Artificial neural network classifier predicts neuroblastoma patients’ outcome

BMC Bioinformatics

Table 2 NB patients classification by different risk factors

	Performance^a
Predictor	Accuracy^b	Sensitivity^c	Precision^d	Specificity^e	NPV^f	MCC^g	F1-score^h
NB-hypo classifier (Good vs Poor)	87 %	90 %	91 %	78 %	75 %	67 %	90 %
Age at diagnosis (< 1 year vs ≥ 1 year)	72 %	61 %	100 %	100 %	50 %	55 %	76 %
INSS stage (1,2,3,4s vs 4)	76 %	75 %	90 %	78 %	55 %	78 %	82 %
MYCN status (normal vs amplified)	84 %	97 %	84 %	52 %	86 %	58 %	90 %

^aPerformance of NB-hypo classifier and other commonly used neuroblastoma risk factors in the test set
For prediction of prognosis by age at diagnosis, patients older than one year were predicted with poor prognosis. For prediction by stage, patients with stage 1,2,3, and 4s were predicted with good prognosis and patients with stage 4 were predicted with poor prognosis. For prediction by MYCN status, patients with amplified MYCN were predicted with poor prognosis while patients without MYCN amplification were predicted with good prognosis
^bAccuracy measures the proportion of correctly classified patients
^cSensitivity measures the proportion of good outcome patients correctly classified as such
^dPrecision measures the proportion of correctly classified good outcome patients
^eSpecificity measures the proportion of poor outcome patients correctly classified as such
^fNPV(Negative Predictive Value) measures the proportion of correctly classified poor outcome patients
^gMCC (Matthew's correlation coefficient) measures the correlation between a classifier prediction and the observed outcomes
^hF1-score measures the weighted average of the precision and sensitivity

ISSN: 1471-2105