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: Jul 10, 2026

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections
06:22

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

Published on: September 19, 2025

ABC-RF-rejection: A two-stage machine-learning-enhanced framework for efficient likelihood-free inference.

Renata Retkute1, Christopher A Gilligan1

  • 1Epidemiology and Modelling Group, Department of Plant Sciences, University of Cambridge, Downing Street, Cambridge, CB2 3EA, UK.

Epidemics
|July 8, 2026
PubMed
Summary
This summary is machine-generated.

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

Predicting the cross-continental spread of the cassava brown streak disease epidemic in sub-Saharan Africa.

Scientific reports·2026
Same author

Parameterisation of epidemiological models from small field experiments: A case study of banana bunchy top virus transmission.

Mathematical biosciences·2026
Same author

Optimizing crop clustering to minimize pathogen invasion in agriculture.

Scientific reports·2025
Same author

Optimizing crop varietal mixtures for viral disease management: A case study on cassava virus epidemics.

PLoS computational biology·2025
Same author

Developing a spatio-temporal model for banana bunchy top disease: leveraging remote sensing and survey data.

Frontiers in plant science·2025
Same author

Where to refine spatial data to improve accuracy in crop disease modelling: an analytical approach with examples for cassava.

Royal Society open science·2025

This study introduces ABC-RF-rejection, a novel framework enhancing computational efficiency for epidemiological model parameter estimation. This method improves decision-making for complex disease models with limited data.

Area of Science:

  • Quantitative Epidemiology
  • Computational Biology
  • Statistical Modeling

Background:

  • Accurate parameter estimation is crucial for robust epidemiological models and evidence-based decision-making.
  • Traditional Approximate Bayesian Computation (ABC) methods are computationally expensive for complex models with intractable likelihoods.
  • Existing methods struggle with low acceptance rates and high simulation costs.

Purpose of the Study:

  • To present a novel, computationally efficient two-stage framework for parameter estimation in complex epidemiological models.
  • To integrate Approximate Bayesian Computation (ABC) rejection sampling with Random Forest (RF) classification.
  • To enhance the speed and accuracy of parameter estimation for stochastic and spatially explicit models.

Main Methods:

Keywords:
Approximate Bayesian computationComputational efficiencyLikelihood-free inferenceMechanistic epidemic modellingRandom Forest classification

Related Experiment Videos

Last Updated: Jul 10, 2026

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections
06:22

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

Published on: September 19, 2025

  • A hybrid approach, ABC-RF-rejection, combining ABC rejection sampling and Random Forest (RF) classification.
  • Stage 1: Small-scale ABC rejection to generate a labelled training dataset.
  • Stage 2: Trained RF model predicts acceptance probabilities, guiding posterior exploration and reducing computational burden.

Main Results:

  • The ABC-RF-rejection framework significantly enhances computational efficiency for parameter estimation.
  • The method successfully applied to diverse epidemiological contexts: onchocerciasis, cassava brown streak virus, and Ebola.
  • Demonstrated adaptability for models with spatial heterogeneity, stochasticity, and limited surveillance data.

Conclusions:

  • ABC-RF-rejection offers an adaptable and robust solution for rapid parameter estimation in complex epidemiological scenarios.
  • The framework facilitates evidence-based decision-making, especially in data-limited or complex settings.
  • Improves the feasibility of using sophisticated models for public health interventions.