External validation of the Bayesian Estimated Tools for Survival (BETS) models in patients with surgically treated skeletal metastases

Table 2 Comparison of continuous features between the training and validation sets

Feature		Training set (n = 189)	Validation set (n = 815)	% Missing data from validation set	P
Age at surgery (years)^‡	Mean	62.4	66.3	0	0.0002*
	SD	13.7	12.8
	Median	62.7	67.0
	IQR	54.4, 72.2	58.0, 76.0
Hemoglobin concentration (mg/dL)^†‡	Mean	11.5	11.5	0.6	1.0
	SD	1.9	3.5
	Median	11.4	11.3
	IQR	10.1, 12.9	10.3, 12.6
Absolute lymphocyte count (K/μL)^†‡	Mean	1.2	1.2	83.8	0.48
	SD	1.3	0.74
	Median	1.0	1.2
	IQR	0.6, 1.5	0.8, 1.6
Senior surgeon’s estimate of survival (months)^†‡	Mean	10.3	N/A	100	N/A
	SD	8.6
	Median	6.0
	IQR	4.0, 12.0

SD=standard deviation; IQR=interquartile range; N/A=not applicable.
^*Distributions are significantly different between training and validation sets by two-tailed Student’s t-test.
^†Denotes feature of 3-month model.
^‡Denotes feature of 12-month model.

ISSN: 1471-2407