Format

Send to

Choose Destination
J Biomed Inform. 2019 Mar;91:103122. doi: 10.1016/j.jbi.2019.103122. Epub 2019 Feb 7.

Feature extraction for phenotyping from semantic and knowledge resources.

Author information

1
Department of Industrial Engineering, Tsinghua University, Beijing, China.
2
Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA.
3
Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA.
4
Computational Health Informatics Program, Boston Children's Hospital, Boston, MA, USA; Department of Anesthesiology, Critical Care, and Pain Medicine, Boston Children's Hospital, Boston, MA, USA; Department of Anesthesia, Harvard Medical School, Boston, MA, USA.
5
Department of Medicine, Division of Rheumatology, Immunology and Allergy, Brigham and Women's Hospital, Boston, MA, USA; Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA.
6
Department of Cardiology, Boston Children's Hospital, Boston, MA, USA; Department of Pediatrics, Harvard Medical School, Boston, MA, USA.
7
Computational Health Informatics Program, Boston Children's Hospital, Boston, MA, USA; Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA.
8
Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA; Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA.
9
Center for Statistical Science, Tsinghua University, Beijing, China; Department of Industrial Engineering, Tsinghua University, Beijing, China; Institute for Data Science, Tsinghua University, Beijing, China. Electronic address: syu@tsinghua.edu.cn.

Abstract

OBJECTIVE:

Phenotyping algorithms can efficiently and accurately identify patients with a specific disease phenotype and construct electronic health records (EHR)-based cohorts for subsequent clinical or genomic studies. Previous studies have introduced unsupervised EHR-based feature selection methods that yielded algorithms with high accuracy. However, those selection methods still require expert intervention to tweak the parameter settings according to the EHR data distribution for each phenotype. To further accelerate the development of phenotyping algorithms, we propose a fully automated and robust unsupervised feature selection method that leverages only publicly available medical knowledge sources, instead of EHR data.

METHODS:

SEmantics-Driven Feature Extraction (SEDFE) collects medical concepts from online knowledge sources as candidate features and gives them vector-form distributional semantic representations derived with neural word embedding and the Unified Medical Language System Metathesaurus. A number of features that are semantically closest and that sufficiently characterize the target phenotype are determined by a linear decomposition criterion and are selected for the final classification algorithm.

RESULTS:

SEDFE was compared with the EHR-based SAFE algorithm and domain experts on feature selection for the classification of five phenotypes including coronary artery disease, rheumatoid arthritis, Crohn's disease, ulcerative colitis, and pediatric pulmonary arterial hypertension using both supervised and unsupervised approaches. Algorithms yielded by SEDFE achieved comparable accuracy to those yielded by SAFE and expert-curated features. SEDFE is also robust to the input semantic vectors.

CONCLUSION:

SEDFE attains satisfying performance in unsupervised feature selection for EHR phenotyping. Both fully automated and EHR-independent, this method promises efficiency and accuracy in developing algorithms for high-throughput phenotyping.

KEYWORDS:

Distributional semantics; Electronic health records; Machine learning; Phenotyping

PMID:
30738949
PMCID:
PMC6424621
[Available on 2020-03-01]
DOI:
10.1016/j.jbi.2019.103122

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center