Can serum biomarkers predict the outcome of systemic therapy for atopic dermatitis?

Abstract

SUMMARYBackgroundAtopic dermatitis (AD or eczema) is a most common chronic skin disease. Designing personalised treatment strategies for AD based on patient stratification, rather than the “one-size-fits-all” treatments, is of high clinical relevance. It has been hypothesised that the measurement of biomarkers could help predict therapeutic response for individual patients.ObjectiveWe aim to assess whether biomarkers can predict the outcome of systemic therapy.MethodsWe developed a statistical machine learning predictive model using the data of an already published longitudinal study of 42 patients who received systemic therapy. The data contained 26 serum cytokines measured before the therapy. The model described the dynamics of the latent disease severity and measurement errors to predict AD severity scores (EASI, (o)SCORAD and POEM) two-weeks ahead. We conducted feature selection to identify the most important biomarkers for predicting the AD severity scores.ResultsWe validated our model and confirmed that it outperformed standard time-series forecasting models. Adding biomarkers did not improve predictive performance. Our estimates of the minimum detectable change for the AD severity scores were larger than already published estimates of the minimal clinically important difference.ConclusionsBiomarkers had a negligible and non-significant effect for predicting the future AD severity scores and the outcome of the systemic therapy. Instead, a historical record of severity scores provides rich and insightful dynamical information required for prediction of therapeutic responses.