Table 2 The performances in training data and testing data

From: Exploring potential methylation markers for ovarian cancer from cervical scraping samples

Dataset	Normal	Benign	Malignant	Overall
Precision
Training	0.92	0.93	1.0	⁺0.95
Testing	0.96	0.73	0.75	⁺0.81
Recall
Training	1.0	0.93	0.71	⁺0.88
Testing	1.0	0.89	0.43	⁺0.77
F1-score
Training	0.96	0.93	0.83	*0.93
Testing	0.98	0.80	0.55	*0.86
Accuracy
Training	0.93
Testing	0.88

⁺Macro-precision and macro-recall, which was the mean of precision and recall
*The overall F1-score was calculated using sklearn weighted F1-score

Back to article page

ISSN: 1479-7364

Contact us

General enquiries: journalsubmissions@springernature.com