Evaluating resources composing the PheMAP knowledge
Presenter
Manager
Moderator
Watch the Recording
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.
Learning Objectives
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