Early recognition of multiple sclerosis using natural language processing of the electronic health record

Table 1 Two cohorts used for MS classification study

Cohort	Purpose	Unique Patients
MS-enriched	Identify predictive attributes, develop a classification model, and determine the achievability of early recognition	MS	165
MS-enriched		Controls	545
Random sample	Identify patients with unrecognized MS	MS	16
Random sample	Identify patients with unrecognized MS	Controls	2273

ISSN: 1472-6947