ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Leveraging SNOMED CT for patient cohort identification over heterogeneous EHR data | JoVE Visualize

Home
Research Domains
Information And Computing Sciences

Leveraging SNOMED CT for patient cohort identification over heterogeneous EHR data

Xubing Hao¹, Yan Huang¹, Licong Cui¹

¹McWilliams School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX.

AMIA Joint Summits on Translational Science Proceedings. AMIA Joint Summits on Translational Science|June 12, 2025

Related Experiment Videos

View abstract on PubMed

Summary

This study developed a SNOMED CT query system for COVID-19 patient data. While promising for cohort identification, challenges with false positives require careful attention.

Area of Science:

Medical Informatics
Health Data Standardization
Clinical Terminology

Background:

Standardizing diverse patient data is crucial for cohort identification.
SNOMED CT offers benefits and challenges in data standardization.
Electronic Health Records (EHR) contain valuable patient information.

Purpose of the Study:

To develop and evaluate a SNOMED CT-driven cohort query system.
To assess the utility of SNOMED CT for querying COVID-19 EHR data.
To identify benefits and challenges of SNOMED CT in cohort queries.

Main Methods:

Developed a SNOMED CT-driven query system using Optum de-identified COVID-19 EHR data.
Utilized concept mappings between ICD-9-CM/ICD-10-CM and SNOMED CT.
Evaluated query performance against ICD-9-CM and ICD-10-CM baselines.

Main Results:

Manual review of 80 cases identified 148 true positive codes and 63 false positive codes.
Issues were found in SNOMED CT code naming, mappings, and hierarchical relations.
The system demonstrated potential but included false positives.

Conclusions:

SNOMED CT-driven cohort query systems show promise for comprehensive patient data analysis.
Challenges with false positives necessitate careful validation and refinement.
Addressing issues in code naming, mapping, and hierarchy is essential for optimal performance.

Related Experiment Videos

Related Concept Videos

Data Management And Data Science

Query Processing And Optimisation

Leveraging Snomed Ct For Patient Cohort Identification Over Heterogeneous Ehr Data