RESUMO
We aimed to set up an Automated Radiology Alert System (ARAS) for the detection of pneumothorax in chest radiographs by a deep learning model, and to compare its efficiency and diagnostic performance with the existing Manual Radiology Alert System (MRAS) at the tertiary medical center. This study retrospectively collected 1235 chest radiographs with pneumothorax labeling from 2013 to 2019, and 337 chest radiographs with negative findings in 2019 were separated into training and validation datasets for the deep learning model of ARAS. The efficiency before and after using the model was compared in terms of alert time and report time. During parallel running of the two systems from September to October 2020, chest radiographs prospectively acquired in the emergency department with age more than 6 years served as the testing dataset for comparison of diagnostic performance. The efficiency was improved after using the model, with mean alert time improving from 8.45 min to 0.69 min and the mean report time from 2.81 days to 1.59 days. The comparison of the diagnostic performance of both systems using 3739 chest radiographs acquired during parallel running showed that the ARAS was better than the MRAS as assessed in terms of sensitivity (recall), area under receiver operating characteristic curve, and F1 score (0.837 vs. 0.256, 0.914 vs. 0.628, and 0.754 vs. 0.407, respectively), but worse in terms of positive predictive value (PPV) (precision) (0.686 vs. 1.000). This study had successfully designed a deep learning model for pneumothorax detection on chest radiographs and set up an ARAS with improved efficiency and overall diagnostic performance.
RESUMO
BACKGROUND: Frey syndrome is a common complication after parotidectomy. This study aimed to investigate the potential predictors for developing severe Frey syndrome after parotidectomy and to identify patients who may benefit from additional preventive maneuvers. METHODS: A total of 485 patients received parotidectomy because of parotid tumors at the Otolaryngology Department of the National Cheng Kung University Hospital, from July 2009 to November 2015. Only 115 of 485 patients were included in this study and to fill in a questionnaire to determine the occurrence and severity of Frey syndrome. RESULTS: A total of 115 parotidectomies were identified. 84 (73%, 84/115) patients were aware of the discomfort and were thus considered symptomatic. 39 (34%, 39/115) patients considered the symptoms apparently affected their quality of life. MSI tests showed that 56 (49%, 56/115) patients had a positive MSI test. By combining the results from symptom questionnaire and MSI test, 23 patients (20%, 23/115) had a severe form of Frey syndrome. Among all clinicopathological variables, the resected specimen size was the only significant predictor of the severe Frey syndrome group (P = 0.04). Disease pathology, tumor size, and adjuvant radiotherapy did not correlate with the severe Frey syndrome. Using receiver operating curve analysis, the best cutoff value of the resected specimen size (in largest dimension) for predicting severe Frey syndrome was 40 mm(sensitivity: 71.7%, specificity: 42.0%; area under the curve = 0.6483). The odds ratio of severe Frey syndrome with every 10 mm increase in the largest diameter of resected specimen was 1.30 (95% confidence interval, 1.01-1.68; P = 0.04). CONCLUSIONS: Resected specimen size is the only significant predictor of developing severe Frey syndrome after parotidectomy. Preventive interventions may have to be considered in high-risk patients whose resected specimen size (in largest dimension) is greater than 40 mm.