Decision Tree With Only Two Musculoskeletal Sites to Diagnose Polymyalgia Rheumatica Using [18F]FDG PET-CT.

Introduction: The aim of this study was to find the best ordered combination of two FDG positive musculoskeletal sites with a machine learning algorithm to diagnose polymyalgia rheumatica (PMR) vs. other rheumatisms in a cohort of patients with inflammatory rheumatisms. Methods: This retrospective study included 140 patients who underwent [18F]FDG PET-CT and whose final diagnosis was inflammatory rheumatism. The cohort was randomized, stratified on the final diagnosis into a training and a validation cohort. FDG uptake of 17 musculoskeletal sites was evaluated visually and set positive if uptake was at least equal to that of the liver. A decision tree classifier was trained and validated to find the best combination of two positives sites to diagnose PMR. Diagnosis performances were measured first, for each musculoskeletal site, secondly for combination of two positive sites and thirdly using the decision tree created with machine learning. Results: 55 patients with PMR and 85 patients with other inflammatory rheumatisms were included. Musculoskeletal sites, used either individually or in combination of two, were highly imbalanced to diagnose PMR with a high specificity and a low sensitivity. The machine learning algorithm identified an optimal ordered combination of two sites to diagnose PMR. This required a positive interspinous bursa or, if negative, a positive trochanteric bursa. Following the decision tree, sensitivity and specificity to diagnose PMR were respectively 73.2 and 87.5% in the training cohort and 78.6 and 80.1% in the validation cohort. Conclusion: Ordered combination of two visually positive sites leads to PMR diagnosis with an accurate sensitivity and specificity vs. other rheumatisms in a large cohort of patients with inflammatory rheumatisms.

Utility of 18F-Fluorodeoxyglucose Positron Emission Tomography in Inflammatory Rheumatism, Particularly Polymyalgia Rheumatica: A Retrospective Study of 222 PET/CT.

Purpose: The objective of this study was to evaluate periarticular FDG uptake scores from 18F-FDG-PET/CT to identify polymyalgia rheumatica (PMR) within a population presenting rheumatic diseases. Methods: A French retrospective study from 2011 to 2015 was conducted. Patients who underwent 18F-FDG-PET/CT for diagnosis or follow-up of a rheumatism or an unexplained biological inflammatory syndrome were included. Clinical data and final diagnosis were reviewed. Seventeen periarticular sites were sorted by a visual reading enabling us to calculate two scores: mean FDG visual uptake score, number of sites with significant uptake same as that or higher than liver uptake intensity and by a semi-quantitative analysis using mean maximum standardized uptake value (SUVmax). Optimal cutoffs of visual score and SUVmax to diagnose PMR were determined using receiver operating characteristics curves. Results: Among 222 18F-FDG PET/CT selected for 215 patients, 161 18F-FDG PET/CT were performed in patients who presented inflammatory rheumatism as a final diagnosis (of whom 57 PMR). The presence of at least three sites with significant uptake identified PMR with a sensitivity of 86% and a specificity of 85.5% (AUC 0.872, 95% CI [0.81-0.93]). The mean FDG visual score cutoff to diagnose a PMR was 0.765 with a sensitivity of 82.5% and a specificity of 75.8% (AUC 0.854; 95% CI [0.80-0.91]). The mean SUVmax cutoff to diagnose PMR was 2.168 with a sensitivity of 77.2% and a specificity of 77.6% (AUC 0.842; 95% CI [0.79-0.89]). Conclusions: This study suggests that 18F-FDG PET/CT had good performances to identify PMR within a population presenting rheumatic diseases.