Skip to main content
. Author manuscript; available in PMC: 2017 Sep 1.
Published in final edited form as: Artif Intell Med. 2016 Jul 27;72:42–55. doi: 10.1016/j.artmed.2016.07.001

Figure 3.

Figure 3

The training and testing sets’ random selection process of cases from the NLST dataset. The training and test set consist of 200 cancer and 200 non-cancer cases, respectively. Ten random training and test sets, with replacement, were selected for our analysis.