Zobrazit v EDS

A machine learning approach to facilitate parasitic egg identification in a conspecific brood parasite.

Uloženo v:
Podrobná bibliografie
Název: A machine learning approach to facilitate parasitic egg identification in a conspecific brood parasite.
Autoři: Hughes AE; Department of Psychology, University of Essex, Colchester CO4 3SQ, UK., Mari L; Department of Biological and Environmental Science, University of Jyväskylä, 40014 Jyväskylä, Finland.; Institute of Vertebrate Biology Czech Academy of Sciences, 603 65 Brno, Czech Republic., Troscianko J; Centre for Ecology and Conservation, University of Exeter, Penryn TR10 9FE, UK., Jelínek V; Institute of Vertebrate Biology Czech Academy of Sciences, 603 65 Brno, Czech Republic., Albrecht T; Institute of Vertebrate Biology Czech Academy of Sciences, 603 65 Brno, Czech Republic.; Department of Zoology, Charles University, 128 44 Prague, Czech Republic., Šulc M; Institute of Vertebrate Biology Czech Academy of Sciences, 603 65 Brno, Czech Republic.
Zdroj: Proceedings. Biological sciences [Proc Biol Sci] 2025 Nov; Vol. 292 (2059), pp. 20252085. Date of Electronic Publication: 2025 Nov 26.
Způsob vydávání: Journal Article
Jazyk: English
Informace o časopise: Publisher: Royal Society of London Country of Publication: England NLM ID: 101245157 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1471-2954 (Electronic) Linking ISSN: 09628452 NLM ISO Abbreviation: Proc Biol Sci Subsets: MEDLINE
Imprint Name(s): Original Publication: London : Royal Society of London, c1990-
Výrazy ze slovníku MeSH: Machine Learning* , Nesting Behavior* , Swallows*/parasitology , Swallows*/physiology , Ovum*, Animals
Abstrakt: Avian brood parasitism offers an excellent system for studying coevolution. While more common than interspecific parasitism, conspecific brood parasitism (CBP) is less studied owing to the challenge of detecting parasitic eggs. Molecular genotyping accurately detects CBP, but its high cost has led researchers to explore egg appearance as a more accessible alternative. Barn swallows ( Hirundo rustica ) are suspected conspecific brood parasites, yet parasitic egg detection has largely relied on subjective human assessment. Here, we used UV-visible photographs of genetically confirmed non-parasitized barn swallow clutches and simulated parasitism to compare the accuracy of human assessment with supervised machine learning models. Participants and models completed two classification tasks, identifying parasitic eggs from either six or two options. Both humans and the 'leave-one-clutch-out' model performed better than chance, with accuracies of 72 and 87% (humans) and 76 and 92% (models). An improved 'leave-one-egg-out' model achieved 97% accuracy, greatly exceeding human performance, likely by integrating more visual information, with egg dimensions being the most important trait, followed by colour and spotting pattern. We present a complete and accessible pipeline for replicating our supervised models, offering a powerful tool to identify parasitic eggs in other species also, and advance research on the evolution of egg phenotypes.
References: J Anim Ecol. 2018 May;87(3):533-545. (PMID: 29111567)
J Exp Psychol Hum Percept Perform. 2019 Sep;45(9):1248-1264. (PMID: 31219282)
Nat Commun. 2014 Jun 18;5:4117. (PMID: 24939367)
Biol Rev Camb Philos Soc. 2006 Aug;81(3):383-406. (PMID: 16740199)
PLoS One. 2021 Mar 4;16(3):e0248021. (PMID: 33661988)
Ecol Evol. 2023 Jul 09;13(7):e10170. (PMID: 37435021)
Methods Ecol Evol. 2015 Nov;6(11):1320-1331. (PMID: 27076902)
Nat Methods. 2012 Jul;9(7):671-5. (PMID: 22930834)
Anim Cogn. 2022 Aug;25(4):991-1002. (PMID: 35778546)
J Exp Biol. 2008 Aug;211(Pt 15):2519-23. (PMID: 18626087)
Res Social Adm Pharm. 2021 May;17(5):1004-1011. (PMID: 33162380)
J Exp Psychol Hum Percept Perform. 2020 Sep;46(9):942-964. (PMID: 32378936)
J Exp Zool B Mol Dev Evol. 2021 Dec;336(8):595-605. (PMID: 32400035)
J Neurosci Methods. 2007 May 15;162(1-2):8-13. (PMID: 17254636)
Behav Processes. 2020 May;174:104087. (PMID: 32088295)
Proc Biol Sci. 2025 Nov;292(2059):20252085. (PMID: 41290166)
Grant Information: Czech Science Foundation
Contributed Indexing: Keywords: artificial intelligence; cognition; colour; egg phenotype; intraspecific nest parasitism; pattern
Entry Date(s): Date Created: 20251125 Date Completed: 20251125 Latest Revision: 20251129
Update Code: 20251129
PubMed Central ID: PMC12646787
DOI: 10.1098/rspb.2025.2085
PMID: 41290166
Databáze: MEDLINE
Popis
Abstrakt:Avian brood parasitism offers an excellent system for studying coevolution. While more common than interspecific parasitism, conspecific brood parasitism (CBP) is less studied owing to the challenge of detecting parasitic eggs. Molecular genotyping accurately detects CBP, but its high cost has led researchers to explore egg appearance as a more accessible alternative. Barn swallows ( Hirundo rustica ) are suspected conspecific brood parasites, yet parasitic egg detection has largely relied on subjective human assessment. Here, we used UV-visible photographs of genetically confirmed non-parasitized barn swallow clutches and simulated parasitism to compare the accuracy of human assessment with supervised machine learning models. Participants and models completed two classification tasks, identifying parasitic eggs from either six or two options. Both humans and the 'leave-one-clutch-out' model performed better than chance, with accuracies of 72 and 87% (humans) and 76 and 92% (models). An improved 'leave-one-egg-out' model achieved 97% accuracy, greatly exceeding human performance, likely by integrating more visual information, with egg dimensions being the most important trait, followed by colour and spotting pattern. We present a complete and accessible pipeline for replicating our supervised models, offering a powerful tool to identify parasitic eggs in other species also, and advance research on the evolution of egg phenotypes.
ISSN:1471-2954
DOI:10.1098/rspb.2025.2085