Table 1.

Areas of phenotypes identified

Area Name	Area#	#Distinct phrases	#Clusters identified	Avg Similar Phrases Cluster Size	% Phrases clustered in area
Syndrome names	1	4,801	278	3.45	19.9
Abdomen/gi	2	707	33	2.3	10.1
Respiratory	3	546	39	2.17	15.6
Gu/renal	4	985	44	2.25	10.0
Gu/genitalia	5	975	44	2.25	10.0
Cardiovascular	6	808	38	2.13	10.0
Muscle	7	1143	68	2.98	17.8
Endo	8	344	16	2.25	10.4
Neuro	9	4.721	247	2.68	14.0
Oncology	10	891	21	2.62	6.17
Heme	11	576	16	2.75	7.6
Immune	12	542	19	2.05	7.2
Eyes	13	2,265	152	2.5	16.8
Face	14	3,927	283	2.56	18.4
Teeth	15	3,542	258	2.48	18.1
Neck	16	3,490	252	2.49	17.9
Head	17	4,196	281	2.51	16.8
Limb	18	4,522	283	3.15	19.7
Skel	19	3,936	247	3.02	18.9
Chest	20	4,307	273	3.03	19.2
Growth	21	497	37	4.24	31.6
Nails	22	1,617	106	2.41	15.8
Skin	23	2,098	140	2.42	16.2
Hair	24	1,701	116	2.41	16.5
Lab	25	3,553	106	2.9	8.6
Misc	26	4,021	Was not clustered