Radiotranscriptomics of non-small cell lung carcinoma for assessing high-level clinical outcomes using a machine learning-derived multi-modal signature

Table 2 Performance analysis of the proposed multi-view and single-source pipelines for survival analysis

	Cox	CoxPH	Extra trees	Survival tree	Random forest	SVM-based
Multi-view	0.63 ± 0.11	0.68 ± 0.15	0.64 ± 0.06	0.64 ± 0.09	0.61 ± 0.12	0.76 ± 0.08
Multi-view score	0.64 ± 0.11	0.67 ± 0.05	0.69 ± 0.11	0.67 ± 0.12	0.66 ± 0.08	0.79 ± 0.03
Deep features	0.61 ± 0.08	0.62 ± 0.10	0.66 ± 0.12	0.64 ± 0.04	0.60 ± 0.04	0.73 ± 0.07
Deep feature score	0.66 ± 0.03	0.66 ± 0.04	0.62 ± 0.07	0.58 ± 0.14	0.57 ± 0.06	0.76 ± 0.06
Radiomics	0.61 ± 0.04	0.63 ± 0.04	0.63 ± 0.08	0.60 ± 0.09	0.57 ± 0.14	0.56 ± 0.05
Radiomic score	0.65 ± 0.03	0.63 ± 0.08	0.66 ± 0.05	0.61 ± 0.11	0.58 ± 0.08	0.68 ± 0.03
Transcriptomics	0.71 ± 0.09	0.70 ± 0.06	0.67 ± 0.05	0.68 ± 0.08	0.64 ± 0.04	0.71 ± 0.15
Transcriptomics score	0.69 ± 0.08	0.72 ± 0.06	0.67 ± 0.05	0.68 ± 0.01	0.64 ± 0.05	0.72 ± 0.09

The following metrics represent the mean ± standard deviation of 100 iterations for each pipeline. CoxPH Cox proportional hazards, SVM support vector machine

ISSN: 1475-925X