Interstitial lung disease (ILD) is one of the primary causes of death in systemic sclerosis (SSc). The majority of patients identify dyspnea as a major impairment of quality of life.
Substantial insights into the underlying pathophysiology has led to the development of specific anti-inflammatory and anti-fibrotic therapeutic approaches. Thus, personalized medicine seems within reach for the individual patient. However, this is opposed by the molecular heterogeneity of the disease. Previous approaches attempting to predict individual outcome or therapeutic response, based on clinical, functional or laboratory data, have failed.
In our interdisciplinary project we will use different mouse models of SSc-ILD to generate a computer-based algorithm in a machine learning approach based on multi-omics data (transcriptomics, proteomics, radiomics, functional data) in order to develop a prediction model. Based on a combination of variables, we envision being able to predict prognosis, drug response and monitoring.
In a second step, we will test the performance of the derived prediction algorithm in patients with SSc-ILD.