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 Video

Updated: Dec 8, 2025

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.8K

Graph Convolutional Networks-Based Noisy Data Imputation in Electronic Health Record.

Byeong Tak Lee1, O-Yeon Kwon1, Hyunho Park1

  • 1VUNO Inc., Seoul, Republic of Korea.

Critical Care Medicine
|September 18, 2020
PubMed
Summary

Related Concept Videos

Methods of Documentation VII: EMR01:30

Methods of Documentation VII: EMR

1.3K
Electronic Medical Records (EMRs) primarily center around electronically documenting patients' health information within a single healthcare organization or practice. They contain essential clinical data related to a patient's medical history, diagnoses, medications, treatment plans, lab results, and other pertinent information relevant to the specific encounter or episode of care. EMRs are designed to streamline documentation and workflow processes within individual healthcare...
1.3K

You might also read

Related Articles

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

Sort by
Same author

Machine learning-based prediction model for long-term mortality after ischemic stroke.

Scientific reports·2026
Same author

Sex-Consistent Performance of an AI-Enabled ECG for Acute Myocardial Infarction: The ROMIAE Study.

JACC. Advances·2026
Same author

Implementation of an AI-Based Clinical Decision Support System Predicting In-Hospital Cardiac Arrest in General Wards: A Multicenter Staggered-Implementation Study in Secondary Hospitals in Korea.

Diagnostics (Basel, Switzerland)·2026
Same author

Artificial Intelligence Electrocardiogram and Left Ventricular Systolic Dysfunction in Kenya.

JAMA cardiology·2026
Same author

Prediction of vasovagal syncope using artificial intelligence-enabled smartwatch photoplethysmography-derived heart rate variability.

European heart journal. Digital health·2026
Same author

Artificial Intelligence-Enabled ECG for Elevated E/e' on Echocardiography: Hemodynamic Relevance and Prognostic Value.

Journal of the American Heart Association·2026

A novel deep learning system accurately predicts sepsis onset up to 12 hours in advance using electronic health records. This sepsis prediction tool demonstrates high performance and potential for real-world clinical application.

Area of Science:

  • Medical Informatics
  • Artificial Intelligence in Healthcare
  • Critical Care Medicine

Background:

  • Sepsis is a life-threatening condition requiring timely intervention.
  • Early detection of sepsis remains a significant clinical challenge.
  • Existing early warning systems have limitations in prediction accuracy and lead time.

Purpose of the Study:

  • To develop and evaluate a deep learning-based early warning system for predicting sepsis onset.
  • To assess the system's ability to detect sepsis at least 6 hours prior to clinical manifestation.
  • To compare the performance of the proposed algorithm against existing methods.

Main Methods:

  • A novel deep learning algorithm was developed using retrospective electronic medical record data from over 60,000 ICU patients.

Related Experiment Videos

Last Updated: Dec 8, 2025

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.8K
  • The algorithm utilized 40 clinical variables, including vital signs and laboratory results, recorded hourly.
  • Performance was evaluated using metrics from the Physionet Challenge 2019, including AUC-ROC and AUC-PR.

    • Main Results:

    • The algorithm successfully predicted sepsis onset 4, 6, 8, and 12 hours in advance.
    • Achieved superior performance with an Area Under the Receiver Operating Characteristic curve (AUC-ROC) of 0.782 and an Area Under the Precision-Recall curve (AUC-PR) of 0.041.
    • Demonstrated high accuracy (0.786) and F-measure (0.046), outperforming other methods in early sepsis prediction.

    Conclusions:

    • The proposed deep learning system provides accurate and early prediction of sepsis onset.
    • The system shows significant potential as a practical early warning tool in real hospital environments.
    • This advancement can improve patient outcomes through timely sepsis management.