Automated classification of urine biomarkers to diagnose pancreatic cancer using 1-D convolutional neural networks

Table 3 Comparative evaluation of developed classifier against the state-of-the-art models to diagnose pancreatic cancers using urine biomarkers

Study	Classifier	Recall	Precision	Specificity	F1-score	AUC	Accuracy
ALPU et al. [41]	LR	0.64	0.89	-	0.74	0.77	0.76
Debernardi et al. [19]	LR	0.83	-	96.2	-	0.92	-
Blyuss et al. [40]	NN, RF, SVM, LR	0.81	-	0.90	-	0.94	-
Laxminarayanamma et al. [42]	CNN	0.96	0.96	-	0.96	0.97	0.95
Developed 1D CNN-LSTM		0.96	0.97	0.98	0.97	0.98	0.97^a

^aBest performance value is indicated in bold. Abbreviations are already defined in the context

ISSN: 1754-1611