Morphometric and radiomics analysis toward the prediction of epilepsy associated with supratentorial low-grade glioma in children

Table 2 Performance of seizure prediction models using tumor location features for pediatric patients with supratentorial glioma

Classifier	Precision	Recall	Specificity	Accuracy	F1-Score	TP	FN	FP	TN	AUC
Cubic SVM	0.760	0.826	0.760	0.792	0.792	19	4	6	19	0.870
Weighted KNN	0.783	0.783	0.800	0.792	0.783	18	5	5	20	0.835
Fine KNN	0.826	0.826	0.840	0.833	0.826	19	4	4	21	0.833
Cosine KNN	0.714	0.870	0.680	0.771	0.784	20	3	8	17	0.814
Linear Discriminant	0.923	0.522	0.960	0.750	0.667	12	11	1	24	0.807
Binary GLM Logistic Regression	0.857	0.522	0.920	0.729	0.649	12	11	2	23	0.803
Medium KNN	0.714	0.870	0.680	0.771	0.784	20	3	8	17	0.800
Cubic KNN	0.714	0.870	0.680	0.771	0.784	20	3	8	17	0.794
Fine Tree	0.741	0.870	0.720	0.792	0.800	20	3	7	18	0.788
Medium Tree	0.741	0.870	0.720	0.792	0.800	20	3	7	18	0.788
Coarse Tree	0.741	0.870	0.720	0.792	0.800	20	3	7	18	0.788
Fine Gaussian SVM	0.750	0.522	0.840	0.688	0.615	12	11	4	21	0.779
Medium Gaussian SVM	0.800	0.522	0.880	0.708	0.632	12	11	3	22	0.767
Gaussian Naive Bayes	0.923	0.522	0.960	0.750	0.667	12	11	1	24	0.760
Coarse Gaussian SVM	0.706	0.522	0.800	0.667	0.600	12	11	5	20	0.760
Quadratic Discriminant	0.917	0.478	0.960	0.729	0.629	11	12	1	24	0.757
Quadratic SVM	0.690	0.870	0.640	0.750	0.769	20	3	9	16	0.708
Linear SVM	0.818	0.391	0.920	0.667	0.529	9	14	2	23	0.694
Kernel Naive Bayes	0.875	0.609	0.920	0.771	0.718	14	9	2	23	0.692
Coarse KNN	NaN	0.000	1.000	0.521	NaN	0	23	0	25	0.000

AUC, area under receiver operating characteristic curve; FN: False Negative; FP: False Positive; GLM: Generalized linear models; KNN: k-nearest neighbors; SVM: Support Vector Machines; TN: True Negative TP: True Positive

ISSN: 1470-7330