AbstractBackgroundBiological agents used for the therapy of psoriasis lose efficacy over time, which leads to discontinuation of the drug. Optimization of long-term biologic treatment is an area of medical need but there are currently no prediction tools for biologic drug discontinuation.ObjectiveTo compare the accuracy of the risk factor-based frequentist statistical model to machine learning to predict the 5-year probability of biologic drug discontinuation.MethodsThe national Danish psoriasis biologic therapy registry, Dermbio, comprising 6,172 treatment series with anti-TNF (Etanercept, Infliximab, Adalimumab), Ustekinumab, Guselkumab and anti-IL17 (Secukinumab and Ixekizumab) in 3,388 unique patients was used as data source. Hazard ratios (HR) were computed for all available predictive factors using Cox regression analysis. Different machine learning (ML) models for the prediction of 5-year risk of drug discontinuation were trained using the 5-fold cross validation technique and using 10 clinical features routinely assessed in psoriasis patients as input variables. Model performance was assessed using the area under the receiver operating characteristic curve (AUC).ResultsThe lowest 5-year risk of discontinuation was associated with therapy with ustekinumab or ixekizumab, male sex and no previous exposure to biologic therapy. The predictive model based on those risk factors had an AUC of 0.61. The best ML model (gradient boosted tree) had an AUC of 0.85.ConclusionsA machine learning-based approach, more than a statistical model, accurately predicts the risk of discontinuation of biologic therapy based on simple patient variables available in clinical practice. ML might be incorporated into clinical decision making.
Global Transmission of COVID-19 for Classifications of Community-Acquired Outbreaks: Machine Learning and Statistical Model Analysis