Approach and Objectives

Early diagnosis

Promote early diagnosis of PsA in patients with Psoriasis. Develop a tool to reliably diagnose patients early with features of PsA. This tool will likely include a variety of objectively measured blood markers (so-called ‘biomarkers’) and patient reported outcomes.

Specific objectives:

• Identify indicators from patient characteristics such as age, sex or lifestyle (smoking, weight gain etc) which help identify PsA
• Search for novel indicators present in the blood or other patient samples which differentiate PsA from other forms of arthritis
• Develop more advanced imaging techniques (e.g. MRI) for detection of early signs of PsA
• Combine these features using advanced statistical approaches with the aim of developing an algorithm for PsA diagnosis.

Prediction of PsA

Develop a test to identify psoriasis patients at risk of progression to PsA. Discovering biomarkers that can identify psoriasis patients at risk of developing PsA. This will enable earlier interventions and possibly prevent the development of PsA.

Specific Objectives:

• Set up a large European study, HPOS, to collect biological and patient-relevant data.
• Results from this study will potentially provide valuable data for all four Work Packages.
• WP1 and 2 will both use methods within the field of Artificial Intelligence and machine learning.

Disease progression

Define the factors that predict disease progression in PsA patients, including early prediction of bone and joint damage. Study the course of joint and bone damage and functional decline over time.

Specific Objectives:

• Identify clinical, imaging and biochemical predictors of disease progression.
• Build predictive models to identify patients at risk of PsA progression.
• Develop treatment strategies that can be customised for each patient to prevent or minimise disease progression.

Personal treatment strategies

Develop a methodology that allows us to select the drug that is most likely to best work for each individual patient. Utilize extensive samples from many European cohorts of PsA patients, including samples from relevant biobanks.

Specific Objectives:

• Test these samples at cellular and molecular levels, including relevant advanced DNA and RNA tests.
• Analyse large volumes of data using artificial intelligence techniques, including machine learning, searching for which patients with which sets of characteristics respond best to particular classes of drug.