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

Predicting Molecular Geometry02:27

Predicting Molecular Geometry

45.4K
VSEPR Theory for Determination of Electron Pair Geometries
45.4K
Interpreting R Charts01:22

Interpreting R Charts

341
R chart, or range chart, is a fundamental tool in statistical process control used to monitor the variability within a process. It complements the X-bar (x̄) chart by focusing on the range of the data, rather than individual values, providing a clear picture of the process dispersion over time.
An R chart plots the range of subsets of measurements collected from a process. Each point on the chart represents the range—defined as the difference between the maximum and minimum...
341
Interpreting Run Charts01:25

Interpreting Run Charts

3.0K
Run charts, essentially line graphs plotted over time, serve as fundamental yet effective tools for process analysis. They chronicle data sequentially, facilitating the identification of trends, shifts, or cyclical movements. This graphical representation is instrumental in determining whether a process is stable or exhibits signs of potential instability indicative of special cause variation. In the healthcare domain, run charts depict infection rates over time, enabling hospitals to monitor...
3.0K
Mass Spectrum: Interpretation01:24

Mass Spectrum: Interpretation

2.8K
An unknown compound can be established by identifying the molecular ion peak in the mass spectrum. The molecular ion peak is often weak or absent due to the predominance of fragmentation in high-energy electron beams. In such cases, a soft-energy electron beam can be used to scan the spectrum to enhance the intensity of the molecular ion peak. Additionally, chemical ionization, field ionization, and desorption ionization spectra are used to obtain a relatively intense molecular ion peak.To...
2.8K
Interpretation of Confidence Intervals01:19

Interpretation of Confidence Intervals

9.4K
A confidence interval is a better estimate of the population than a point estimate, as it uses a range of values from a sample instead of a single value.
Confidence intervals have confidence coefficients that are crucial for their interpretation. The most common confidence coefficients are 0.90, 0.95, and 0.99, which can be written as percentages–90%, 95%, and 99%, respectively.
Suppose a person calculates a confidence interval with a confidence coefficient of 0.95. In that case, they can...
9.4K
Interpreting X̄ Charts01:13

Interpreting X̄ Charts

303
Interpreting x̄ charts, a type of control chart used in statistical process control helps monitor the variation in processes over time. The x̄ chart is based on the sample mean and allows for monitoring variations in the process mean over time. These charts are pivotal for quality assurance in manufacturing and other sectors.
An x̄ chart plots the values of individual measurements over time against control limits calculated from historical data. The central line...
303

You might also read

Related Articles

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

Sort by
Same author

A Novel Cooperative AI-Based Fall Risk Prediction Model for Older Adults.

Sensors (Basel, Switzerland)·2025
Same author

A polygeneric immunogen composed of 22 venoms from sub-Saharan African snakes to expand the neutralization scope of the EchiTAb-plus-ICP antivenom.

Toxicon: X·2024
Same author

Pilot-scale evaluation of a dynamic body-feed filtration system for primary clarification of snake antivenoms produced by the caprylic acid method.

Toxicon: X·2024
Same author

LPWAN Key Exchange: A Centralised Lightweight Approach.

Sensors (Basel, Switzerland)·2022
Same author

A Dynamic Algorithm for Interference Management in D2D-Enabled Heterogeneous Cellular Networks: Modeling and Analysis.

Sensors (Basel, Switzerland)·2022
Same author

Development and characterization of two equine formulations towards SARS-CoV-2 proteins for the potential treatment of COVID-19.

Scientific reports·2021

Related Experiment Video

Updated: Jan 20, 2026

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

10.6K

ISeeU: Visually interpretable deep learning for mortality prediction inside the ICU.

William Caicedo-Torres1, Jairo Gutierrez2

  • 1Auckland University of Technology, Auckland, New Zealand; Universidad Tecnológica de Bolívar, Cartagena, Colombia.

Journal of Biomedical Informatics
|August 21, 2019
PubMed
Summary

This study introduces an interpretable deep learning model for predicting Intensive Care Unit (ICU) patient mortality using the MIMIC-III database. The novel approach achieves competitive performance while providing visual explanations for its predictions.

Keywords:
Deep learningICUMIMIC-IIIShapley Values

More Related Videos

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data
09:34

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

Published on: September 25, 2021

4.5K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.5K

Related Experiment Videos

Last Updated: Jan 20, 2026

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

10.6K
A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data
09:34

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

Published on: September 25, 2021

4.5K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.5K

Area of Science:

  • Biostatistics
  • Artificial Intelligence
  • Medical Informatics

Background:

  • Traditional biostatistical scores for predicting negative outcomes in Intensive Care Units (ICUs) demonstrate sub-optimal performance.
  • Deep learning models show promise in outperforming traditional methods for prediction tasks in healthcare.
  • A significant barrier to deep learning adoption in healthcare is its lack of interpretability, hindering trust and validation.

Purpose of the Study:

  • To develop an interpretable deep learning model for predicting patient mortality in Intensive Care Units (ICUs).
  • To enhance the explainability of deep learning models in healthcare by visualizing input feature importance.
  • To evaluate the model's performance against existing state-of-the-art methods using the MIMIC-III dataset.

Main Methods:

  • A deep multi-scale convolutional neural network architecture was designed and trained on the Medical Information Mart for Intensive Care III (MIMIC-III) dataset.
  • Coalitional game theory concepts were employed to generate visual explanations, highlighting the importance of input features.
  • The model's predictive performance was assessed using Receiver Operating Characteristic Area Under the Curve (ROC AUC).

Main Results:

  • The proposed deep learning model achieved a competitive ROC AUC of 0.8735 (± 0.0025) for mortality prediction.
  • The model demonstrated interpretability through visual explanations derived from coalitional game theory.
  • The results indicate that the model is capable of learning relevant features without relying on spurious correlations.

Conclusions:

  • The developed interpretable deep learning model offers a promising approach for accurate and understandable mortality prediction in ICUs.
  • This work addresses the critical need for explainable artificial intelligence in clinical decision-making.
  • The methodology provides a foundation for building trustworthy deep learning applications in critical care settings.