RESUMO
Background: Disease-modifying antirheumatic drugs (bDMARDs) have shown efficacy in treating Rheumatoid Arthritis (RA). Predicting treatment outcomes for RA is crucial as approximately 30% of patients do not respond to bDMARDs and only half achieve a sustained response. This study aims to leverage machine learning to predict both initial response at 6 months and sustained response at 12 months using baseline clinical data. Methods: Baseline clinical data were collected from 154 RA patients treated at the University Hospital in Erlangen, Germany. Five machine learning models were compared: Extreme Gradient Boosting (XGBoost), Adaptive Boosting (AdaBoost), K-nearest neighbors (KNN), Support Vector Machines (SVM), and Random Forest. Nested cross-validation was employed to ensure robustness and avoid overfitting, integrating hyperparameter tuning within its process. Results: XGBoost achieved the highest accuracy for predicting initial response (AUC-ROC of 0.91), while AdaBoost was the most effective for sustained response (AUC-ROC of 0.84). Key predictors included the Disease Activity Score-28 using erythrocyte sedimentation rate (DAS28-ESR), with higher scores at baseline associated with lower response chances at 6 and 12 months. Shapley additive explanations (SHAP) identified the most important baseline features and visualized their directional effects on treatment response and sustained response. Conclusions: These findings can enhance RA treatment plans and support clinical decision-making, ultimately improving patient outcomes by predicting response before starting medication.
RESUMO
OBJECTIVE: Our aim was to quantify nociceptive spontaneous behaviors, knee edema, proinflammatory cytokines, bone density, and microarchitecture in high-fat diet (HFD)-fed mice with unilateral knee arthritis. METHODS: ICR male mice were fed either standard diet (SD) or HFD starting at 3 weeks old. At 17 weeks, HFD and SD mice received intra-articular injections either with Complete Freund's Adjuvant (CFA) or saline into the right knee joint every 7 days for 4 weeks. Spontaneous pain-like behaviors and knee edema were assessed for 26 days. At day 26 post-first CFA injection, serum levels of IL-1ß, IL-6, and RANKL were measured by ELISA, and microcomputed tomography analysis of knee joints was performed. RESULTS: HFD-fed mice injected with CFA showed greater spontaneous pain-like behaviors of the affected extremity as well as a decrease in the weight-bearing index compared to SD-fed mice injected with CFA. Knee edema was not significantly different between diets. HFD significantly exacerbated arthritis-induced bone loss at the distal femoral metaphysis but had no effect on femoral diaphyseal cortical bone. HFD did not modify serum levels of proinflammatory cytokines. CONCLUSIONS: HFD exacerbates pain-like behaviors and significantly increases the magnitude of periarticular trabecular bone loss in a murine model of unilateral arthritis.