Journal of Orthopaedic Surgery and Research

Table 2 Performance metrics of various models in both the training and validation sets

From: Application of machine learning-based multi-sequence MRI radiomics in diagnosing anterior cruciate ligament tears

Model	Cohort	AUC (95% CI)	Accuracy	Sensitivity	Specificity	PPV	NPV
Combined	Train	0.973(0.954–0.991)	0.933	0.930	0.935	0.880	0.963
	Validation	0.927(0.878–0.976)	0.857	0.829	0.871	0.763	0.910
T1	Train	0.968(0.953–0.984)	0.919	0.902	0.928	0.866	0.949
	Validation	0.878(0.804–0.951)	0.848	0.800	0.871	0.757	0.897
PD	Train	0.950(0.927–0.973)	0.886	0.909	0.874	0.788	0.949
	Validation	0.904(0.847–0.962)	0.829	0.857	0.814	0.698	0.919

Back to article page

ISSN: 1749-799X

Contact us

Submission enquiries: journalsubmissions@springernature.com