BackgroundMultiple biologic and targeted synthetic disease-modifying rheumatic drugs (b/tsDMARDs) are approved for the management of rheumatoid arthritis (RA), including TNF inhibitors (TNFi), bDMARDs with other modes of action (bDMARD-OMA) and Janus kinase inhibitors (JAKi). Combination of b/tsDMARDs with conventional synthetic DMARDs (csDMARDs) is recommended, yet monotherapy is common in practice.ObjectiveTo compare drug maintenance and clinical effectiveness of three alternative treatment options for RA management.MethodsThis observational cohort study was nested within the Swiss RA Registry. TNFi, bDMARD-OMA (abatacept or anti-IL6 agents) or the JAKi tofacitinib (Tofa) initiated in adult RA patients were included. The primary outcome was overall drug retention. We further analysed secondary effectiveness outcomes and whether concomitant csDMARDs modified effectiveness, adjusting for potential confounding factors.Results4023 treatment courses of 2600 patients were included, 1862 on TNFi, 1355 on bDMARD-OMA and 806 on Tofa. TNFi was more frequently used as a first b/tsDMARDs, at a younger age and with shorter disease duration. Overall drug maintenance was significantly lower with TNFi compared with Tofa [HR 1.29 (95% CI 1.14 to 1.47)], but similar between bDMARD-OMA and Tofa [HR 1.09 (95% CI 0.96 to 1.24)]. TNFi maintenance was decreased when prescribed without concomitant csDMARDs [HR: 1.27 (95% CI 1.08 to 1.49)], while no difference was observed for bDMARD-OMA or Tofa maintenance with respect to concomitant csDMARDs.ConclusionTofa drug maintenance was comparable with bDMARDs-OMA and somewhat higher than TNFi. Concomitant csDMARDs appear to be required for optimal effectiveness of TNFi, but not for bDMARD-OMA or Tofa.

Background and purpose Clinical outcomes vary substantially among individuals with large vessel occlusion (LVO) stroke. A small infarct core and large imaging mismatch were found to be associated with good recovery. The aim of this study was to investigate whether those imaging variables would improve individual prediction of functional outcome after early (<6 h) endovascular treatment (EVT) in LVO stroke. Methods We included 222 patients with acute ischemic stroke due to middle cerebral artery (MCA)‐M1 occlusion who received EVT. As predictors, we used clinical variables and region of interest (ROI)‐based magnetic resonance imaging features. We developed different machine‐learning models and quantified their prediction performance according to the area under the receiver‐operating characteristic curves and the Brier score. Results The rate of successful recanalization was 78%, with 54% patients having a favorable outcome (modified Rankin scale score 0–2). Small infarct core was associated with favorable functional outcome. Outcome prediction improved only slightly when imaging was added to patient variables. Age was the driving factor, with a sharp decrease in likelihood of favorable functional outcome above the age of 78 years. Conclusions In patients with MCA‐M1 occlusion strokes referred to EVT within 6 h of symptom onset, infarct core volume was associated with outcome. However, ROI‐based imaging variables led to no significant improvement in outcome prediction at an individual patient level when added to a set of clinical predictors. Our study is in concordance with current practice, where imaging mismatch or collateral readouts are not recommended as factors for excluding patients with MCA‐M1 occlusion for early EVT.

At present, the majority of the proposed Deep Learning (DL) methods provide point predictions without quantifying the model's uncertainty. However, a quantification of the reliability of automated image analysis is essential, in particular in medicine when physicians rely on the results for making critical treatment decisions. In this work, we provide an entire framework to diagnose ischemic stroke patients incorporating Bayesian uncertainty into the analysis procedure. We present a Bayesian Convolutional Neural Network (CNN) yielding a probability for a stroke lesion on 2D Magnetic Resonance (MR) images with corresponding uncertainty information about the reliability of the prediction. For patientlevel diagnoses, different aggregation methods are proposed and evaluated, which combine the single image-level predictions. Those methods take advantage of the uncertainty in image predictions and report model uncertainty at the patient-level. In a cohort of 511 patients, our Bayesian CNN achieved an accuracy of 95.33% at the image-level representing a significant improvement of 2% over a non-Bayesian counterpart. The best patient aggregation method yielded 95.89% of accuracy. Integrating uncertainty information about image predictions in aggregation models resulted in higher uncertainty measures to false patient classifications, which enabled to filter critical patient diagnoses that are supposed to be closer examined by a medical doctor. We therefore recommend using Bayesian approaches not only for improved image-level prediction and uncertainty estimation but also for the detection of uncertain aggregations at the patient-level.