Journal of Ovarian Research

Table 2 Diagnostic efficiency of different classifiers in the training and test cohorts

From: Development and validation of an ultrasound‑based radiomics nomogram to predict lymph node status in patients with high-grade serous ovarian cancer: a retrospective analysis

Classifiers	Training cohort				10 fold cross validation
Classifiers	AUC (95% CI)	SEN	SPE	ACC	Mean AUC	Mean SEN	Mean SPE	Mean ACC
SVM	0.936 (0.906,0.967)	0.916	0.830	0.866	0.843	0.658	0.870	0.782
KNN	0.907 (0.878,0.937)	0.906	0.728	0.804	0.811	0.595	0.846	0.733
RF	0.988 (0.980,0.996)	0.978	0.951	0.963	0.823	0.627	0.871	0.767
DT	0.893 (0.858,0.928)	0.797	0.859	0.832	0.774	0.663	0.744	0.705
LR	0.899 (0.864,0.933)	0.877	0.804	0.835	0.876	0.688	0.860	0.789

Abbreviations SVM, support vector machine; KNN, K-nearest neighbor; RF, random forest; DT, decision tree; LR, logistic regression; AUC, area under the curve; CI, confidence interval; SEN, sensitivity; SPE, specificity; ACC, accuracy

Back to article page

ISSN: 1757-2215

Contact us

General enquiries: journalsubmissions@springernature.com