Rxivist logo

Comparative Effectiveness of Knowledge Graphs- and EHR Data-Based Medical Concept Embedding for Phenotyping

By Junghwan Lee, Cong Liu, Jae Hyun Kim, Alex Butler, Ning Shang, Chao Pang, Karthik Natarajan, Patrick Ryan, Casey Ta, Chunhua Weng

Posted 17 Jul 2020
medRxiv DOI: 10.1101/2020.07.14.20151274

ObjectiveFeature engineering is a major bottleneck in phenotyping. Properly learned medical concept embeddings (MCEs) have the semantics of medical concepts, thus useful for retrieving relevant medical features in phenotyping tasks. We compared the effectiveness of MCEs learned from knowledge graphs and electronic healthcare records (EHR) data in retrieving relevant medical features for phenotyping tasks. Materials and MethodsWe implemented five embedding methods including node2vec, singular value decomposition (SVD), LINE, skip-gram, and GloVe with two data sources: (1) knowledge-graphs obtained from the Observational Medical Outcomes Partnership (OMOP) common data model; and (2) patient level data obtained from the OMOP compatible electronic health records (EHR) from Columbia University Irving Medical Center (CUIMC). We used phenotypes with their relevant concepts developed and validated by the Electronic Medical Records and Genomics (eMERGE) network to evaluate the performance of learned MCEs in retrieving phenotype-relevant concepts. Hits@k% in retrieving phenotype-relevant concepts based on a single and multiple seed concept(s) was used to evaluate MCEs. ResultsAmong all MCEs, MCEs learned by using node2vec with knowledge graphs showed the best performance. Of MCEs based on knowledge graphs and EHR data, MCEs learned by using node2vec with knowledge graphs and MCEs learned by using GloVe with EHR outperforms other MCEs respectively. ConclusionMedical concept embedding enables scalable feature engineering tasks, thereby facilitating high-throughput phenotyping. Knowledge graphs constructed by hierarchical relationships among medical concepts learn more effective MCEs, highlighting the need of more sophisticated use of big data to leverage EHR for phenotyping.

Download data

  • Downloaded 697 times
  • Download rankings, all-time:
    • Site-wide: 39,469
    • In health informatics: 153
  • Year to date:
    • Site-wide: 20,482
  • Since beginning of last month:
    • Site-wide: 28,937

Altmetric data


Downloads over time

Distribution of downloads per paper, site-wide


PanLingua

News