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

You might also read

Related Articles

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

Sort by
Same author

Single-shot wide-field biochemical imaging at 1 kHz frame rate.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

Pectin removal in Acer rubrum increases pit membrane compliance and embolism propagation.

Plant physiology·2026
Same author

Poly-IgA immune complex as a monitoring biomarker of response to telitacicept in IgA nephropathy.

Frontiers in immunology·2026
Same author

A Curated Dataset for Question Answering on Laboratory Test Reference Ranges and Interpretation.

Scientific data·2026
Same author

Patient Experiences With Online Laboratory Test Presentations From Access to Activation: Systematic Review.

Journal of medical Internet research·2026
Same author

Usability and Acceptance of In-App Social-Interacting Features for Promoting Adherence to Computerized Cognitive Training: A Pilot Evaluation.

Journal of cognitive enhancement : towards the integration of theory and practice·2026
Same journal

SMKD: Selective Mutual Knowledge Distillation.

Proceedings of ... International Joint Conference on Neural Networks. International Joint Conference on Neural Networks·2024
Same journal

Dynamic Perturbation of Weights for Improved Data Reconstruction in Unsupervised Learning.

Proceedings of ... International Joint Conference on Neural Networks. International Joint Conference on Neural Networks·2022
Same journal

Classification Based on Neuroimaging Data by Tensor Boosting.

Proceedings of ... International Joint Conference on Neural Networks. International Joint Conference on Neural Networks·2020
Same journal

Subject-Specific Convolutional Neural Networks for Accelerated Magnetic Resonance Imaging.

Proceedings of ... International Joint Conference on Neural Networks. International Joint Conference on Neural Networks·2020
Same journal

Predicting Nodule Malignancy using a CNN Ensemble Approach.

Proceedings of ... International Joint Conference on Neural Networks. International Joint Conference on Neural Networks·2018
Same journal

Representation of Deep Features using Radiologist defined Semantic Features.

Proceedings of ... International Joint Conference on Neural Networks. International Joint Conference on Neural Networks·2018
See all related articles

Related Experiment Video

Updated: Dec 4, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.5K

DeepConsensus: Consensus-based Interpretable Deep Neural Networks with Application to Mortality Prediction.

Shaeke Salman1, Seyedeh Neelufar Payrovnaziri2, Xiuwen Liu1

  • 1Department of Computer Science, Florida State University, FL 32306, USA.

Proceedings of ... International Joint Conference on Neural Networks. International Joint Conference on Neural Networks
|October 26, 2020
PubMed
Summary
This summary is machine-generated.

This study introduces a novel consensus algorithm for deep neural networks, enhancing accuracy and interpretability in healthcare predictions. The method effectively handles adversarial examples and out-of-distribution data, improving patient mortality predictions.

More Related Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.2K
Constructing and Visualizing Models using Mime-based Machine-learning Framework
06:19

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

1.7K

Related Experiment Videos

Last Updated: Dec 4, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.5K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.2K
Constructing and Visualizing Models using Mime-based Machine-learning Framework
06:19

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

1.7K

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Medical Informatics

Background:

  • Deep neural networks (DNNs) excel in complex tasks but their 'black-box' nature hinders critical applications like healthcare.
  • Adversarial examples and overgeneralization to out-of-distribution data reduce trust and explainability in DNN decisions.
  • Interpretable and accurate prediction models are crucial for healthcare, especially for patient mortality prediction.

Purpose of the Study:

  • To analyze DNN generalization mechanisms.
  • To propose a novel (n, k) consensus algorithm for improved robustness and interpretability.
  • To enhance prediction accuracy and reliability in healthcare applications.

Main Methods:

  • Developed an (n, k) consensus algorithm to achieve insensitivity to adversarial examples and reliable rejection of out-of-distribution samples.
  • Utilized multiple trained deep neural networks within the consensus framework to boost classification accuracy.
  • Clustered linear approximations of individual models to identify robust feature importance, enhancing interpretability.
  • Applied the algorithm to a one-year patient mortality prediction task using an ICU dataset.

Main Results:

  • The proposed consensus algorithm demonstrated robustness against adversarial examples and effectively rejected out-of-distribution samples.
  • The method significantly improved prediction accuracy for one-year patient mortality compared to standard deep neural network approaches.
  • Interpretability was maintained at levels comparable to conventional shallow models like logistic regression.
  • Experimental results on an ICU dataset confirmed the algorithm's effectiveness in enhancing both accuracy and interpretability.

Conclusions:

  • The (n, k) consensus algorithm offers a viable solution for creating accurate and interpretable deep neural network models in healthcare.
  • The approach addresses key limitations of DNNs, namely their susceptibility to adversarial attacks and lack of transparency.
  • This work contributes to the development of trustworthy AI in critical domains by improving both the performance and explainability of predictive models.