Paper: Exploring Label Dependency in Active Learning for Phenotype Mapping

ACL ID W12-2418
Title Exploring Label Dependency in Active Learning for Phenotype Mapping
Venue Workshop on Biomedical Natural Language Processing
Session
Year 2012
Authors

Many genetic epidemiological studies of hu- man diseases have multiple variables related to any given phenotype, resulting from dif- ferent definitions and multiple measurements or subsets of data. Manually mapping and harmonizing these phenotypes is a time- consuming process that may still miss the most appropriate variables. Previously, a su- pervised learning algorithm was proposed for this problem. That algorithm learns to de- termine whether a pair of phenotypes is in the same class. Though that algorithm ac- complished satisfying F-scores, the need to manually label training examples becomes a bottleneck to improve its coverage. Herein we present a novel active learning solution to solve this challenging phenotype-mapping problem. Active learning will make pheno- type mapping more ef...