Fig. 1From: A machine learning model to determine the accuracy of variant calls in capture-based next generation sequencingModel Sensitivity. ROC curve plotting the true positive rate (sensitivity) against the false positive rate (specificity). The model threshold was chosen to eliminate false positives (variants erroneously called as high-confidence, but were found to be not present by Sanger sequencing). This resulted in a calculated area under the curve (AUC) of 0.99913Back to article page