Fig. 1: Flowchart of model population enrollment. | npj Digital Medicine

Fig. 1: Flowchart of model population enrollment.

From: Interpretable machine learning model for digital lung cancer prescreening in Chinese populations with missing data

Fig. 1

The figure illustrates the inclusion process for the training set, internal validation set, time-based external validation set, and geography-based external validation set. Samples from the Cheeloo LEAD database, spanning January 1, 2015, to October 31, 2017, were included in the training and internal validation sets, while data from January 1, 2018, – October 31, 2020, were used for the time-based external validation set. The geography-based external validation set was sourced from the Boxing database.

Back to article page