Predicting students’ academic progress and related attributes in first-year medical students: an analysis with artificial neural networks and Naïve Bayes

Table 3 Results obtained from the models for both classes (regular and irregular students). N = 7,066 from 2011 to 2017 cohorts, UNAM Faculty of Medicine, Mexico

Target groups	Model	Accuracy	Sensitivity	Specificity	PPV	NPV
Irregularity	Neural networks (ANN)	0.74	0.72	0.75	0.79	0.68
Irregularity	Naïve Bayes	0.71	0.72	0.70	0.70	0.72
Regularity	Neural networks (ANN)	0.73	0.75	0.72	0.67	0.79
Regularity	Naïve Bayes	0.71	0.70	0.72	0.72	0.70

ISSN: 1472-6920