Open AccessPhenotyping issues for exploring electronic health records to design clinical trials
Author(s) -
Jill Schnall,
Lingjiao Zhang,
Jinbo Chen
Publication year - 2020
Publication title -
clinical trials
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.559
H-Index - 63
eISSN - 1740-7753
pISSN - 1740-7745
DOI - 10.1177/1740774520931039
Subject(s) - health records , electronic health record , context (archaeology) , gold standard (test) , clinical trial , medical record , computer science , electronic records , data science , medicine , data mining , health care , world wide web , pathology , paleontology , radiology , economics , biology , economic growth
For utilizing electronic health records to help design and conduct clinical trials, an essential first step is to select eligible patients from electronic health records, that is, electronic health record phenotyping. We present two novel statistical methods that can be used in the context of electronic health record phenotyping. One mitigates the requirement for gold-standard control patients in developing phenotyping algorithms, and the other effectively corrects for bias in downstream analysis introduced by study samples contaminated by ineligible subjects.