Skip to main content

Table 3 Results of radiomics machine learning models for predicting overall survival, disease-free survival and local tumor control

From: Radiomics for prediction of radiation-induced lung injury and oncologic outcome after robotic stereotactic body radiotherapy of lung cancer: results from two independent institutions

Endpoint Coxnet Gradient boost
Number of features CCI train-set CCI cross-valid CCI test-set Number of features CCI train-set CCI cross-valid CCI test-set
Overall survival 191 0.80
p < 0.005
0.52 ± 0.15 0.46
n.s
22 0.99
p < 0.005
0.68 ± 0.13 0.45
n.s
Disease free SV 197 0.94
p < 0.005
0.54 ± 0.11 0.49
n.s
10 0.97
p < 0.005
0.76 ± 0.09 0.52
n.s
Local control 199 0.77
p < 0.005
0.54 ± 0.24 0.36
n.s
5 0.98
p < 0.005
0.89 ± 0.11 0.17
n.s
  1. CCI concordance index, means ± standard deviation are shown, p values: significance level of the model risk score in univariate Cox regression analysis.