ABSTRACT
Background Corticosteroids injected for the treatment of musculoskeletal pain are systemically absorbed and can affect the immune response to viral infections. Purpose To determine the incidence of symptomatic COVID-19 disease in individuals receiving image-guided corticosteroid injections for musculoskeletal pain compared with the general population during the pandemic recovery period. Materials and methods In this prospective cohort multicenter study, adults with a history of musculoskeletal pain who underwent imaging-guided intra-articular and spine corticosteroid injections between April 2020 and February 2021 were consecutively enrolled. Participants were followed for a minimum of 28 days through their electronic medical record (EMR) or by direct phone call to screen for COVID-19 test results or symptoms. Clinical data including body mass index (BMI) was also obtained from the EMR. Incidence of COVID-19 in the state was obtained using the Massachusetts COVID-19 Response Reporting website. Student t tests were used for continuous variable comparisons. Univariable analyses were performed using Fisher exact tests. Results A total of 2714 corticosteroid injections were performed for 2190 adult participants (mean age ± standard deviation, 59 ± 15 years, 1031 women). Follow-up was available for 1960 (89%) participants who received 2484 injections. Follow-up occurred 97 ± 33 days (range 28 - 141 days) after the injection. There were 10/1960 participants with COVID-19 within 28 days from the injection (0.5%, 95% CI, 0.24-0.94%) and 43/1960 participants with COVID-19 up to 4 months after the injection (2.2% 95%CI, 1.6-2.9%). This was lower than the incidence rate in the population of Massachusetts during the same period (519,195/6,892,503, 7.5%, P <.001 both at 28 days and 4 months). Participants diagnosed with COVID-19 (n=10) at 28 days had higher BMI than the entire cohort (n=1960) (32 ± 10 vs. 28 ± 6 kg/m2, P=.04). Conclusion Adults who received image-guided corticosteroid injections for pain management performed during the pandemic recovery period had a lower incidence of symptomatic COVID- 19 compared with the general population.
ABSTRACT
OBJECTIVES: CT findings of COVID-19 look similar to other atypical and viral (non-COVID-19) pneumonia diseases. This study proposes a clinical computer-aided diagnosis (CAD) system using CT features to automatically discriminate COVID-19 from non-COVID-19 pneumonia patients. METHODS: Overall, 612 patients (306 COVID-19 and 306 non-COVID-19 pneumonia) were recruited. Twenty radiological features were extracted from CT images to evaluate the pattern, location, and distribution of lesions of patients in both groups. All significant CT features were fed in five classifiers namely decision tree, K-nearest neighbor, naïve Bayes, support vector machine, and ensemble to evaluate the best performing CAD system in classifying COVID-19 and non-COVID-19 cases. RESULTS: Location and distribution pattern of involvement, number of the lesion, ground-glass opacity (GGO) and crazy-paving, consolidation, reticular, bronchial wall thickening, nodule, air bronchogram, cavity, pleural effusion, pleural thickening, and lymphadenopathy are the significant features to classify COVID-19 from non-COVID-19 groups. Our proposed CAD system obtained the sensitivity, specificity, and accuracy of 0.965, 93.54%, 90.32%, and 91.94%, respectively, using ensemble (COVIDiag) classifier. CONCLUSIONS: This study proposed a COVIDiag model obtained promising results using CT radiological routine features. It can be considered an adjunct tool by the radiologists during the current COVID-19 pandemic to make an accurate diagnosis. KEY POINTS: ⢠Location and distribution of involvement, number of lesions, GGO and crazy-paving, consolidation, reticular, bronchial wall thickening, nodule, air bronchogram, cavity, pleural effusion, pleural thickening, and lymphadenopathy are the significant features between COVID-19 from non-COVID-19 groups. ⢠The proposed CAD system, COVIDiag, could diagnose COVID-19 pneumonia cases with an AUC of 0.965 (sensitivity = 93.54%; specificity = 90.32%; and accuracy = 91.94%). ⢠The AUC, sensitivity, specificity, and accuracy obtained by radiologist diagnosis are 0.879, 87.10%, 88.71%, and 87.90%, respectively.