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 6, 2025

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

407

Bi-Directional Gated Recurrent Unit Based Ensemble Model for the Early Detection of Sepsis.

Sajila D Wickramaratne, M D Shaad Mahmud

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
    |October 6, 2020
    PubMed
    Summary

    Early sepsis detection is crucial for timely treatment and reduced mortality. A new deep learning model using Bi-Directional Gated Recurrent Units (GRU) predicts sepsis 6 hours in advance, outperforming existing methods.

    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

    Machine Learning Model Combining Ventilatory, Hypoxic, Arousal Domains Across Sleep Better Predicts Adverse Consequences of Obstructive Sleep Apnea.

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
    Same author

    SleepSIM: Conditional GAN-based non-REM sleep EEG Signal Generator.

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2023
    Same author

    Detection and Characterization of Walking Bouts Using a Single Wrist-Worn Accelerometer in Free-living Conditions.

    medRxiv : the preprint server for health sciences·2023
    Same author

    LSTM based GAN Networks for Enhancing Ternary Task Classification Using fNIRS Data.

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2021
    Same author

    Conditional-GAN Based Data Augmentation for Deep Learning Task Classifier Improvement Using fNIRS Data.

    Frontiers in big data·2021
    Same author

    Automatic Detection of Respiratory Effort Related Arousals With Deep Neural Networks From Polysomnographic Recordings.

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2020

    Area of Science:

    • Medical Informatics
    • Artificial Intelligence in Medicine
    • Clinical Decision Support

    Background:

    • Early sepsis prediction is vital to reduce mortality, with delayed treatment increasing risk.
    • Current sepsis detection relies on Clinical Decision Rules (CDRs), which have limitations in generalizability and performance variability.
    • Developing and validating traditional sepsis detection systems is a lengthy process.

    Purpose of the Study:

    • To propose a novel deep learning model for early sepsis prediction.
    • To improve upon the performance and generalizability of existing sepsis detection systems.
    • To develop a model capable of handling real-world complexities in patient data.

    Main Methods:

    • Development of a deep learning model utilizing Bi-Directional Gated Recurrent Units (GRU).

    More Related Videos

    A Reproducible Intensive Care Unit-Oriented Endotoxin Model in Rats
    05:56

    A Reproducible Intensive Care Unit-Oriented Endotoxin Model in Rats

    Published on: February 20, 2021

    2.4K
    Evaluation of a Reliable Biomarker in a Cecal Ligation and Puncture-Induced Mouse Model of Sepsis
    05:28

    Evaluation of a Reliable Biomarker in a Cecal Ligation and Puncture-Induced Mouse Model of Sepsis

    Published on: December 9, 2022

    4.1K

    Related Experiment Videos

    Last Updated: Dec 6, 2025

    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

    407
    A Reproducible Intensive Care Unit-Oriented Endotoxin Model in Rats
    05:56

    A Reproducible Intensive Care Unit-Oriented Endotoxin Model in Rats

    Published on: February 20, 2021

    2.4K
    Evaluation of a Reliable Biomarker in a Cecal Ligation and Puncture-Induced Mouse Model of Sepsis
    05:28

    Evaluation of a Reliable Biomarker in a Cecal Ligation and Puncture-Induced Mouse Model of Sepsis

    Published on: December 9, 2022

    4.1K
  • Integration of diverse patient data, including vital signs, laboratory results, and demographics.
  • Model designed to effectively manage missing data and irregular sampling intervals.

    • Main Results:

    • The proposed GRU model achieved an Area Under the Receiver Operating Characteristic (AUROC) of 0.97.
    • Demonstrated superior performance compared to all existing sepsis prediction systems in the literature.
    • Successfully handled missing data and irregular sampling, common in electronic health records.

    Conclusions:

    • The deep learning model offers a significant advancement in sepsis prediction accuracy and reliability.
    • The model can predict sepsis onset up to 6 hours in advance.
    • This machine learning approach provides a more robust and generalizable alternative to traditional CDRs for sepsis detection.