Formalizing eligibility criteria in a computer-interpretable language would facilitate eligibility determination of study subjects and the identification of studies on similar patient populations. Because formalizing eligibility criteria is extremely labor intensive, we developed a methodology to apply natural-language processing methods to partially automate the encoding of free-text criteria into a standardized, computable format called ERGO Annotation. We evaluated the methodology in three ways.
First, we assessed the extent to which ERGO Annotations capture the semantics of 1000 eligibility criteria randomly drawn from ClinicalTrials.gov. Second, we demonstrated the practicality of the encoding process in a feasibility study. Finally, we demonstrated the use of ERGO Annotation to (1) structure a library of eligibility criteria, (2) search for studies enrolling specified study populations, and (3) screen patients for potential eligibility for a study. We therefore demonstrate a new and practical method for incrementally capturing the semantics of free-text eligibility criteria into computable form.
