Combining human and machine intelligence for clinical trial eligibility querying
Co-author Chunhua Weng discusses this month JAMIA Journal Club selection:
Fang Y, Idnay B, Sun Y, Liu H, et al. Combining human and machine intelligence for clinical trial eligibility querying [published online ahead of print, 2022 April 15]. J Am Med Inform Assoc. 2022;ocac051. doi:10.1093/jamia/ocac051
Watch the Recording
Dr. Chunhua Weng, (she/her), is a Professor of Biomedical Informatics at Columbia University and an elected fellow of both the American College of Medical Informatics (ACMI) and International Academy of Health Sciences Informatics (IAHSI). She has been co-leading the Biomedical Informatics Resource for the Columbia CTSA (The Irving Institute for Clinical and Translational Science) since 2011. She is also an Associate Editor for the Journal of Biomedical Informatics. Dr. Weng holds a PhD in Biomedical and Health Informatics from the University of Washington at Seattle. As an active researcher in the field of Clinical Research Informatics since 2000, Dr. Weng does research on EHR data-driven optimization of clinical trial eligibility criteria, deep phenotyping for rare genetic disorders, EHR data quality assessment and data analytics, and text knowledge engineering using a variety of text (e.g., EHR narratives, PubMed abstracts and clinical trial summaries).
JAMIA Journal Club managers and monthly moderators are JAMIA Student Editorial Board members:
Statement of Purpose
Recruitment is a major barrier to clinical research. Various technologies have been developed to leverage the rich electronic health records data to facilitate electronic screening of patients for clinical research recruitment. However, many of the existing solutions are designed for IT professionals to use, which entail extra costs for institutions and researchers and extra work for researchers to work with IT to complete the e-screening tasks. In our research with Criteria2Query, our goal is to engage clinical researchers and incorporate their valuable experience in chart review and eligibility determination into the e-screening process. They know how to prioritize and simplify eligibility criteria text and how to select reliable data types or data sources from the noisy and heterogeneous EHR data for screening. Criteria2Query 2.0 is designed to combine machine and human intelligence seamlessly to complete the e-screening task efficiently and accurately. In this presentation, we will describe the design and preliminary evaluation of this system.
The target audience for this activity is professionals and students interested in health informatics.
After participating in this webinar the listener should be better able to:
- Understand the unmet user needs and the technology gap for electronic screening for clinical research
- Appreciate the fundamental theorem of informatics for user augmentation, or the new definition of AI (Augmented Intelligence)
- Explore the technical feasibility of combining machine and human intelligence for improving e-screening accuracy and efficiency while minimizing the cost of hiring "the middle man"
- 35-minute presentation by article author(s) considering salient features of the published study and its potential impact on practice
- 25-minute discussion of questions submitted by learners via the webinar tools and moderated by JAMIA Student Editorial Board members.
The American Medical Informatics Association is accredited by the Accreditation Council for Continuing Medical Education to provide continuing medical education for physicians.
No commercial support was received for this activity.
Disclosures for this Activity
The following planners and staff who are in a position to control the content of this activity disclose that they have no financial relationships with commercial interests/ineligible entities:
Presenter: Chunhua Weng, PhD
JAMIA Journal Club Planners: Harry Reyes Nieva; Kirk Roberts; Jiancheng Ye
AMIA Staff: Susanne Arnold