Table 5.
ColonFlag performance based on different tumor locations across the colon and rectum
| Study | Sensitivitya | ORb | Others |
|---|---|---|---|
| Kinar, 2016 10 | Specificitya | ||
| Rectum=85.9% | |||
| Left colon=87.4% | |||
| Transverse colon=93.6% | |||
| Right colon=96.1% | |||
| Hornbrook, 2017 15 | Cecum=93.4 | ||
| Ascending=90.0 | |||
| Transverse=51.1 | |||
| Sigmoid=13.8 | |||
| Rectum=10.2 | |||
| Hilsden, 2018 6 | Ascending/cecum=10.8% | Ascending/cecum=2.6 | |
| Other=13.2% | Other=3 | ||
| Schneider, 2020 18 | Distal=27.3% | Distal=12.1 | AUCc |
| Proximal=51.8% | Proximal=34.7 | Distal=0.74 | |
| Proximal=0.86 |
AUC: Area Under the Curve; OR: Odds Ratio;
a
Using the predicted outcomes from a binary classification model and comparing them to the true outcomes of the instances.
b
Calculated by comparing the odds of the event in the exposed group to the odds of the event in the unexposed group using data.
c
Computed by plotting a Receiver Operating Characteristics (ROC) curve based on model predictions and true labels, then calculating the area under this curve.