Table 2.

Distribution of cases and non-cases in testing and training data sets.

Data Set	# of Patients	# Cases	# Non-cases	# Clinical notes	# Sentences with CRC concepts	# ICD-9 codes	# CPT codes
Training Set	150	63	87	35727	1879	49	19
Test Set	150	58	92	34093	1099	39	10
All	300	121	179	69820	2978	88	29