Article
Natural language processing to build a computable phenotype library for adults with congenital heart disease.
International journal of medical informatics - 15 Nov 2026
Thomas Spencer, Dawson Angus, Chaudhry Hifsa, Ahmad Sidra, Ding Xiyu, Hummel Sarah A, Leone David M, Vanam Rohith, Weingarten Angela J, Farber-Eger Eric, Shaffer Lauren Lee, Frischhertz Benjamin P, Clemmons Sydney St, Ghelani Sunil J, Reyes Fernando Baraona, Wu Tzu-Chun, Wu Danny T Y, Opotowsky Alexander R, Miller Timothy A
Abstract excerpt
OBJECTIVE: Our objective was to build classifiers for multiple phenotypes that categorize a cohort of adults with congenital heart disease (ACHD), that can be used to populate variables in a biobank. MATERIALS AND METHODS: A dataset of 1492 ACHD patients, with expert-created labels for eight phenotypes, was created and used to train classifiers with three different architectures. A larger unlabeled dataset...
Read the complete abstract on PubMedTopics
- Humans
- Heart Defects, Congenital
- Phenotype
- Natural Language Processing