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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Point-of-care ultrasound in cardiovascular imaging: current status and future prospects.

Expert review of medical devices·2026
Same author

Cardiovascular Regulatory Science: Accelerating the Path from Bench to Bedside.

American heart journal·2026
Same author

Baseline ECG Outperforms the Angiogram for Predicting Mortality in COVID-19-Associated STEMI: Insights From the NACMI Registry.

Journal of the Society for Cardiovascular Angiography & Interventions·2026
Same author

A Wearable Infrared Sensor for Detecting Non-ST Segment Elevation Acute Coronary Syndromes.

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

Clinical outcomes and discharge disposition in nonagenarians with ST-elevation myocardial infarction.

American heart journal·2025
Same author

Reperfused Myocardial Infarction: The Road to CCS Classification of Acute MI and Beyond.

JACC. Advances·2025

Related Experiment Video

Updated: Oct 27, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.4K

Machine learning for holistic visualization of STEMI registry data.

Keshav R Nayak1, André Skupin2, Timothy Schempp2

  • 1Department of Cardiology, Scripps Mercy Hospital, San Diego, CA, United States.

Journal of Biomedical Informatics
|July 23, 2021
PubMed
Summary

This study uses data visualization and machine learning to map patient data for ST-Elevation Myocardial Infarction (STEMI), offering new insights into patient characteristics and outcomes. The novel approach refines data accuracy and guides future research in cardiovascular medicine.

Keywords:
Artificial neural networkData visualizationMachine learningSTEMI outcomesSelf-organizing maps

More Related Videos

3D Whole-heart Myocardial Tissue Analysis
06:53

3D Whole-heart Myocardial Tissue Analysis

Published on: April 12, 2017

9.0K
A Data-Driven Approach to Quantifying Immune States in Sepsis
07:42

A Data-Driven Approach to Quantifying Immune States in Sepsis

Published on: February 7, 2025

354

Related Experiment Videos

Last Updated: Oct 27, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.4K
3D Whole-heart Myocardial Tissue Analysis
06:53

3D Whole-heart Myocardial Tissue Analysis

Published on: April 12, 2017

9.0K
A Data-Driven Approach to Quantifying Immune States in Sepsis
07:42

A Data-Driven Approach to Quantifying Immune States in Sepsis

Published on: February 7, 2025

354

Area of Science:

  • Cardiovascular Medicine
  • Data Science
  • Biomedical Informatics

Background:

  • Evidence-based guidelines have improved ST-Elevation Myocardial Infarction (STEMI) survival but outcomes have plateaued.
  • A novel approach is needed to holistically understand STEMI patient data.
  • Integrating cartography and machine learning offers a promising avenue for deeper insights.

Purpose of the Study:

  • To develop a holistic understanding of the STEMI patient space using data visualization.
  • To apply principles from cartography and machine learning to analyze a large STEMI registry.
  • To create novel visualizations of patient characteristics and outcomes.

Main Methods:

  • Utilized the Minnesota Heart Institute Foundation (MHIF) STEMI registry (over 5000 patients, 15 years).
  • Employed machine learning, dimensionality reduction, and data visualization techniques.
  • Trained a high-resolution self-organizing neural network to create a 2-D map of the multivariate patient space.

Main Results:

  • Transformed a large STEMI database into novel 2-D visualizations of patient attributes and outcomes.
  • Visualizations revealed patient characteristics, demographics, conditions, procedures, and outcomes.
  • Identified data anomalies, enabling corrections and refining registry accuracy.

Conclusions:

  • Pioneered the integration of cartography and machine learning for STEMI data visualization.
  • Demonstrated the potential of these visualizations to uncover patient data anomalies and improve registry integrity.
  • Future research can leverage these visualization techniques to better understand STEMI risk factors and predictors.