aims to explain health-to-PsA transition and advance PsA diagnosis and care by: a) identifying the key drivers in a multiscale/multifactorial PsA model explaining the causalities between inflammation and organs (systems-level), using xAI-based data mining on multi-source human studies data (medical, clinical, well-being, life-style, environmental, occupational) initialized by the knowledge from the state-of-the-art, b) extending the multiscale/multifactorial PsA model to novel PsA detection models, along with personalized prognostic models for the transition from PsO to PsA, by incorporating a system of omics-based biomarkers, xAI-based features from non-invasive skin microvascular/joint imaging (Optoacoustics), combined with novel digital phenotyping to inform the xAI models by tracking key PsA risk/progression markers in daily living, via unobtrusive sensing with smart sensors (smartphone, smartwatch), c) designing, implementing, and validating novel personalized interventions towards the remission of the PsA symptoms and treatment optimization, and ultimately d) offering a validated, privacy-aware, xAI-driven toolkit, supporting healthcare professionals (HCPs) in disease screening, monitoring and treatment optimization, via quantitative, explainable evidence, and empowering individuals with/at risk of PsA with tailored insights for informed health management.
Ainigma is responsible for integrating heterogeneous multimodal data to create dynamic, and personalised explainable-driven models of the health-to-PsA inflammation transition. With the aid of those models, we will enable prediction of risk and early diagnosis of PsA in people at risk, with emphasis on PsO patients, as well as prognosis of disease progression targeting the prevention of PsA inflammation exacerbation.
Technologies we use:
