Prediction of ineffectiveness of biological drugs using machine learning and explainable AI methods: data from the Austrian Biological Registry BioReg.

OBJECTIVES: Machine learning models can support an individualized approach in the choice of bDMARDs. We developed prediction models for 5 different bDMARDs using machine learning methods based on patient data derived from the Austrian Biologics Registry (BioReg). METHODS: Data from 1397 patients and 19 variables with at least 100 treat-to-target (t2t) courses per drug were derived from the BioReg biologics registry. Different machine learning algorithms were trained to predict the risk of ineffectiveness for each bDMARD within the first 26 weeks. Cross-validation and hyperparameter optimization were applied to generate the best models. Model quality was assessed by area under the receiver operating characteristic (AUROC). Using explainable AI (XAI), risk-reducing and risk-increasing factors were extracted. RESULTS: The best models per drug achieved an AUROC score of the following: abatacept, 0.66 (95% CI, 0.54-0.78); adalimumab, 0.70 (95% CI, 0.68-0.74); certolizumab, 0.84 (95% CI, 0.79-0.89); etanercept, 0.68 (95% CI, 0.55-0.87); tocilizumab, 0.72 (95% CI, 0.69-0.77). The most risk-increasing variables were visual analytic scores (VAS) for abatacept and etanercept and co-therapy with glucocorticoids for adalimumab. Dosage was the most important variable for certolizumab and associated with a lower risk of non-response. Some variables, such as gender and rheumatoid factor (RF), showed opposite impacts depending on the bDMARD. CONCLUSION: Ineffectiveness of biological drugs could be predicted with promising accuracy. Interestingly, individual parameters were found to be associated with drug responses in different directions, indicating highly complex interactions. Machine learning can be of help in the decision-process by disentangling these relations.

Felty's syndrome.

Felty's syndrome was first described in 1924 by the US-American physician Augustus Roi Felty as a triad of rheumatoid arthritis, splenomegaly and leucopenia. Even nearly 100 years later, this rare syndrome is still paralleled by diagnostic and therapeutic challenges and its pathogenesis is incompletely understood. Neutropenia with potentially life-threatening infections is the main problem and several pathomechanisms like Fas-mediated apoptosis, anti-neutrophil antibodies, anti-G-CSF antibodies, neutrophil consumption in the context of NETosis and suppression of granulopoiesis by T-LGLs have been suggested. Felty's syndrome has various differential diagnoses as splenomegaly and cytopenia are common features of different infectious diseases, malignancies and autoimmune disorders. Additionally, benign clonal T-/NK-LGL lymphocytosis is increasingly noticed in Felty's syndrome, which further complicates diagnosis. Today's treatment options are still sparse and are largely based on case reports and small case series. Methotrexate is the mainstay of therapy, followed by rituximab, but there is less evidence for alternatives in the case of adverse reactions or failure of these drugs. This article gives an updated review about Felty's syndrome including its pathogenesis and treatment options.