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: May 28, 2026

Using the FishSim Animation Toolchain to Investigate Fish Behavior: A Case Study on Mate-Choice Copying In Sailfin Mollies
10:50

Using the FishSim Animation Toolchain to Investigate Fish Behavior: A Case Study on Mate-Choice Copying In Sailfin Mollies

Published on: November 8, 2018

Evaluating and Refining PCB Mixture Indicators in Marine Fish Through Explainable Artificial Intelligence.

Vojin Ćućuz1, Gordana Jovanović2, Timea Bezdan3

  • 1National Cancer Research Centre, Pasterova 14, 11000 Belgrade, Serbia.

Toxics
|May 27, 2026
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

The Role of Antioxidants in the Management of Polycystic Ovary Syndrome.

Antioxidants (Basel, Switzerland)·2026
Same author

Uncovering Benzene Pollution Patterns Using an Interpretable, Setting-Aware Artificial Intelligence Approach.

Toxics·2026
Same author

Application of the AI-Based Framework for Analyzing the Dynamics of Persistent Organic Pollutants (POPs) in Human Breast Milk.

Toxics·2025
Same author

Efficiency of clustering methods and self-organizing maps of Adriatic sardines and anchovies regarding organochlorine and fatty acid burden.

Environmental science and pollution research international·2024
Same author

Polychlorinated biphenyls in mussels, small pelagic fish, tuna, turtles, and dolphins from the Croatian Adriatic Sea waters: an overview of the last two decades of monitoring.

Arhiv za higijenu rada i toksikologiju·2024
Same author

Potential of Coupling Metaheuristics-Optimized-XGBoost and SHAP in Revealing PAHs Environmental Fate.

Toxics·2023
Same journal

Environmental Concentrations of PFOS Accumulate in the <i>Euglena</i> Eyespot and Impair Chloroplast ATP Synthase Activity: A Dual Impairment of Phototaxis and Photosynthetic Light Reactions.

Toxics·2026
Same journal

Heavy Metal(loid) Pollution Characteristics and Risk Assessment in the Water-Soil-Vegetable System of a Watershed in Southwest China.

Toxics·2026
Same journal

Sludge Retention Time Governs Ectoine Synthesis and Pollutant Removal in Halophilic Activated Sludge Treating High-Salinity Wastewater.

Toxics·2026
Same journal

Interpretable Machine Learning and Spatiotemporal Modeling of Meteorological and Environmental Drivers for Tuberculosis Incidence in China.

Toxics·2026
Same journal

A 3D Graphene Oxide Model Reveals Fine Particulate Matter Induced Cell Cycle Dysregulation in Neural Stem Cells.

Toxics·2026
Same journal

Storage-Dependent Changes in Microplastic-Associated Recoverable Residues in Yogurt Containing <i>Bifidobacterium longum</i> subsp. <i>infantis</i>.

Toxics·2026
See all related articles
This summary is machine-generated.

New methods using machine learning improve indicators for polychlorinated biphenyls (PCBs) in marine fish. This helps better track PCB contamination and protect ecosystems.

Area of Science:

  • Environmental Chemistry
  • Marine Biology
  • Computational Science

Background:

  • Polychlorinated biphenyls (PCBs) are persistent organic pollutants of significant concern in marine ecosystems.
  • Bioaccumulation of complex PCB congener mixtures in fish challenges traditional indicator approaches for monitoring contamination.
  • Understanding PCB dynamics is crucial for effective environmental management and risk assessment.

Purpose of the Study:

  • To develop and evaluate a data-driven framework for refining PCB mixture-based indicators using ensemble machine learning and explainable AI.
  • To identify optimal congener combinations and biological covariates for representing cumulative PCB burden in Mediterranean pelagic fish.
  • To assess the influence of concentration range and mixture context on indicator performance.

Main Methods:

Keywords:
Shapley additive explanationsShapley additive global importanceexplainable artificial intelligenceexposure profilingindicator mixturesmarine fishpolychlorinated biphenyls (PCBs)

Related Experiment Videos

Last Updated: May 28, 2026

Using the FishSim Animation Toolchain to Investigate Fish Behavior: A Case Study on Mate-Choice Copying In Sailfin Mollies
10:50

Using the FishSim Animation Toolchain to Investigate Fish Behavior: A Case Study on Mate-Choice Copying In Sailfin Mollies

Published on: November 8, 2018

  • Analysis of 24 organochlorine concentrations and biological covariates in four Mediterranean pelagic fish species.
  • Application of ensemble machine learning and explainable artificial intelligence for indicator development and evaluation.
  • Comparative performance assessment of traditional and alternative PCB indicator groups, including specific congener combinations and DDD/DDE mixtures.

Main Results:

  • Alternative congener combinations (i4 PCBs, i6 PCBs, DDD/DDE mixtures) demonstrated superior performance in representing total PCB burden compared to traditional indicators.
  • Clustering revealed two distinct bioaccumulation settings: high-concentration coherent congener effects and low-concentration heterogeneous responses.
  • Indicator performance was found to be dependent on concentration range and the specific mixture context.

Conclusions:

  • The study provides a robust framework for optimizing PCB indicators, enhancing the monitoring of legacy contaminants in marine environments.
  • Interpretable machine learning offers valuable tools for formal evaluation and refinement of environmental indicators.
  • Improved indicators are essential for effective long-term management of marine ecosystems facing persistent PCB exposure and renewed inputs.