Probability calibration-based prediction of recurrence rate in patients with diffuse large B-cell lymphoma

Table 3 Performance of the 5 traditional machine learning algorithms

	AUC	ECE	MCE	BS	P_value
NB	0.760 (0.741–0.783)	15.711 (13.557–17.914)	34.350 (29.275–39.800)	0.212 (0.199–0.228)	< 0.001(< 0.001- < 0.001)
LR	0.758 (0.733–0.779)	8.517 (7.244–10.093)	20.100 (16.675–25.025)	0.188 (0.180–0.196)	0.152 (0.022–0.403)
RF	0.757 (0.739–0.776)	12.740 (10.910–14.336)	27.200 (23.375–31.925)	0.201 (0.190–0.211)	< 0.001(< 0.001- < 0.001)
SVM	0.748 (0.724–0.771)	9.872 (8.317–11.777)	23.800 (19.000–28.925)	0.194 (0.185–0.204)	0.016(< 0.001–0.117)
FFNN	0.767 (0.747–0.787)	8.238 (6.805–9.611)	20.150 (16.600–24.500)	0.184 (0.177–0.192)	0.244 (0.075–0.518)

NB naïve Bayes, LR logistic regression, RF random forest, SVM support vector machine, FFNN feedforward neural network. In each cell M (P₂₅ - P₇₅): M is the median, P₂₅ is the 25th percentile and P₇₅ is the 75th percentile of 500 evaluations. The best performance in each column is in bold; The secondary best performance in each column is underlined

ISSN: 1756-0381