Session Summary
Obtaining computed phenotypes, Implementation of Natural Language Processing (NLP) and the use of learning algorithms with applications for directing the phenotyping workflow are discussed during this session.
Presenters (4)
Victor Castro
Corporate Team Lead II
Partners HealthCare
James Cimino, MD
Director, Informatics Institute
University of Alabama at Birmingham
Vivian Gainer
Corporate Manager
Partners HealthCare
Ken Mandl, MD, MPH
Director, Computational Health Informatics Program
Boston Children's Hospital
Professor of Biomedical Informatics
Harvard Medical School
Presentations (3)
Presentation 1: High-throughput Population Phenotyping
Presenter(s): Victor Castro and Vivian Gainer
- High-quality computed phenotype
- Partners Biobank
- Phenotyping the biobank population
- High-throughput phenotype training
Presentation 2: i2b2 Development at UAB (UABi2b2)
Presenter(s): James Cimino, MD
- Automatic IRB approval for limited data sets
- UAB Learning System
- i2b2 incremental updates
- Infobuttons for i2b2 (i3b3 plug-in)
Presentation 3: Data Fusion in Phenotypes EHR, Registry, PRO
Presenter(s): Ken Mandl, MD, MPH
- More common phenotypes in Non-Registry
- More common phenotypes in Registry
- C3-PRO: Connecting ResearchKit to the Health System Using i2b2 and FHIR