Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Identifying UMLS concepts from ECG Impressions using KnowledgeMap.

Joshua C Denny1, Anderson Spickard, Randolph A Miller

  • 1Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN, USA.

AMIA ... Annual Symposium Proceedings. AMIA Symposium
|June 17, 2006
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Clinical care site data integration reveals heterogeneity in EHR phenotyping and healthcare utilization patterns.

medRxiv : the preprint server for health sciences·2026
Same author

An EHR-based framework for modeling growth curves and constructing growth centile charts for genetic disorders.

NPJ genomic medicine·2026
Same author

Colocalization of eQTLs With Type 2 Diabetes and Glycemic Traits Using Whole-Genome Sequences in Diverse Populations From the NHLBI Trans-Omics in Precision Medicine (TOPMed) Program.

Diabetes·2026
Same author

CYP2D6 phenotype and post-surgical pain control with hydrocodone and oxycodone.

Frontiers in pharmacology·2026
Same author

Integrating genetically predicted transcriptomic signatures with longitudinal real-world data enables scalable drug repurposing for Alzheimer's disease.

Research square·2026
Same author

Gene-gene interactions between a LMNA variant and common polymorphisms drive early-onset atrial fibrillation.

Nature communications·2026
Same journal

Sensitivity Analyses of a Scoring System for a Contraception Decision Aid.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2026
Same journal

Improving electronic health record processing of large language models via retrieval-augmented generation: A case study on dietary supplements.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2026
Same journal

Developing a User-Centered Mobile Application Prototype: Bridging Lower-Limb Fracture Care from Skilled Nursing Facility and Back to the Community.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2026
Same journal

KERAP: A Knowledge-Enhanced Reasoning Approach for Accurate Zero-shot Diagnosis Prediction Using Multi-agent LLMs.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2026
Same journal

Automating Adjudication of Cardiovascular Events Using Large Language Models.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2026
Same journal

Predictive Factors and State-Level Barriers to Postpartum Birth Control Usage in the United States: Insights from PRAMS Phase 8.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2026
See all related articles

The Knowledge Map Concept Identifier (KMCI) effectively extracts medical information from electrocardiogram (ECG) reports. This tool accurately maps ECG impressions to Unified Medical Language System (UMLS) concepts, aiding decision support and drug discovery.

Area of Science:

  • Medical Informatics
  • Clinical Data Analysis
  • Biomedical Natural Language Processing

Background:

  • Electrocardiogram (ECG) reports contain valuable clinical data often locked in free text.
  • Automated methods struggle to access the rich information within unstructured ECG impression sections.
  • Decision support and drug-effect discovery are hindered by the inaccessibility of this data.

Purpose of the Study:

  • To evaluate the efficacy of the Knowledge Map Concept Identifier (KMCI) in mapping ECG impressions to Unified Medical Language System (UMLS) concepts.
  • To assess the accuracy and recall of KMCI in extracting structured medical information from ECG reports.
  • To determine KMCI's potential for improving automated analysis of ECG data.

Main Methods:

  • ECG impressions were processed using the KMCI tool.

Related Experiment Videos

  • Multiple human raters evaluated the accuracy of KMCI-identified concepts.
  • Unidentified concepts were logged by reviewers.
  • Metrics such as recall and precision were calculated to quantify performance.

    • Main Results:

    • KMCI achieved a recall of 0.90, correctly identifying 1059 out of 1171 concepts.
    • The precision of KMCI was 0.94, indicating a high proportion of correctly identified concepts.
    • KMCI demonstrated exceptional performance in identifying ECG rhythms (0.99 recall), perfusion changes (0.98 recall), and noncardiac medical concepts (1.00 recall).

    Conclusions:

    • KMCI proves to be an effective tool for mapping free-text ECG impressions to standardized UMLS concepts.
    • The high accuracy and recall suggest KMCI can significantly enhance the automated extraction of clinical insights from ECG reports.
    • This method holds promise for advancing automated decision support and drug-effect discovery using ECG data.