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 11, 2026

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

43.4K

A Hybrid Bidirectional Deep Learning Model Using HRV for Prediction of ICU Mortality Risk in TBI Patients.

Hasitha Kuruwita A1, Shu Kay Ng2, Alan Wee-Chung Liew3

  • 1School of Medicine and Dentistry, Griffith University, Gold Coast, Australia.

Journal of Healthcare Informatics Research
|November 13, 2025
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

Integrative transcriptome and long non-coding RNA analysis to decipher the molecular basis of cleistogamy in pigeonpea (Cajanus cajan (L) Millsp).

Planta·2026
Same author

The Hidden Architecture of Brain Structural Variability in 22q11.2 Deletion Syndrome: A Multi-site Study.

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

Retraction Note: Spin polarized first principles study of electro-magnetic and optical properties of K<sub>2</sub>NaXI<sub>6</sub> (X :Cr Fe) double halide perovskites.

Scientific reports·2026
Same author

Remote ischemic preconditioning protects heart via modulation of purinergic signaling and AMPK-mediated autophagy in rat model of ischemia reperfusion injury.

Iranian journal of basic medical sciences·2026
Same author

Analysis of Infection Types, Pathogens, Antimicrobial Treatment, and Clinical Outcomes Data in Hospitalised Patients: Comprehensive Online Database for Antimicrobial Resistance (CODAR) Retrospective Pilot Study.

Journal of epidemiology and global health·2026
Same author

Copy number variants reveal divergent genetic and diagnostic cortical signatures across psychiatric disorders.

Research square·2026

Predicting mortality risk in traumatic brain injury (TBI) patients is vital. This study uses a deep learning model analyzing heart rate variability (HRV) from ECGs to accurately forecast early mortality risk in ICU patients.

Area of Science:

  • Critical Care Medicine
  • Biomedical Engineering
  • Data Science

Background:

  • Early mortality prediction in intensive care unit (ICU) traumatic brain injury (TBI) patients is essential for resource allocation and patient management.
  • Current methods may lack the precision needed for timely intervention.
  • Analyzing physiological signals like electrocardiogram (ECG) offers potential for improved risk assessment.

Purpose of the Study:

  • To develop and validate a novel deep learning model for predicting early mortality risk in TBI patients.
  • To leverage heart rate variability (HRV) from continuous ECG monitoring for enhanced predictive accuracy.
  • To assess the model's performance against conventional machine learning approaches.

Main Methods:

  • A hybrid deep learning model integrating a weight predictor with a bidirectional long short-term memory (BiLSTM) unit was developed.
Keywords:
Clinical decision supportHeart rate variabilityMachine learningMortality predictionTraumatic brain injury

More Related Videos

A Bedside, Single Burr Hole Approach to Multimodality Monitoring in Severe Brain Injury
06:18

A Bedside, Single Burr Hole Approach to Multimodality Monitoring in Severe Brain Injury

Published on: March 26, 2019

9.5K

Related Experiment Videos

Last Updated: Jan 11, 2026

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

43.4K
A Bedside, Single Burr Hole Approach to Multimodality Monitoring in Severe Brain Injury
06:18

A Bedside, Single Burr Hole Approach to Multimodality Monitoring in Severe Brain Injury

Published on: March 26, 2019

9.5K
  • The model analyzed heart rate variability (HRV) extracted from the first 24 hours of ECG signals from TBI patients.
  • Data from Gold Coast University Hospital and the Cerebral Haemodynamic Autoregulatory Information System (CHARIS) were used for training and testing.

    • Main Results:

    • The hybrid model achieved high cross-validation accuracy (0.933) and AUROC (0.995).
    • On a hold-out test set, the model demonstrated prediction accuracy of 0.917 and AUROC of 0.926.
    • The proposed model significantly outperformed existing conventional machine learning models in mortality risk prediction.

    Conclusions:

    • The developed deep learning model accurately predicts early mortality risk in TBI patients using HRV from ECG data.
    • The model's reliance on readily available ICU ECG data facilitates straightforward clinical implementation.
    • This approach offers a promising tool to enhance critical care strategies and patient outcomes.