Integration of Clinical, Cytokine, and Ultrasound Data Using Machine Learning Reveals a Multidimensional Inflammatory...

Background: Polymyalgia rheumatica (PMR) is a clinically heterogeneous inflammatory disorder in which conventional acute-phase reactants may inadequately reflect the complexity and biological variability of disease activity. Precision medicine approaches integrating multidimensional clinical and laboratory data may offer a more comprehensive characterization of inflammatory phenotypes. This study investigated whether the combined assessment of cytokine profiles, routine laboratory biomarkers, ultrasound findings, and clinical variables could improve disease activity stratification in PMR. Methods: A total of 103 consecutive patients with PMR were retrospectively analyzed. Disease activity was assessed using the PMR Activity Score (PMR-AS) and, for exploratory purposes, dichotomized according to the cohort median (≥11 vs. <11). Group differences were evaluated using non-parametric statistical methods. The multidimensional structure of the dataset was explored through Spearman correlation analysis, principal component analysis (PCA), and unsupervised clustering. Predictive models, including logistic regression, random forest, and gradient boosting, were developed to evaluate the potential contribution of integrated analytical approaches to patient stratification. Results: The study cohort included 103 patients (63.1% female), with a median age of 76 years (IQR 71-81); 57 patients (55.3%) presented PMR-AS ≥11. Patients with higher disease activity exhibited significantly increased levels of CRP, fibrinogen, platelet count, IL-6, serum amyloid A (SAA), and myeloid-related protein (MRP), together with a higher prevalence of joint effusion and Power Doppler positivity. Among the evaluated biomarkers, SAA demonstrated the strongest correlation with disease activity (Spearman ρ = 0.878; p < 0.001). Multivariate predictive modeling showed high discriminative performance, with random forest achieving the highest cross-validated AUC (0.934), whereas gradient boosting demonstrated the best overall accuracy (0.883). Unsupervised clustering analysis identified a subgroup characterized by a more pronounced inflammatory signature associated with higher PMR-AS values. Conclusions: These findings support the concept that disease activity in PMR may be more effectively represented through an integrated multidimensional inflammatory profile rather than isolated biomarkers. The combined evaluation of routine laboratory parameters, cytokines, and imaging features may contribute to more refined patient stratification within a precision medicine framework. Although exploratory, these results highlight the potential value of advanced data integration strategies for supporting biologically informed disease characterization in PMR, while underscoring the need for external validation before translation into clinical practice.