Predicting chronic wasting disease in white-tailed deer at the county scale using machine learning.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
22 Jun 2024
22 Jun 2024
Historique:
received:
31
10
2023
accepted:
15
06
2024
medline:
23
6
2024
pubmed:
23
6
2024
entrez:
22
6
2024
Statut:
epublish
Résumé
Continued spread of chronic wasting disease (CWD) through wild cervid herds negatively impacts populations, erodes wildlife conservation, drains resource dollars, and challenges wildlife management agencies. Risk factors for CWD have been investigated at state scales, but a regional model to predict locations of new infections can guide increasingly efficient surveillance efforts. We predicted CWD incidence by county using CWD surveillance data depicting white-tailed deer (Odocoileus virginianus) in 16 eastern and midwestern US states. We predicted the binary outcome of CWD-status using four machine learning models, utilized five-fold cross-validation and grid search to pinpoint the best model, then compared model predictions against the subsequent year of surveillance data. Cross validation revealed that the Light Boosting Gradient model was the most reliable predictor given the regional data. The predictive model could be helpful for surveillance planning. Predictions of false positives emphasize areas that warrant targeted CWD surveillance because of similar conditions with counties known to harbor CWD. However, disagreements in positives and negatives between the CWD Prediction Web App predictions and the on-the-ground surveillance data one year later underscore the need for state wildlife agency professionals to use a layered modeling approach to ensure robust surveillance planning. The CWD Prediction Web App is at https://cwd-predict.streamlit.app/ .
Identifiants
pubmed: 38909151
doi: 10.1038/s41598-024-65002-7
pii: 10.1038/s41598-024-65002-7
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
14373Subventions
Organisme : U.S. Fish and Wildlife Service
ID : F23AP0048-00
Informations de copyright
© 2024. The Author(s).
Références
Williams, E. & Young, S. Chronic wasting disease of captive mule deer: a spongiform encephalopathy. J. Wildl. Dis. 16, 89–96 (1980).
doi: 10.7589/0090-3558-16.1.89
Poggiolini, I., Saverioni, D. & Parchi, P. Prion protein misfolding, strains, and neurotoxicity: An update from studies on mammalian prions. Int. J. Cell Biol. 2013, 24. https://doi.org/10.1155/2013/910314 (2013).
doi: 10.1155/2013/910314
United States Geological Survey (USGS). Distribution of chronic wasting disease in North America. https://www.usgs.gov/media/images/distribution-chronic-wasting-disease-north-america-0 . (2024).
Association of Fish and Wildlife Agencies (AFWA). Best management practices for surveillance, management, and control of chronic wasting disease. fishwildlife.org/application/files/1315/7054/8052/AFWA_CWD_BMP_First_Supplement_FINAL.pdf. (Washington, DC, USA, 2018).
Schuler, K., Hollingshead, N., Kelly, J., Applegate, R., & Yoest, C. Risk-based surveillance for chronic wasting disease in Tennessee. Tennessee Wildlife Resources Agency (TWRA) Wildlife Technical Report 18–4 (2018).
Chiavacci, S. J. The economic costs of chronic wasting disease in the United States. PLoS One 17(12), e0278366. https://doi.org/10.1371/journal.pone.0278366 (2022).
doi: 10.1371/journal.pone.0278366
pubmed: 36480524
pmcid: 9731425
Hanley, B. et al. Informing surveillance through the characterization of outbreak potential of chronic wasting disease in white-tailed deer. Ecolo. Model. 471, 110054. https://doi.org/10.1016/j.ecolmodel.2022.110054 (2022).
doi: 10.1016/j.ecolmodel.2022.110054
Miller, M., & Fischer, J. The first five (or more) decades of chronic wasting disease: Lessons for the five decades to come. Transactions of the North American wildlife and natural resources conference. Vol. 81 110–120 (2016).
Miller, M. & Williams, E. Chronic wasting disease of cervids. Curr. Top. Microbiol. Immunol. 284, 193–214 (2004).
pubmed: 15148993
Miller, M., Williams, E., Hobbs, N. & Wolfe, L. Environmental sources of prions transmission in mule deer. Emerg. Infect. Dis. 10(6), 1003–1006 (2004).
doi: 10.3201/eid1006.040010
pubmed: 15207049
pmcid: 3323154
Johnson, C., Pederson, J., Chappell, R., McKenzie, D. & Aiken, J. Oral transmissibility of prion disease is enhanced by binding to soil particles. PLoS Pathog. 3(7), 0874–0881 (2007).
doi: 10.1371/journal.ppat.0030093
New York State Interagency. CWD Risk Minimization Plan. https://extapps.dec.ny.gov/docs/wildlife_pdf/cwdpreventionplan2018.pdf (2018).
Ruiz, M., Kelly, A., Brown, W., Novakofski, J. & Mateus-Pinilla, N. Influence of landscape factors and management decisions on spatial and temporal patterns of the transmission of chronic wasting disease in white-tailed deer. Geospat. Health 8(1), 215–227 (2013).
doi: 10.4081/gh.2013.68
Nichols, T. et al. Detection of protease-resistant cervid prion protein in water from a CWD-endemic area. Prion 3(3), 171–183 (2009).
doi: 10.4161/pri.3.3.9819
pubmed: 19823039
pmcid: 2802782
Storm, D. et al. Deer density and disease prevalence influence transmission of chronic wasting disease in white-tailed deer. Ecosphere 4, 1–14 (2013).
doi: 10.1890/ES12-00141.1
Baier, L. E. Federalism, preemption, and the nationalization of American wildlife management: the dynamic balance between state and federal authority. (Rowman & Littlefield, Lanham, Maryland, USA, 2022).
Hilton, C. D. & Ballard, J. R. Wildlife regulations that affect veterinarians in the United States. in Fowler's Zoo and Wild Animal Medicine Current Therapy, Vol. 10. 43-46. https://doi.org/10.1016/B978-0-323-82852-9.00008-3 (2023).
Recknagel, F. Applications of machine learning to ecological modelling. Ecol. Model. 146(1–3), 303–310 (2001).
doi: 10.1016/S0304-3800(01)00316-7
Allan, B. et al. Futurecasting ecological research: The rise of technoecology. Ecosphere 9(5), e02163. https://doi.org/10.1002/ecs2.2163 (2018).
doi: 10.1002/ecs2.2163
Ahmed, M., Ishikawa, F., & Sugiyama, M. Testing machine learning code using polyhedral region. In Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 1533–1536 (2020).
Dietterich, T. Machine learning in ecosystem informatics and sustainability. In International Joint Conference on Artificial Intelligence (IJCAI) (Pasadena, CA, USA, 2009).
Tuia, D. et al. Perspectives in machine learning for wildlife conservation. Nat. Commun. 13, 792–807 (2022).
doi: 10.1038/s41467-022-27980-y
pubmed: 35140206
pmcid: 8828720
Nakagawa, S. et al. Rapid literature mapping on the recent use of machine learning for wildlife imagery. Peer Community J. https://doi.org/10.24072/pcjournal.261 (2023).
doi: 10.24072/pcjournal.261
Besson, M. et al. Towards the fully automated monitoring of ecological communities. Ecol. Lett. 25, 2753–2775 (2022).
doi: 10.1111/ele.14123
pubmed: 36264848
pmcid: 9828790
Robles-Fernández, Á., Santiago-Alarcon, D. & Lira-Noriega, A. Wildlife susceptibility to infectious diseases at global scales. Proc. Natl. Acad. Sci. 119(35), e2122851119. https://doi.org/10.1073/pnas.2122851119 (2022).
doi: 10.1073/pnas.2122851119
pubmed: 35994656
pmcid: 9436312
Pillai, N., Ramkumar, M. & Nanduri, B. Artificial intelligence models for zoonotic pathogens: A survey. Microorganisms 10(10), 1911–1931 (2022).
doi: 10.3390/microorganisms10101911
pubmed: 36296187
pmcid: 9607465
Breiman, L. Random forests. Mach. Learn. 45, 5–32 (2001).
doi: 10.1023/A:1010933404324
Quinlan, J. Induction of decision trees. Mach. Learn. 1(1), 81–106 (1986).
doi: 10.1007/BF00116251
Friedman, J. Greedy function approximation: A gradient boosting machine. Ann. Stat. 29(5), 1189–1232 (2001).
doi: 10.1214/aos/1013203451
Ke, G., et al. LightGBM: A highly efficient gradient boosting decision tree. NIPS'17: Proceedings of the 31st International Conference on Neural Information Processing Systems 3149–3157 (2017).
Staartjes, V. & Kernback, J. Foundations of machine learning-based clinical predictions modeling: Part III—model evaluation and other points of significance. In Machine learning in clinical neuroscience. Acta Neurochirurgica Supplement Vol. 134 (eds Staartjes, V. et al.) (Springer, 2022). https://doi.org/10.1007/978-3-030-85292-4_4 .
doi: 10.1007/978-3-030-85292-4_4
R Statistical Computing (R). R package: Confusion matrix. https://search.r-project.org/CRAN/refmans/qwraps2/html/confusion_matrix.html#:~:text=sensitivity%20%3D%20TP%20%2F%20(TP%20%2B,TN%20%2F%20(TN%20%2B%20FN ). (2023).
Schuler, K., et al. North American wildlife agency CWD testing and ancillary data (2000–2022) [Dataset]. Cornell University Library eCommons Repository (2024). https://doi.org/10.7298/7txw-2681.2
Michigan Department of Natural Resources (MIDNR). CWD and Cervidae regulations in North America NEW. https://michigan.gov/dnr/managing-resources/wildlife/cwd/hunters/cwd-and-cervidae-regulations-in-north-america . (2022).
Green, M. L., Manjerovic, M. B., Mateus-Pinilla, N. & Novakofski, J. Genetic assignment tests reveal dispersal of white-tailed deer: Implication for chronic wasting disease. J. Mammal. 95(3), 646–654 (2014).
doi: 10.1644/13-MAMM-A-167
Conner, M. M. et al. The relationship between harvest management and chronic wasting disease prevalence trends in western mule deer (Odocoileus Hemionus) herds. J. Wildl. Dis. 57(4), 831–843 (2021).
doi: 10.7589/JWD-D-20-00226
pubmed: 34648639
Kuznetsova, A., McKenzie, D., Banser, P., Siddique, T. & Aiken, J. Potential role of soil properties in the spread of CWD in western Canada. Prion 8(1), 92–99 (2014).
doi: 10.4161/pri.28467
pubmed: 24618673
pmcid: 7030902
Walter, W., Walsh, D., Farnsworth, M., Winkelman, D. & Miller, M. Soil clay content underlies prion infection odds. Nat. Commun. 2, 200–206 (2011).
doi: 10.1038/ncomms1203
Dorak, S. et al. Clay content and pH: Soil characteristic associations with the persistent presence of chronic wasting disease in northern Illinois. Sci. Rep. 7(1), 18062–18072 (2017).
doi: 10.1038/s41598-017-18321-x
pubmed: 29273783
pmcid: 5741720
Wyckoff, A. et al. Clay components in soil dictate environmental stability and bioavailability of cervid prions in mice. Front. Microbiol. 7, 1–11 (2016).
doi: 10.3389/fmicb.2016.01885
Booth, C., Lichtenberg, S., Chappell, R. & Pedersen, J. Chemical inactivation of prions is altered by binding to the soil mineral montmorillonite. ACS Infect. Dis. 7(4), 859–870 (2021).
doi: 10.1021/acsinfecdis.0c00860
pubmed: 33787209
Ibe, O. C. Laws of large numbers. Basic concepts in probability. In Markov processes for stochastic modeling 2nd edn (Elsevier, 2013). https://doi.org/10.1016/C2012-0-06106-6 .
doi: 10.1016/C2012-0-06106-6
Cunningham, C., Peery, R., Dao, A., McKenzie, D. & Coltman, D. Predicting the spread-risk potential of chronic wasting disease to sympatric ungulate species. Prion 14(1), 56–66 (2020).
doi: 10.1080/19336896.2020.1720486
Tidd, J. Trophy-hunting business owner admits to illegally importing deer to Kansas (Accessed 10 August 2018); https://www.kansas.com/sports/outdoors/article198543619.html
Fitzgerald, R. They smuggled deer to Forrest County, feds say. But that wasn't the only problem (Accessed 10 August 2018); https://www.sunherald.com/news/local/crime/article173323226.html
Organ, J., et al. The North American Model of Wildlife Conservation. The Wildlife Society Technical Review 12–04. The Wildlife Society. (Bethesda, Maryland, USA, 2012).
Centers for Disease Control (CDC). Chronic wasting disease (occurrence) (Accessed 15 April 2024); https://www.cdc.gov/prions/cwd/occurrence.html
Booth, J. G. et al. Sample size for estimating disease prevalence in free-ranging wildlife: A Bayesian modeling approach. J. Agric. Biol. Environ. Stat. https://doi.org/10.1007/s13253-023-00578-7 (2023).
doi: 10.1007/s13253-023-00578-7
Schuler, K., Jenks, J., Klaver, R., Jennelle, C. & Bowyer, R. Chronic wasting disease detection and mortality sources in a semi-protected deer population. Wildl. Biol. 1, 1–7 (2018).
doi: 10.2981/wlb.00437
United States Department of Agriculture and Animal and Plant Health Inspection Service Veterinary Services. Chronic wasting disease program standards. www.aphis.usda.gov/sites/default/files/cwd-program-standards.pdf (2019).
Walter, W. D. et al. Predicting the odds of chronic wasting disease with Habitat Risk software. Spat. Spatio-temporal Epidemiol. 49, 100650. https://doi.org/10.1016/j.sste.2024.100650 (2024).
doi: 10.1016/j.sste.2024.100650
Winter, S. N., Kirchgessner, M. S., Frimpong, E. A. & Escobar, L. E. A landscape epidemiological approach for predicting chronic wasting disease: A case study in Virginia, US. Front. Vet. Sci. https://doi.org/10.3389/fvets.2021.698767 (2021).
doi: 10.3389/fvets.2021.698767
pubmed: 34504887
pmcid: 8421794
Hefley, T., Hooten, M., Russell, R., Walsh, D. & Powell, J. When mechanism matters: Bayesian forecasting using models of ecological diffusion. Ecol. Lett. 20(5), 640–650 (2017).
doi: 10.1111/ele.12763
pubmed: 28371055
Todman, L., Bush, A. & Hood, A. “Small data” for big insights in ecology. Trends Ecol. Evol. 38(7), 615–622 (2023).
doi: 10.1016/j.tree.2023.01.015
pubmed: 36797167
Albon, C. Machine learning with Python cookbook (O’Reilly Media Inc., 2018).
Shalev-Shwartz, S. & Ben-David, S. Understanding machine learning: From theory to algorithms (Cambridge University Press, 2014).
doi: 10.1017/CBO9781107298019
Pedregosa, F. et al. Scikit-learn: Machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011).
Hastie, T., Tibshirani, R. & Friedman, J. The elements of statistical learning: Data mining, inference and prediction 2nd edn. (Springer, 2009). https://doi.org/10.1007/978-0-387-84858-7 .
doi: 10.1007/978-0-387-84858-7
Pudjihartono, N., Fadason, T., Kempa-Liehr, A. & O’Sullivan, J. A review of feature selection methods for machine learning-based disease risk prediction. Front. Bioinform. 2, 1–17 (2022).
doi: 10.3389/fbinf.2022.927312
QGIS.org, QGIS Geographic Information System. QGIS Association. http://www.qgis.org (2024).