Skip Navigation

CANCELED - Bridging the Semantic Gap between Research Eligibility Criteria and Clinical Data: Methods and IssuesNIH Only

Air date: Wednesday, March 6, 2013, 2:00:00 PM
Time displayed is Eastern Time, Washington DC Local
Description: NLM Lecture Series

Central to clinical and translational research activities, clinical research eligibility criteria are perceived, defined, interpreted, and implemented by various stakeholders in a series of translations. They are initially authored by investigators to define target research populations. Then they are interpreted by research volunteers seeking experimental therapies for self-screening, translated and implemented by clinical database query analysts as database queries for electronic screening, referenced by research coordinators for manual patient screening, summarized in meta-analyses by scientists for developing clinical practice guidelines, and eventually interpreted by physicians to screen patients for evidence-based care. As a result, their intended meanings often get distorted, as in the game of “telephone”, and lead to misinterpretation of clinical research results.

With the burgeoning adoption of electronic health records (EHRs), vast amounts of clinical data are increasingly available for computational reuse. It is imperative that the scientific community leverage these data to accelerate clinical and translational science at low cost and large scale. A critical step toward this goal is cohort identification by matching clinical data to research eligibility criteria. However, this task is complicated by the semantic gap between the raw clinical data and free-text human-provided eligibility criteria: each criterion has many ways to describe it and a myriad of clinical data points that represent it.

Dr. Weng will describe the evolving understanding of the semantic gap and approaches to overcoming it in the context of EHR-based phenotyping and clinical trial prescreening. She will present considerations for augmenting domain experts in interrogating large clinical databases as part of their current efforts and the need for data-driven phenotype modeling and summarization as their potential future directions.

Dr. Chunhua Weng is the Florence Irving Assistant Professor of Biomedical Informatics at Columbia University, where she has been a faculty member since 2007. Before arriving at Columbia, she obtained an undergraduate degree in computer science with a focus on software engineering from Nankai University, P. R. China, a master’s degree in Information and Computer Science from University of California at Irvine, and a Ph.D. in Biomedical and Health Informatics from University of Washington at Seattle. Her research theme is developing human-computer collaborative approaches to help clinical researchers make the best use of health information technology. Her current research is focused on problems that include interactive query formulation to assist clinical researchers in interrogating large clinical databases.
Author: Chunhua Weng, Ph.D., Columbia University
Runtime: 1 hour