The authors are commended for completing a very technically challenging study, including three-dimensional PET parametric imaging and arterial blood sampling validation with the ultra-short-lived tracers 82Rb and 15O-water.
Furthermore, the small sample size prevented a comprehensive split-sample validation with any strategy.
The model has demonstrated a high level of validation and accuracy when subjected to internal split-sample validation with separate training and validation data sets.
On cross-platform analysis we found discrepancies occurred almost exclusively at low variant allele frequencies (<13%), suggesting that in real-life clinical samples, validation with highly sensitive, multiplexed and unbiased methods such as NGS are feasible and appropriate (Hadd et al, 2013).
For large sample validation, we recruited 100 patients with coronary bifurcation lesion aged 45 88 years (average 67.8 ± 10.9 years) and 100 control patients with coronary nonbifurcation lesion aged 40 84 years (average 65.5 ± 10.2 years).
Their factor analysis with split-half sample validation was converted into nine dimensions [ 4].
Thirty-two of the 38 (84.2%) articles collected samples prospectively and six [53], [65], [66], [69], [74], [85] (15.8%) retrospectively; two [65], [75] (5.2%) articles reported the use of a randomly selected subset of the sample for validation with the reference standard.
After the creation of the multivariate logistic regression models from the SEER patient data set, model validation was performed using split-sample internal validation with separate training and validation data sets.
Exome sequencing and verification were performed for nine pairs of ESCC and the matched blood samples, followed by validation with additional samples using Sanger sequencing.
In both of these approaches, cross-validation is important and can be performed across different data sets if the populations are similar enoughor with split-sample validation methods applied to pooled samples when study populations differ.
