A radiomics-based deep learning approach to predict progression free-survival after tyrosine kinase inhibitor therapy in non-small cell lung cancer

Table 2 Statistical comparisons between developed prediction models based on test dataset

Model performance	Radiomic (C-index = 0.57)	Clinical (C-index = 0.63)	Combined (C-index = 0.66)	p-values
Model performance	Radiomic (C-index = 0.57)	Clinical (C-index = 0.63)	Combined (C-index = 0.66)	Radiomic vs. Combined	Clinical vs. Combined
3 months
Original AUC	0.49	0.71	0.76
AUC	0.52 ± 0.05	0.70 ± 0.06	0.75 ± 0.06	< 0.001^a	< 0.001^a
Sensitivity	0.48 ± 0.10	0.66 ± 0.10	0.68 ± 0.05	< 0.001^a	0.03^a
Specificity	0.64 ± 0.09	0.69 ± 0.06	0.73 ± 0.13	< 0.001^a	< 0.001
12 months
Original AUC	0.59	0.71	0.77
AUC	0.60 ± 0.11	0.70 ± 0.06	0.78 ± 0.05	< 0.001^a	< 0.001^a
Sensitivity	0.51 ± 0.04	0.67 ± 0.11	0.69 ± 0.06	< 0.001^a	0.02^a
Specificity	0.60 ± 0.08	0.62 ± 0.07	0.70 ± 0.11	< 0.001^a	< 0.001^a
18 months
Original AUC	0.69	0.72	0.76
AUC	0.70 ± 0.05	0.71 ± 0.08	0.78 ± 0.05	< 0.001^a	< 0.001^a
Sensitivity	0.60 ± 0.10	0.67 ± 1.12	0.65 ± 0.06	< 0.001^a	0.07
Specificity	0.67 ± 0.03	0.62 ± 0.06	0.80 ± 0.14	< 0.001^a	< 0.001^a
24 months
Original AUC	0.67	0.71	0.86
AUC	0.70 ± 0.10	0.69 ± 0.13	0.85 ± 0.05	< 0.001^a	< 0.001^a
Sensitivity	0.71 ± 0.08	0.71 ± 0.13	0.89 ± 0.06	< 0.001^a	< 0.001^a
Specificity	0.75 ± 0.13	0.78 ± 0.06	0.80 ± 0.14	< 0.001^a	0.03^a

ISSN: 1470-7330