Table 4

Prediction performance of machine-learning algorithms: 12-month survival

Cancer type	Area under ROC curve (95% CI)
Cancer type	EAR only	ECO only	EAR+ECO
Genitourinary	0.79 (0.75 to 0.83)	0.79 (0.75 to 0.83)	0.84 (0.80 to 0.87)*,†
Colorectal	0.82 (0.78 to 0.86)	0.83 (0.79 to 0.86)	0.87 (0.83 to 0.90)*,†
Lung	0.73 (0.69 to 0.77)	0.78 (0.73 to 0.82)*	0.82 (0.78 to 0.86)*,†
Breast	0.71 (0.65 to 0.78)	0.90 (0.86 to 0.94)	0.92 (0.89 to 0.96)*
Haematological	0.63 (0.59 to 0.68)	0.70 (0.66 to 0.75)*	0.69 (0.64 to 0.74)*
Upper gastrointestinal	0.62 (0.57 to 0.66)	0.70 (0.65 to 0.74)*	0.72 (0.68 to 0.76)*
Skin	0.76 (0.71 to 0.88)	0.89 (0.85 to 0.93)*	0.93 (0.90 to 0.96)*
Head and neck	0.77 (0.73 to 0.88)	0.68 (0.63 to 0.73)	0.79 (0.75 to 0.84)†
Gynaecological	0.95 (0.92 to 0.97)	1 (1 to 1)*	0.99 (0.98 to 1)*
CNS	0.66 (0.58 to 0.73)	0.68 (0.61 to 0.76)	0.69 (0.63 to 0.76)
Unknown primary	0.87 (0.84 to 0.91)	0.81 (0.77 to 0.85)	0.88 (0.84 to 0.91)

*Significantly greater than EAR only.
†Significantly greater than ECO only.
CNS, central nervous system; EAR, electronic administrative records; ECO, Evaluation of Cancer Outcomes; ROC, receiver operating characteristic.