A Decision Support System to Predict Acute Fish Toxicity

Anders L Madsen, S. Jannicke Moe, Thomas Braunbeck, Kristin A. Connors, Michelle Embry, Kristin Schirmer, Stefan Scholz, Raoul Wolf, Adam Lillicrap
Proceedings of The 11th International Conference on Probabilistic Graphical Models, PMLR 186:253-264, 2022.

Abstract

We present a decision support system using a Bayesian network to predict acute fish toxicity from multiple lines of evidence. Fish embryo toxicity testing has been proposed as an alternative to using juvenile or adult fish in acute toxicity testing for hazard assessments of chemicals. The European Chemicals Agency has recommended the development of a so-called weight-of-evidence approach for strengthening the evidence from fish embryo toxicity testing. While weight-of-evidence approaches in the ecotoxicology and ecological risk assessment community in the past have been largely qualitative, we have developed a Bayesian network for using fish embryo toxicity data in a quantitative approach. The system enables users to efficiently predict the potential toxicity of a chemical substance based on multiple types of evidence including physical and chemical properties, quantitative structure-activity relationships, toxicity to algae and daphnids, and fish gill cytotoxicity. The system is demonstrated on three chemical substances of different levels of toxicity. It is considered as a promising step towards a probabilistic weight-of-evidence approach to predict acute fish toxicity from fish embryo toxicity.

Cite this Paper

BibTeX
@InProceedings{pmlr-v186-madsen22b, title = {A Decision Support System to Predict Acute Fish Toxicity}, author = {Madsen, Anders L and Moe, S. Jannicke and Braunbeck, Thomas and Connors, Kristin A. and Embry, Michelle and Schirmer, Kristin and Scholz, Stefan and Wolf, Raoul and Lillicrap, Adam}, booktitle = {Proceedings of The 11th International Conference on Probabilistic Graphical Models}, pages = {253--264}, year = {2022}, editor = {Salmerón, Antonio and Rumı́, Rafael}, volume = {186}, series = {Proceedings of Machine Learning Research}, month = {05--07 Oct}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v186/madsen22b/madsen22b.pdf}, url = {https://proceedings.mlr.press/v186/madsen22b.html}, abstract = {We present a decision support system using a Bayesian network to predict acute fish toxicity from multiple lines of evidence. Fish embryo toxicity testing has been proposed as an alternative to using juvenile or adult fish in acute toxicity testing for hazard assessments of chemicals. The European Chemicals Agency has recommended the development of a so-called weight-of-evidence approach for strengthening the evidence from fish embryo toxicity testing. While weight-of-evidence approaches in the ecotoxicology and ecological risk assessment community in the past have been largely qualitative, we have developed a Bayesian network for using fish embryo toxicity data in a quantitative approach. The system enables users to efficiently predict the potential toxicity of a chemical substance based on multiple types of evidence including physical and chemical properties, quantitative structure-activity relationships, toxicity to algae and daphnids, and fish gill cytotoxicity. The system is demonstrated on three chemical substances of different levels of toxicity. It is considered as a promising step towards a probabilistic weight-of-evidence approach to predict acute fish toxicity from fish embryo toxicity. } }
Endnote
%0 Conference Paper %T A Decision Support System to Predict Acute Fish Toxicity %A Anders L Madsen %A S. Jannicke Moe %A Thomas Braunbeck %A Kristin A. Connors %A Michelle Embry %A Kristin Schirmer %A Stefan Scholz %A Raoul Wolf %A Adam Lillicrap %B Proceedings of The 11th International Conference on Probabilistic Graphical Models %C Proceedings of Machine Learning Research %D 2022 %E Antonio Salmerón %E Rafael Rumı́ %F pmlr-v186-madsen22b %I PMLR %P 253--264 %U https://proceedings.mlr.press/v186/madsen22b.html %V 186 %X We present a decision support system using a Bayesian network to predict acute fish toxicity from multiple lines of evidence. Fish embryo toxicity testing has been proposed as an alternative to using juvenile or adult fish in acute toxicity testing for hazard assessments of chemicals. The European Chemicals Agency has recommended the development of a so-called weight-of-evidence approach for strengthening the evidence from fish embryo toxicity testing. While weight-of-evidence approaches in the ecotoxicology and ecological risk assessment community in the past have been largely qualitative, we have developed a Bayesian network for using fish embryo toxicity data in a quantitative approach. The system enables users to efficiently predict the potential toxicity of a chemical substance based on multiple types of evidence including physical and chemical properties, quantitative structure-activity relationships, toxicity to algae and daphnids, and fish gill cytotoxicity. The system is demonstrated on three chemical substances of different levels of toxicity. It is considered as a promising step towards a probabilistic weight-of-evidence approach to predict acute fish toxicity from fish embryo toxicity.
APA
Madsen, A.L., Moe, S.J., Braunbeck, T., Connors, K.A., Embry, M., Schirmer, K., Scholz, S., Wolf, R. & Lillicrap, A.. (2022). A Decision Support System to Predict Acute Fish Toxicity. Proceedings of The 11th International Conference on Probabilistic Graphical Models, in Proceedings of Machine Learning Research 186:253-264 Available from https://proceedings.mlr.press/v186/madsen22b.html.

Related Material