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: Jan 5, 2026

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

452

LiSep LSTM: A Machine Learning Algorithm for Early Detection of Septic Shock.

Josef Fagerström1, Magnus Bång2, Daniel Wilhelms3,4

  • 1Department of Computer and Information Science, Linköping University, Linköping, 581 83, Sweden. josef.fagerstrom@liu.se.

Scientific Reports
|October 24, 2019
PubMed
Summary

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

The evolving prehospital care: a 12-year retrospective analysis.

Scandinavian journal of trauma, resuscitation and emergency medicine·2026
Same author

Cardiogenic shock - toward phenotype-directed, precision management.

Current opinion in critical care·2026
Same author

Advanced haemodynamic monitoring in cardiogenic shock.

Current opinion in critical care·2026
Same author

Facilitators and barriers to the implementation of critical care ultrasound (CCUS): an international survey.

Journal of critical care·2026
Same author

ETHER: a proposal for a European peri-operative data sharing and registry network.

European journal of anaesthesiology·2026
Same author

Clinical Criteria for the Definition of Refractory Septic Shock: A Joint Delphi Consensus from the Society of Critical Care Medicine (SCCM) and European Society of Intensive Care Medicine (ESICM).

Critical care medicine·2026

Early detection of sepsis is crucial. LiSep LSTM, a Long Short-Term Memory neural network, accurately identifies patients at risk for septic shock, potentially reducing mortality.

Area of Science:

  • Artificial Intelligence
  • Critical Care Medicine
  • Machine Learning

Background:

  • Sepsis affects 31.5 million globally, with high mortality rates.
  • Early detection and treatment of sepsis significantly reduce mortality.
  • Automated tools can improve early and accurate identification of at-risk patients.

Purpose of the Study:

  • To present LiSep LSTM, a novel Long Short-Term Memory neural network model.
  • To enable early identification of patients at risk for septic shock.
  • To evaluate the performance of LiSep LSTM against existing algorithms.

Main Methods:

  • Developed a Long Short-Term Memory (LSTM) neural network using Keras and TensorFlow.
  • Trained the model on a large dataset of ICU patient data (59,000 patients).

More Related Videos

Asthma Detection Research Based on Voice Signal Processing and Machine Learning
04:04

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

859

Related Experiment Videos

Last Updated: Jan 5, 2026

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

452
Asthma Detection Research Based on Voice Signal Processing and Machine Learning
04:04

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

859
  • Utilized vital signs, laboratory data, and journal entries for model training.

    • Main Results:

    • LiSep LSTM achieved an AUROC of 0.8306 (95% CI: 0.8236, 0.8376).
    • The model demonstrated median prediction offsets up to 40 hours before septic shock onset.
    • LiSep LSTM outperformed a less complex model using the same features and targets.

    Conclusions:

    • LiSep LSTM shows significant potential for early septic shock detection.
    • The model's ability to predict onset hours in advance can aid timely intervention.
    • Further comparison with state-of-the-art algorithms highlights its efficacy.