Format

Send to

Choose Destination
J Am Med Inform Assoc. 2016 Nov;23(6):1166-1173. doi: 10.1093/jamia/ocw028. Epub 2016 May 12.

Learning statistical models of phenotypes using noisy labeled training data.

Author information

1
Biomedical Informatics Training Program, Stanford University, Stanford CA 94305-5479, USA vibhua@stanford.edu.
2
Biomedical Informatics Training Program, Stanford University, Stanford CA 94305-5479, USA.
3
Stanford Center for Biomedical Informatics Research, Stanford University, Stanford CA 94305-5479, USA.
4
Department of Pediatrics, Stanford University School of Medicine, Stanford CA 94305-5208, USA.
5
Department of Clinical Informatics, Stanford Children's Health, Stanford CA 94305-5474, USA.
6
Division of General Medical Disciplines, Stanford University, Stanford CA 94305, USA.
7
Faculty of Medicine, University of Calgary, Calgary Alberta, T2N 4N1, Canada.
8
Department of Surgery, Stanford Hospital & Clinics, Stanford CA 94305-2200, USA.
9
Division of Vascular Surgery, Stanford Hospital & Clinics, Stanford CA 94305-5642, USA.

Abstract

OBJECTIVE:

Traditionally, patient groups with a phenotype are selected through rule-based definitions whose creation and validation are time-consuming. Machine learning approaches to electronic phenotyping are limited by the paucity of labeled training datasets. We demonstrate the feasibility of utilizing semi-automatically labeled training sets to create phenotype models via machine learning, using a comprehensive representation of the patient medical record.

METHODS:

We use a list of keywords specific to the phenotype of interest to generate noisy labeled training data. We train L1 penalized logistic regression models for a chronic and an acute disease and evaluate the performance of the models against a gold standard.

RESULTS:

Our models for Type 2 diabetes mellitus and myocardial infarction achieve precision and accuracy of 0.90, 0.89, and 0.86, 0.89, respectively. Local implementations of the previously validated rule-based definitions for Type 2 diabetes mellitus and myocardial infarction achieve precision and accuracy of 0.96, 0.92 and 0.84, 0.87, respectively.We have demonstrated feasibility of learning phenotype models using imperfectly labeled data for a chronic and acute phenotype. Further research in feature engineering and in specification of the keyword list can improve the performance of the models and the scalability of the approach.

CONCLUSIONS:

Our method provides an alternative to manual labeling for creating training sets for statistical models of phenotypes. Such an approach can accelerate research with large observational healthcare datasets and may also be used to create local phenotype models.

KEYWORDS:

Electronic health record; high throughput; machine learning; noisy labels; phenotyping

PMID:
27174893
PMCID:
PMC5070523
DOI:
10.1093/jamia/ocw028
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Silverchair Information Systems Icon for PubMed Central
Loading ...
Support Center