Journal of the American College of Surgeons
-
Traditional teaching continues to espouse the value of initial trauma chest x-ray (CXR) as a screening tool for blunt thoracic aortic injury (BTAI). The ability of this modality to yield findings that reliably correlate with grade of injury and need for subsequent treatment, however, requires additional multicenter prospective examination. We hypothesized that CXR is not a reliable screening tool, even at the highest grades of BTAI. ⋯ CXR is not a reliable screening tool for the detection of BTAI, even at the highest grades of injury. Further investigations of specific high-risk criteria for screening that incorporate imaging, mechanism, and physiologic findings are warranted.
-
Multicenter Study
Pediatric DUCT Score: A Highly Specific Predictive Model for Choledocholithiasis in Children.
Current adult guidelines for the management of choledocholithiasis (CDL) may not be appropriate for children. We hypothesized adult preoperative predictive factors are not reliable for predicting CDL in children. ⋯ Our study demonstrated that the pediatric DUCT criteria, incorporating common bile duct dilation, choledocholithiasis seen on ultrasound, and total bilirubin ≥1.8 mg/dL, highly predicts the presence of choledocholithiasis in children. Other adult preoperative factors are not predictive of common bile duct stone in children.
-
Multicenter Study
Development and Validation of an Alpha-Fetoprotein Tumor Burden Score Model to Predict Post-Recurrence Survival among Patients with Hepatocellular Carcinoma.
The purpose of this study is to establish a prognostic model to predict postrecurrence survival (PRS) probability after initial resection of hepatocellular carcinoma (HCC). ⋯ The ATS model had excellent prognostic discriminatory power to stratify patients relative to PRS.
-
The American College of Surgeons NSQIP risk calculator (RC) uses regression to make predictions for fourteen 30-day surgical outcomes. While this approach provides accurate (discrimination and calibration) risk estimates, they might be improved by machine learning (ML). To investigate this possibility, accuracy for regression-based risk estimates were compared to estimates from an extreme gradient boosting (XGB)-ML algorithm. ⋯ XGB-ML provided more accurate risk estimates than regression in terms of discrimination and calibration. Differences in calibration between regression and XGB-ML were of substantial magnitude and support transitioning the RC to XGB-ML.