Mathematical models of amino acid panel for assisting diagnosis of children acute leukemia

Table 5 The true positive and negative prediction performance of morphology and XGBoost model in Group B

	Diagnosis (model/clinical diagnosis)				Kappa value	p value	AUC^e
	+/+^a	∓^b	±^c	−/−^d	Kappa value	p value	AUC^e
M	268	12	86	222	0.670	< 0.001	0.742
X	252	28	34	274	0.789	0.720	0.830
M + X	262	18	26	282	0.850	0.523	0.872

McNemar’s test
M: morphology; X: XGBoost model; AUC: area under curve
^aOur model or clinical diagnosis were both positive-children were with leukemia
^bOur model diagnosed children as normal, but the clinical diagnosis of them was leukemia
^cOur model diagnosed children as leukemia, but the clinical diagnosis of them was normal
^dOur model or clinical diagnosis were both negative, and children were normal
^eROC analysis

ISSN: 1479-5876