Relational machine learning for electronic health record-driven phenotyping

• Published in: Journal of biomedical informatics Vol. 52; pp. 260 - 270
• Main Authors: Peissig, Peggy L., Santos Costa, Vitor, Caldwell, Michael D., Rottscheit, Carla, Berg, Richard L., Mendonca, Eneida A., Page, David
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.12.2014
• Subjects: Algorithms; Artificial Intelligence; Classification; Data Mining - methods; Databases, Factual; Electronic health record; Electronic health records; Electronic Health Records - classification; Electronics; Humans; Inductive logic programming; Learning; Machine learning; Medical; Patients; Phenotyping; Relational machine learning; Training; Electronic health record; Inductive logic programming; Relational machine learning; Machine learning; Phenotyping

[Display omitted] •We compared ILP to propositional machine learning approaches for EHR phenotyping.•Training subject selection for machine learning was automated using ICD-9 codes.•ILP out-performed propositional machine learning approaches in AUROC.•Relational learning using ILP offers a viable ap...