Skip to main content

Table 3 Summary of prediction performance of PredictCBC-1A, PredictCBC-1B, PredictCBC-2.0A, and PredictCBC-2.0B with the corresponding 95% prediction intervals (PI) based on a leave-one-study-out cross-validation procedure

From: PredictCBC-2.0: a contralateral breast cancer risk prediction model developed and validated in ~ 200,000 patients

CBC risk prediction model

Performance measure

Discrimination

Calibration

AUC (95% PI)

O/E ratio (95% PI)

5-year

10-year

5-year

10-year

PredictCBC-1A

0.62 (0.51–0.74)

0.63 (0.54–0.71)

0.90 (0.36–2.24)

0.91 (0.34–2.48)

PredictCBC-2.0A

0.66 (0.55–0.76)

0.65 (0.56–0.74)

0.91 (0.35–2.34)

0.92 (0.34–2.54)

PredictCBC-1B

0.59 (0.49–0.69)

0.58 (0.51–0.65)

0.91 (0.32–2.55)

0.92 (0.30–2.80)

PredictCBC-2.0B

0.59 (0.51–0.68)

0.58 (0.51–0.65)

0.91 (0.31–2.63)

0.92 (0.30–2.87)

  1. AUC area under the curve, CBC contralateral breast cancer, PI prediction interval, O/E observed/expected
Back to article page

Breast Cancer Research

ISSN: 1465-542X

Contact us