RESUMO
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.
RESUMO
PURPOSE: To compare, vs CMR, four softwares: quantitative gated SPECT (QGS), myometrix (MX), corridor 4DM (4DM), and Emory toolbox (ECTb) to evaluate left ventricular ejection fraction (LVEF), end-systolic (ESV), and end-diastolic volumes (EDVs) by gated MPI CZT-SPECT. METHODS: 48 patients underwent MPI CZT-SPECT and CMR 6 weeks after STEMI, LV parameters were measured with four softwares at MPI CZT-SPECT vs CMR. We evaluated (i) concordance and correlation between MPI CZT-SPECT and CMR, (ii) concordance MPI CZT-SPECT/CMR for the categorical evaluation of the left ventricular dysfunction, and (iii) impacts of perfusion defects > 3 segments on concordance. RESULTS: LVEF: LCC QGS/CMR = 0.81 [+ 2.2% (± 18%)], LCC MX/CMR = 0.83 [+ 1% (± 17.5%)], LCC 4DM/CMR = 0.73 [+ 3.9% (± 21%)], LCC ECTb/CMR = 0.69 [+ 6.6% (± 21.1%)]. ESV: LCC QGS/CMR = 0.90 [- 8 mL (± 40 mL)], LCC MX/CMR = 0.90 [- 9 mL (± 36 mL)], LCC 4DM/CMR = 0.89 [+ 4 mL (± 45 mL)], LCC ECTb/CMR = 0.87 [- 3 mL (± 45 mL)]. EDV: LCC QGS/CMR = 0.70 [- 16 mL (± 67 mL)], LCC MX/CMR = 0.68 [- 21 mL (± 63 mL], LCC 4DM/CMR = 0.72 [+ 9 mL (± 73 mL)], LCC ECTb/CMR = 0.69 [+ 10 mL (± 70 mL)]. CONCLUSION: QGS and MX were the two best-performing softwares to evaluate LVEF after recent STEMI.