Predictive value of quantitative 18F-FDG-PET radiomics analysis in patients with head and neck squamous cell carcinoma

EJNMMI Research

Table 4 The accuracy of the prediction models for recurrence, metastasis, and overall survival in the training set and validated in the validation set. For the recurrence prediction, the combination of HPV, SUVmean, SUVpeak, factors 3, 4, and 6 was most accurate. For the metastasis prediction, the use of only MATV was most accurate. For overall survival prediction, the combination of HPV, SUVmax, SUVmean, factors 1 and 5 was most accurate

Final prediction models	Training set				Validation set
Final prediction models	Patients	Events	Concordance index	SE	Patients	Events	Concordance index	SE
Recurrence prediction model HPV, SUVmean, SUVpeak, factor 3, factor 4, factor 6	103	27	0.779	0.050	71	19	0.645	0.071
Metastasis prediction model MATV	103	10	0.657	0.093	71	18	0.627	0.094
Overall survival prediction model HPV, SUVmax, SUVmean, factor 1, factor 5	103	37	0.751	0.045	71	22	0.764	0.052

Events: amount of recurrences in the recurrence prediction model; amount of distant metastases in the metastasis prediction model; amount of deaths in the overall survival prediction model
SE standard error