{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T11:21:35Z","timestamp":1785410495498,"version":"3.56.0"},"reference-count":42,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T00:00:00Z","timestamp":1777680000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100017592","name":"Institute of Physics Belgrade","doi-asserted-by":"crossref","award":["#7373"],"award-info":[{"award-number":["#7373"]}],"id":[{"id":"10.13039\/100017592","id-type":"DOI","asserted-by":"crossref"}]},{"award":["#7373"],"award-info":[{"award-number":["#7373"]}],"id":[{"id":"https:\/\/ror.org\/04h3h5b09","id-type":"ROR","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000780","name":"European Union","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"crossref"}]},{"id":[{"id":"https:\/\/ror.org\/019w4f821","id-type":"ROR","asserted-by":"publisher"}]},{"name":"Institute for Medical Research and Occupational Health","award":["533-03-23-0006"],"award-info":[{"award-number":["533-03-23-0006"]}]},{"award":["533-03-23-0006"],"award-info":[{"award-number":["533-03-23-0006"]}],"id":[{"id":"https:\/\/ror.org\/052zr0n46","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Toxics"],"abstract":"<jats:p>Polychlorinated biphenyls (PCBs) remain a major concern in marine ecosystems, where bioaccumulation in fish occurs as complex congener mixtures whose dynamics challenge conventional indicator approaches. This study develops and evaluates a data-driven framework for refining mixture-based indicators of PCB contamination by integrating ensemble machine learning with explainable artificial intelligence. Focusing on PCB-138 as a target indicator of cumulative PCB burden, we analyse concentrations of 24 organochlorines together with biological covariates in four Mediterranean edible pelagic fish species (sardine, anchovy, horse mackerel, and chub mackerel). Comparative evaluation of indicator performance shows that alternative congener combinations, including i4 PCBs (-138, -153, -170, -180), i6 PCBs (-138, -153, -170, -180, -118, -123), and mixtures incorporating DDD and DDE, more effectively represent total PCB burden than traditional indicator groups. Clustering identifies two distinct bioaccumulation settings, characterized by high-concentration coherent congener effects and low-concentration heterogeneous responses, demonstrating that indicator performance depends on concentration range and mixture context. The study illustrates how interpretable machine learning approaches can serve as formal tools for indicator evaluation and optimisation, strengthening long-term monitoring and management of legacy contaminants in marine ecosystems, particularly under conditions of persistent exposure and renewed inputs from sediment remobilization and riverine transport.<\/jats:p>","DOI":"10.3390\/toxics14050393","type":"journal-article","created":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T01:12:09Z","timestamp":1777857129000},"page":"393","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Evaluating and Refining PCB Mixture Indicators in Marine Fish Through Explainable Artificial Intelligence"],"prefix":"10.3390","volume":"14","author":[{"given":"Vojin","family":"\u0106u\u0107uz","sequence":"first","affiliation":[{"name":"National Cancer Research Centre, Pasterova 14, 11000 Belgrade, Serbia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8657-423X","authenticated-orcid":false,"given":"Gordana","family":"Jovanovi\u0107","sequence":"additional","affiliation":[{"name":"Institute of Physics Belgrade, a National Institute of the Republic of Serbia, Pregrevica 118, 11080 Belgrade, Serbia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6938-6974","authenticated-orcid":false,"given":"Timea","family":"Bezdan","sequence":"additional","affiliation":[{"name":"Faculty of Informatics and Computing, Singidunum University, Danijelova 32, 11000 Belgrade, Serbia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2382-4734","authenticated-orcid":false,"given":"Snje\u017eana","family":"Herceg Romani\u0107","sequence":"additional","affiliation":[{"name":"Institute for Medical Research and Occupational Health, Ksaverska Cesta 2, P.O. Box 291, 10001 Zagreb, Croatia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bosiljka","family":"Musta\u0107","sequence":"additional","affiliation":[{"name":"Department of Ecology, Agronomy and Aquaculture, University of Zadar, Trg Kneza Vi\u0161eslava 9, 23000 Zadar, Croatia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5293-9533","authenticated-orcid":false,"given":"Andreja","family":"Stoji\u0107","sequence":"additional","affiliation":[{"name":"Institute of Physics Belgrade, a National Institute of the Republic of Serbia, Pregrevica 118, 11080 Belgrade, Serbia"},{"name":"Environment and Sustainable Development Studies, Singidunum University, Danijelova 32, 11000 Belgrade, Serbia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8287-4136","authenticated-orcid":false,"given":"Mirjana","family":"Peri\u0161i\u0107","sequence":"additional","affiliation":[{"name":"Institute of Physics Belgrade, a National Institute of the Republic of Serbia, Pregrevica 118, 11080 Belgrade, Serbia"},{"name":"Environment and Sustainable Development Studies, Singidunum University, Danijelova 32, 11000 Belgrade, Serbia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,5,2]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"118319","DOI":"10.1016\/j.marpolbul.2025.118319","article-title":"Contaminants in fish and seafood from the marine environment: A global overview of current status and future perspective","volume":"219","author":"Barbieri","year":"2025","journal-title":"Mar. Pollut. Bull."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"9400","DOI":"10.1021\/acs.est.0c08093","article-title":"Persistent organic pollutants (POPs) and related chemicals in the global environment: Some personal reflections","volume":"55","author":"Jones","year":"2021","journal-title":"Environ. Sci. Technol."},{"key":"ref_3","unstructured":"Food and Agriculture Organization of the United Nations, FAO (2018). The State of Mediterranean and Black Sea Fisheries, General Fisheries Commission for the Mediterranean. Licence: CC BY-NC-SA 3.0 IGO."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1007\/s12526-020-01067-7","article-title":"Feeding ecology of Sardina pilchardus considering co- occurring small pelagic fish in the eastern Adriatic Sea","volume":"50","author":"Hure","year":"2020","journal-title":"Mar. Biodivers."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"113198","DOI":"10.1016\/j.marpolbul.2021.113198","article-title":"Trends of banned pesticides and PCBs in different tissues of striped dolphins (Stenella coeruleoalba) stranded in the Northwestern Mediterranean reflect changing contamination patterns","volume":"174","author":"Dron","year":"2020","journal-title":"Mar. Pollut. Bull."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1016\/j.aquatox.2018.11.008","article-title":"Supporting evidence for PCB pollution threatening global killer whale populations","volume":"206","author":"Schnitzler","year":"2019","journal-title":"Aquat. Toxicol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/j.envpol.2016.01.022","article-title":"Global monitoring plan for persistent organic pollutants (POPs) under the Stockholm Convention: Triggering, streamlining and catalyzing global POPs monitoring","volume":"217","author":"Magulova","year":"2016","journal-title":"Environ. Pollut."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"110878","DOI":"10.1016\/j.marpolbul.2019.110878","article-title":"Trace elements levels in muscle and liver of a rarely investigated large pelagic fish: The Mediterranean spearfish Tetrapturus belone (Rafinesque, 1810)","volume":"151","author":"Ancora","year":"2020","journal-title":"Mar. Pollut. Bull."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"560","DOI":"10.1007\/s10661-025-13956-0","article-title":"Occurrence, distribution, and levels of polychlorinated biphenyls (PCB), polychlorinated dibenzo-p-dioxins (PCDD), and polychlorinated dibenzofurans (PCDF) in fish from the Antioquia Region, Colombia","volume":"197","author":"Avila","year":"2025","journal-title":"Environ. Monit. Assess."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"118343","DOI":"10.1016\/j.marpolbul.2025.118343","article-title":"Tracing PCB contamination in fish using shadow profiles and self-organizing maps","volume":"220","author":"Blume","year":"2025","journal-title":"Mar. Pollut. Bull."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Lakhmanov, D., Varakina, Y., Aksenov, A., Sorokina, T., Sobolev, N., Kotsur, D., Plakhina, E., Chashchin, V., and Thomassen, Y. (2020). Persistent organic pollutants (POPs) in fish consumed by the indigenous peoples from Nenets Autonomous Okrug. Environments, 7.","DOI":"10.3390\/environments7010003"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"928","DOI":"10.1007\/s00128-012-0606-y","article-title":"Persistent organic pollutants (PCBs and DDTs) in European conger eel (Conger conger L.) from the Ionian Sea (Mediterranean Sea)","volume":"88","author":"Storelli","year":"2012","journal-title":"Bull. Environ. Contam. Toxicol."},{"key":"ref_13","unstructured":"UNEP (2025). Global Monitoring Plan for Persistent Organic Pollutants: Regional and Global Monitoring Reports, UNEP. Stockholm Convention Secretariat, 2017\u20132021."},{"key":"ref_14","unstructured":"ATSDR (2020). Toxicological Profile for Polychlorinated Biphenyls (PCBs)."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"163712","DOI":"10.1016\/j.scitotenv.2023.163712","article-title":"The screening and prioritization of contaminants of emerging concern in the marine environment based on multiple biological response measures","volume":"886","author":"James","year":"2023","journal-title":"Sci. Total Environ."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"116266","DOI":"10.1016\/j.envpol.2020.116266","article-title":"Organic pollutants in marine samples from Tunisian coast: Occurrence and associated human health risks","volume":"271","author":"Jebara","year":"2021","journal-title":"Environ. Pollut."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"180167","DOI":"10.1016\/j.scitotenv.2025.180167","article-title":"Polychlorinated biphenyls in various fish species farmed and caught in the Adriatic Sea over ten years: A health risk assessment","volume":"996","author":"Sedak","year":"2025","journal-title":"Sci. Total Environ."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1038\/s43247-025-02348-4","article-title":"Climate change drives persistent organic pollutant dynamics in marine environments","volume":"6","author":"Noyes","year":"2025","journal-title":"Commun. Earth Environ."},{"key":"ref_19","unstructured":"Lundberg, S.M., and Lee, S.-I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, Curran Associates Inc."},{"key":"ref_20","unstructured":"Covert, I., Lundberg, S.M., and Lee, S.-I. (2020, January 6\u201312). Understanding global feature contributions with additive importance measures. Proceedings of the 34th Conference Neural Information Processing Systems (NeurIPS), Vancouver, BC, Canada."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"111170","DOI":"10.1016\/j.engappai.2025.111170","article-title":"Machine learning approaches to predict oxidative potential of fine particulate matter based on chemical constituents","volume":"156","author":"Lee","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Radi\u0107, N., Peri\u0161i\u0107, M., Jovanovi\u0107, G., Bezdan, T., Stani\u0161i\u0107, S., Stani\u0107, N., and Stoji\u0107, A. (2025). An AI-based framework for characterizing the atmospheric fate of air pollutants within diverse environmental settings. Atmosphere, 16.","DOI":"10.3390\/atmos16020231"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"108017","DOI":"10.1016\/j.eiar.2025.108017","article-title":"Assessing ozone formation impact through SHAP interaction redistribution analysis: A novel framework for evaluating VOC photochemical loss and source interactions","volume":"115","author":"Yao","year":"2025","journal-title":"Environ. Impact Assess. Rev."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Jovanovi\u0107, G., Bezdan, T., Bio\u0161i\u0107, M., Menda\u0161, G., Herceg Romani\u0107, S., Stoji\u0107, S., Matek Sari\u0107, M., and Peri\u0161i\u0107, M. (2025). Application of the AI-based framework for analyzing the dynamics of persistent organic pollutants (POPs) in human breast milk. Toxics, 13.","DOI":"10.3390\/toxics13080631"},{"key":"ref_25","first-page":"15","article-title":"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","volume":"75","author":"Fingler","year":"2024","journal-title":"Arh. Hig. Rada Toksikol."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"112654","DOI":"10.1016\/j.marpolbul.2021.112654","article-title":"Fatty acids, persistent organic pollutants, and trace elements in small pelagic fish from the eastern Mediterranean Sea","volume":"170","year":"2021","journal-title":"Mar. Pollut. Bull."},{"key":"ref_27","first-page":"299","article-title":"Chlorinated compounds in the muscle tissue of fish from the Croatian Adriatic: Preliminary data on contamination","volume":"66","year":"2015","journal-title":"Arch. Ind. Hyg. Toxicol."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1006\/jcss.1997.1504","article-title":"A decision-theoretic generalization of on-line learning and an application to boosting","volume":"55","author":"Freund","year":"1997","journal-title":"J. Comput. Syst. Sci."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/s10994-006-6226-1","article-title":"Extremely randomized trees","volume":"63","author":"Geurts","year":"2006","journal-title":"Mach. Learn."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: A gradient boosting machine","volume":"29","author":"Friedman","year":"2001","journal-title":"Ann. Stat."},{"key":"ref_31","first-page":"849","article-title":"A streaming parallel decision tree algorithm","volume":"11","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref_32","unstructured":"Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T.Y. (2017). LightGBM: A highly efficient gradient boosting decision tree. Advances in Neural Information Processing Systems, Curran Associates Inc."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1016\/j.knosys.2015.12.022","article-title":"SCA: A sine cosine algorithm for solving optimization problems","volume":"96","author":"Mirjalili","year":"2016","journal-title":"Knowl.-Based Syst."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"849","DOI":"10.1016\/j.future.2019.02.028","article-title":"Harris hawks optimization: Algorithm and applications","volume":"97","author":"Heidari","year":"2019","journal-title":"Future Gener. Comput. Syst."},{"key":"ref_36","unstructured":"Wang, Y., and Zheng, Y. (2021, January 27\u201330). PaCMAP: Pairwise controlled manifold approximation for dimensionality reduction. Proceedings of the Conference Uncertainty in Artificial Intelligence (UAI), Online."},{"key":"ref_37","first-page":"160","article-title":"Density-based clustering based on hierarchical density estimates","volume":"Volume 7819","author":"Pei","year":"2013","journal-title":"Advances in Knowledge Discovery and Data Mining"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1145\/2733381","article-title":"Hierarchical density estimates for data clustering, visualization, and outlier detection","volume":"10","author":"Campello","year":"2015","journal-title":"ACM Trans. Knowl. Discov. Data"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"124429","DOI":"10.1016\/j.chemosphere.2019.124429","article-title":"Evaluation of the effectiveness of different indicator PCBs for estimating total PCB concentrations in environmental investigations","volume":"237","author":"Megson","year":"2019","journal-title":"Chemosphere"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1021\/es503427r","article-title":"Evaluation and interconversion of various indicator PCB schemes for \u2211PCB and dioxin-like PCB toxic equivalent levels in fish","volume":"49","author":"Gandhi","year":"2015","journal-title":"Environ. Sci. Technol."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"eado5534","DOI":"10.1126\/sciadv.ado5534","article-title":"Exploring global oceanic persistence and ecological effects of legacy persistent organic pollutants across five decades","volume":"10","author":"Zhang","year":"2024","journal-title":"Sci. Adv."},{"key":"ref_42","first-page":"75","article-title":"Patterns of PCB-138 bioaccumulation in small pelagic fish from the eastern Mediterranean Sea using explainable machine learning prediction","volume":"Volume 973","author":"Pap","year":"2021","journal-title":"Artificial Intelligence: Theory and Applications"}],"container-title":["Toxics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2305-6304\/14\/5\/393\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T04:19:22Z","timestamp":1777868362000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2305-6304\/14\/5\/393"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,2]]},"references-count":42,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["toxics14050393"],"URL":"https:\/\/doi.org\/10.3390\/toxics14050393","relation":{},"ISSN":["2305-6304"],"issn-type":[{"value":"2305-6304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,2]]}}}