Table 5. Comparison of genetic versus non-genetic model for 10% weight gain prediction at one year after transplantation.

		AUROC [95% CI]	Specificity	Sensitivity	Accuracy	LRT-p	IDI [95% CI]*	NNG
Sample A	SNP group#1
	non genetic model	0.66 [0.58–0.72]	0.59	0.66	0.61	0.0004	0.08 [0.06–0.10]	24
	genetic model	0.74 [0.70–0.83]	0.61	0.77	0.65
	SNP group#2
	non genetic model	0.66 [0.54–0.69]	0.65	0.62	0.64	0.008	0.17 [0.14–0.20]	13
	genetic model	0.80 [0.71–0.84]	0.70	0.77	0.72
Sample B	SNP group#1
	non genetic model	0.67 [0.61–0.88]	0.55	0.76	0.63	0.04	0.36 [0.28–0.45]	6
	genetic model	0.89 [0.79–0.97]	0.78	0.88	0.81

AUROC: Area Under the Receiver Operating Characteristic Curve

IDI: Integrated Discrimination Improvement

NNG: Number Needed to Genotype

LRT: Likelihood Ratio tests

SNP: Single Nucleotide Polymorphism

CI: Confidence Interval

*p-value < 0.01