Table 2 Predictive performance (C-index) of intratumoral, different peritumoral, and deep learning radscores for LC and OS prediction of the LRRC patients in the training and validation sets. Peri peritumoral, RS radscore, C-index concordance index, CI confidence interval.

From: Machine learning prognosis model for locally recurrent rectal cancer patients after radioactive 125I seed implantation

 

Training

Validation

Training

Validation

LC prediction: C-index (95%CI)

OS prediction: C-index (95%CI)

RSIntra

0.74 (0.68–0.80)

0.72 (0.63–0.81)

0.72 (0.67–0.77)

0.67 (0.60–0.70)

RSperi1mm

0.77 (0.71–0.83)

0.70 (0.60–0.77)

0.69 (0.63–0.75)

0.57 (0.47–0.67)

RSperi2mm

0.72 (0.65–0.79)

0.66 (0.58–0.78)

0.72 (0.66–0.77)

0.46 (0.36–0.56)

RSperi3mm

0.75 (0.69–0.81)

0.65 (0.55–0.76)

0.70 (0.65–0.76)

0.49 (0.38–0.60)

RSperi4mm

0.73 (0.67–0.78)

0.61 (0.52–0.72)

0.72 (0.67–0.77)

0.64 (0.53–0.74)

RSperi5mm

0.67 (0.58–0.72)

0.62 (0.56–0.74)

0.72 (0.66–0.79)

0.55 (0.50–0.68)

RSperi6mm

0.74 (0.68–0.80)

0.61 (0.49–0.72)

0.70 (0.64–0.79)

0.58 (0.51–0.69)

RSDL1

0.69 (0.62–0.75)

0.53 (0.40–0.66)

0.66 (0.60–0.72)

0.60 (0.51–0.69)

RSDL2

0.73 (0.67–0.78)

0.56 (0.44–0.67)

0.70 (0.65–0.75)

0.63 (0.54–0.70)

RSDL3

0.66 (0.65–0.78)

0.54 (0.42–0.66)

0.67 (0.62–0.74)

0.52 (0.40–0.63)

RSDL4

0.73 (0.66–0.78)

0.67 (0.57–0.77)

0.69 (0.65–0.72)

0.57 (0.51–0.70)

Clinic

0.61 (0.54–0.68)

0.66 (0.60–0.72)

0.68 (0.63–0.73)

0.67 (0.60–0.74)