Evaluating resources composing the PheMAP knowledge base to enhance high-throughput phenotyping
Lead author Nicholas Wan discusses this month's JAMIA journal club selection:
Wan N, Yaqoob A, Ong H, Zhao J, Wei W. Evaluating resources composing the PheMAP knowledge base to enhance high-throughput phenotyping. J Am Med Inform Assoc. 2023;ocac234. doi:10.1093/jamia/ocac234
Watch the Recording
Nicholas Wan is a third-year biomedical engineering student at Vanderbilt University. He currently works in Wei Lab through Vanderbilt University Medical Center where he does research pertaining to natural language processing, phenotyping, and phenome-wide association studies. Nick is from Aurora, IL and is currently on track to apply to medical school in the upcoming cycle.
Statement of Purpose
Phenotyping and related algorithm design using electronic health record (EHR) data can be challenging and time-consuming. The PheMAP knowledge base was created to streamline the phenotyping process in EHR data. PheMAP is a knowledge base of medical concepts with quantified relationships to phenotypes that have been extracted by natural language processing from five independent, publicly available online resources like MedlinePlus and Wikipedia. We have previously demonstrated that PheMAP achieved comparable performance with algorithms generated by domain experts.
In this study we aimed to identify methods of improving the phenotyping process and explore whether specific individual online resources were more beneficial than others. Our article
“Evaluating resources composing the PheMAP knowledge base to enhance high-throughput phenotyping” visualizes the composition of the individual online resources that comprise the previously created PheMAP knowledge base and details how the resources perform independently compared to the original implementation with regards to phenotyping. This research sought to determine how to leverage diverse resources for accurate and effective phenotyping. Our findings reveal an ensemble approach that increases the efficacy of the original PheMAP implementation in high-throughput phenotyping. Our findings provide further insight into high-throughput phenotyping utilizing natural language processing.
The target audience for this activity is professionals and students interested in health informatics.
After participating in the webinar, attendees should be able to:
- Describe the process flow of the PheMAP knowledge base and how it can be applied in EHR
- Identify methods for comparing the utility of public online resources in phenotyping prediction
- Contrast different methods of leveraging disparate resources for implementation within the PheMAP knowledge base
- Discuss future directions for PheMAP and high-throughput phenotyping
- 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 listeners 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.
Credit Designation Statement
The American Medical Informatics Association designates this live activity for a maximum of 1.0 AMA PRA Category 1 Credits™. Physicians should claim only the credit commensurate with the extent of their participation in the activity.
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: Nicholas Wan
JAMIA Journal Club Planners: Lu He; Sanya Taneja; Kirk Roberts
AMIA Staff: Susanne Arnold