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

Model Approaches for Pharmacokinetic Data: Distributed Parameter Models01:06

Model Approaches for Pharmacokinetic Data: Distributed Parameter Models

203
Pharmacokinetic models are mathematical constructs that represent and predict the time course of drug concentrations in the body, providing meaningful pharmacokinetic parameters. These models are categorized into compartment, physiological, and distributed parameter models.
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
203
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

228
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
228
Mechanistic Models: Compartment Models in Individual and Population Analysis01:23

Mechanistic Models: Compartment Models in Individual and Population Analysis

198
Mechanistic models are utilized in individual analysis using single-source data, but imperfections arise due to data collection errors, preventing perfect prediction of observed data. The mathematical equation involves known values (Xi), observed concentrations (Ci), measurement errors (εi), model parameters (ϕj), and the related function (ƒi) for i number of values. Different least-squares metrics quantify differences between predicted and observed values. The ordinary least...
198

You might also read

Related Articles

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

Sort by
Same author

Falling short? Mitigating equity gaps and demographic bias in AI-driven molecular diagnostics.

Expert review of molecular diagnostics·2026
Same author

Atlas-based Multi-Parametric Quantitative Brain MRI Analysis of Children with Neurofibromatosis Type 1.

Clinical neuroradiology·2026
Same author

RetCond: A Conditional Diffusion Model for Self-Explanatory Multi-Class Fundus Image Classification.

Journal of medical systems·2026
Same author

A platform for investigating prompt framing as interface parameters in foundation models for robotics.

Frontiers in robotics and AI·2026
Same author

Apathy in Mild Behavioural Impairment: Associations with Cortical Thickness and Grey Matter Volume.

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

Combining federated learning and travelling model boosts performance and opens opportunities for digital health equity.

NPJ digital medicine·2026

Related Experiment Video

Updated: Dec 23, 2025

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

2.0K

Building machine learning models without sharing patient data: A simulation-based analysis of distributed learning by

Anup Tuladhar1, Sascha Gill2, Zahinoor Ismail3

  • 1Department of Radiology, University of Calgary, Calgary, Alberta, Canada; Hotchkiss Brain Institute, University of Calgary, Calgary, Alberta, Canada.

Journal of Biomedical Informatics
|April 27, 2020
PubMed
Summary

Distributed learning enables training machine learning models without sharing patient data, even for rare diseases with limited data. Ensembling local models improves performance, making it suitable for small datasets.

Keywords:
Artificial neural networksDistributed learningMachine learningMedical information systemsRandom forestSupport vector machines

More Related Videos

Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models
14:14

Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models

Published on: August 12, 2018

9.2K

Related Experiment Videos

Last Updated: Dec 23, 2025

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

2.0K
Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models
14:14

Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models

Published on: August 12, 2018

9.2K

Area of Science:

  • Medical informatics
  • Machine learning in healthcare
  • Distributed computing

Background:

  • Sharing patient data for machine learning is challenging.
  • Distributed learning trains models locally, avoiding data sharing.
  • Its effectiveness for rare diseases with limited data is unknown.

Purpose of the Study:

  • To evaluate distributed learning for rare diseases.
  • To simulate distributed learning using ensembling methods.
  • To assess performance with limited local data.

Main Methods:

  • Ensembled artificial neural networks (ANN), support vector machines (SVM), and random forests (RF).
  • Trained models locally across four medical datasets.
  • Evaluated performance with varying numbers of local training examples.

Main Results:

  • Distributed learning improved performance over single-institution models, even with few local examples.
  • Performance increased with more models in the ensemble.
  • Local class imbalance affected SVM but not ANN or RF.

Conclusions:

  • Distributed learning by ensembling is effective for training ML models without data sharing.
  • This approach is suitable for small datasets, including those for rare diseases.
  • ANN and RF are robust to local class imbalance in distributed settings.