BMC Medical Informatics and Decision Making

Table 3 Performance comparison of classifiers. The values are expressed as average, except the values referring to the trained classifier. Abbreviations: AUC, Area Under the ROC Curve; Sens., Sensitivity. Spec., Specificity; NN, Neural Networks

From: Computer-aided autism diagnosis using visual attention models and eye-tracking: replication and improvement proposal

Dataset	Approach	AUC	F1-Score	Accuracy	Sens.	Precision	Spec.
Current	Trained (NN)	0.56	0.53	0.58	0.55	0.51	0.61
	Replication (NN)	0.71	0.55	0.66	0.62	0.56	0.73
	Random Forest	0.74	0.64	0.67	0.67	0.61	0.67
Previous	Reference (NN)^a	0.82	0.62	0.76	0.69	0.90	0.93
Previous	Random Forest	0.95	0.91	0.88	0.88	0.95	0.87

^a result described by Oliveira et al., 2021, added for comparison

Back to article page

ISSN: 1472-6947

Contact us

General enquiries: journalsubmissions@springernature.com