RESUMO
Introduction: Percutaneous transhepatic biliary drainage (PTBD) is a common procedure for biliary obstructive jaundice caused by biliary tract obstruction. In clinical practice, PTBD can be carried out at right- or left-sided approach. However, different hepatic entry site may affect success rates and complications. Couinaud classification of liver anatomy further divides the liver into functionally independent segments (segment 2/3, segment 5/6, and segment 7/8). Therefore, this study aimed to elucidate whether different Couinaud hepatic segments as PTBD entry site are associated with high PTBD success and low complications. Methods: A total of 617 patients who underwent PTBD were retrospectively reviewed. Univariate and multivariate logistic regression analyses were performed to identify entry segments associated with PTBD success, bilirubin reduction, and complications. Results: With higher hepatic segment of PTBD entry site (segment 2/3, 5/6, and 7/8), the trend of PTBD success rate (82.0%, 71.7% and 60.7%; P<0.001) and bilirubin reduction (93.2%, 89.5%, and 82.0%; P=0.012) decreased. Furthermore, PTBD entry at segment 7/8 (42.6%) had highest complication rate than segment 5/6 (6.4%) and 2/3 (9.4%). Univariate and multivariate logistic regression analyses showed that PTBD entry segment was an independent factor associated with PTBD success, bilirubin reduction, and complications. Compared to segment 7/8, segment 2/3 and 5/6 had higher odds of PTBD success (aOR=2.699 and aOR=1.454, respectively) and bilirubin reduction (aOR=3.472 and aOR=2.361, respectively) and associated with lower risk of complications (aOR=0.143 and aOR=0.098, respectively). No independent risk factor for PTBD success and bilirubin reduction were identified in intrahepatic tumors. Moreover, for extrahepatic tumors, PTBD entry at segment 2/3 and segment 5/6 was more likely achieve PTBD success (aOR=3.037 and aOR=1.929, respectively), bilirubin reduction (aOR=3.069 and aOR=3.515) and low complications (aOR=0.102 and aOR=0.126, respectively). Discussion: Good clinical outcomes were observed for PTBD entry at segments 5/6 and 2/3. In contrast, segment 7/8 had the lowest success rate, smallest bilirubin reduction, and the highest complication rate. For patients with obstructive jaundice, PTBD entry in hepatic segments 2/3 and 5/6 is recommended to achieve high success rates and low complications.
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.
