From the case:
Receiver operating characteristic (ROC) curve
{"current_user":null,"step_through_annotations":true,"access":{"can_edit":false,"can_download":true,"can_toggle_annotations":true,"can_feature":false,"can_examine_pipeline_reports":false,"can_pin":false},"extraPropsURL":"/studies/36265/annotated_viewer_json?iframe=true\u0026lang=us"}
This graph demonstrates a theoretically perfect test (green "curve") with an area under the curve of 1.0. The grey line demonstrates a worthless test, with a 50/50 chance of being accurate in detection.
From the case:
Receiver operating characteristic (ROC) curve
{"current_user":null,"step_through_annotations":true,"access":{"can_edit":false,"can_download":true,"can_toggle_annotations":true,"can_feature":false,"can_examine_pipeline_reports":false,"can_pin":false},"extraPropsURL":"/studies/113380/annotated_viewer_json?iframe=true\u0026lang=us"}
This graph compares different modalities, tests, or readers given a certain disease and patient population. The green curve represents a "better" test with a lower false positive rate at a given level of sensitivity (or a higher sensitivity at a given false positive rate). The green curve has a larger area under the curve (AUR). The grey line represents a worthless test that is no better than chance.
From the case:
Receiver operating characteristic (ROC) curve
{"current_user":null,"step_through_annotations":true,"access":{"can_edit":false,"can_download":true,"can_toggle_annotations":true,"can_feature":false,"can_examine_pipeline_reports":false,"can_pin":false},"extraPropsURL":"/studies/113381/annotated_viewer_json?iframe=true\u0026lang=us"}
Derivations of sensitivity and specificity