Anthime Flaus1, Julie Amat2, Nathalie Prevot1,3, Louis Olagne4, Lucie Descamps5, Clément Bouvet2, Bertrand Barres2, Clémence Valla2, Sylvain Mathieu5, Marc Andre4, Martin Soubrier5, Charles Merlin2, Antony Kelly2, Marion Chanchou2, Florent Cachin2. 1. Department of Nuclear Medicine, Saint-Etienne University Hospital, University of Saint-Etienne, Saint-Etienne, France. 2. Department of Nuclear Medicine, Jean Perrin Oncology Institute of Clermont-Ferrand, Clermont-Ferrand, France. 3. Institut national de la santé et de la recherche médicale, U 1059 Sainbiose, Université Jean Monnet, Saint-Etienne, France. 4. Department of Internal Medicine, Gabriel Montpied University Hospital, University of Clermont-Ferrand, Clermont-Ferrand, France. 5. Department of Rheumatology, Gabriel Montpied University Hospital, University of Clermont-Ferrand, Clermont-Ferrand, France.
Abstract
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.
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.
Authors: Lien Moreel; Lennert Boeckxstaens; Albrecht Betrains; Maarten Van Hemelen; Steven Vanderschueren; Koen Van Laere; Daniel Blockmans Journal: Front Med (Lausanne) Date: 2022-09-21
Authors: Kornelis S M van der Geest; Yannick van Sleen; Pieter Nienhuis; Maria Sandovici; Nynke Westerdijk; Andor W J M Glaudemans; Elisabeth Brouwer; Riemer H J A Slart Journal: Rheumatology (Oxford) Date: 2022-03-02 Impact factor: 7.580