Develop and validate a radiomics space-time model to predict the pathological complete response in patients undergoing neoadjuvant treatment of rectal cancer: an artificial intelligence model study based on machine learning

Table 2 Results of the ROC curve analysis for each basic model

ROC curve analysis	Classification of the basic model
ROC curve analysis	Pre-treatment model	Post-treatment model	Delta model	Combined basic model
AUC	0.771 (0.666, 0.856)	0.681 (0.578, 0.775)	0.871 (0.78, 0.935)	0.907 (0.848, 0.956)
Sensitivity	0.727	0.864	0.909	0.909
Specificity	0.803	0.492	0.656	0.803
F1_score	0.612	0.528	0.613	0.667
Recall	0.682	0.864	0.864	0.909
Accuracy	0.771	0.59	0.711	0.759

ISSN: 1471-2407