Table 1.

Neighbor terms to “colonoscopy” and similarity scores.

Terma	Similarity score	Rank
“suprep”	0.9722890	1
“peg”	0.9519246	2
“sutab”	0.9513488	3
“plenvu”	0.9504289	4
“glycol”	0.9498276	5
“miralax”	0.9449067	6
“rectal”	0.9435940	7
“cleanse”	0.9422708	8
“cologuard”	0.9421358	9
“colorectal”	0.9403084	10

^aNeighbor terms are terms with the most semantic similarity (with corresponding high similarity scores or low ranks) to “colonoscopy” based on YouTube video data. Score refers to the cosine similarity metric between word embeddings (ie, terms) in a multidimensional vector space.