1
|
Singleton AL, Glidden CK, Chamberlin AJ, Tuan R, Palasio RGS, Pinter A, Caldeira RL, Mendonça CLF, Carvalho OS, Monteiro MV, Athni TS, Sokolow SH, Mordecai EA, De Leo GA. Species distribution modeling for disease ecology: A multi-scale case study for schistosomiasis host snails in Brazil. PLOS GLOBAL PUBLIC HEALTH 2024; 4:e0002224. [PMID: 39093879 PMCID: PMC11296653 DOI: 10.1371/journal.pgph.0002224] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/06/2023] [Accepted: 07/17/2024] [Indexed: 08/04/2024]
Abstract
Species distribution models (SDMs) are increasingly popular tools for profiling disease risk in ecology, particularly for infectious diseases of public health importance that include an obligate non-human host in their transmission cycle. SDMs can create high-resolution maps of host distribution across geographical scales, reflecting baseline risk of disease. However, as SDM computational methods have rapidly expanded, there are many outstanding methodological questions. Here we address key questions about SDM application, using schistosomiasis risk in Brazil as a case study. Schistosomiasis is transmitted to humans through contact with the free-living infectious stage of Schistosoma spp. parasites released from freshwater snails, the parasite's obligate intermediate hosts. In this study, we compared snail SDM performance across machine learning (ML) approaches (MaxEnt, Random Forest, and Boosted Regression Trees), geographic extents (national, regional, and state), types of presence data (expert-collected and publicly-available), and snail species (Biomphalaria glabrata, B. straminea, and B. tenagophila). We used high-resolution (1km) climate, hydrology, land-use/land-cover (LULC), and soil property data to describe the snails' ecological niche and evaluated models on multiple criteria. Although all ML approaches produced comparable spatially cross-validated performance metrics, their suitability maps showed major qualitative differences that required validation based on local expert knowledge. Additionally, our findings revealed varying importance of LULC and bioclimatic variables for different snail species at different spatial scales. Finally, we found that models using publicly-available data predicted snail distribution with comparable AUC values to models using expert-collected data. This work serves as an instructional guide to SDM methods that can be applied to a range of vector-borne and zoonotic diseases. In addition, it advances our understanding of the relevant environment and bioclimatic determinants of schistosomiasis risk in Brazil.
Collapse
Affiliation(s)
- Alyson L. Singleton
- Emmett Interdisciplinary Program in Environment and Resources, Stanford University, Stanford, California, United States of America
| | - Caroline K. Glidden
- Department of Biology, Stanford University, Stanford, California, United States of America
- Institute for Human-centered Artificial Intelligence, Stanford University, Stanford, California, United States of America
| | - Andrew J. Chamberlin
- Department of Oceans, Hopkins Marine Station, Stanford University, Pacific Grove, California, United States of America
| | | | | | | | | | | | - Omar S. Carvalho
- Fiocruz Minas/Belo Horizonte-Minas Gerais, Belo Horizonte, Brazil
| | - Miguel V. Monteiro
- Geoinformation & Earth Observation Division, National Institute for Space Research (INPE), São Paulo, Brazil
| | - Tejas S. Athni
- Department of Biology, Stanford University, Stanford, California, United States of America
- Harvard Medical School, Boston, Massachusetts, United States of America
| | - Susanne H. Sokolow
- Department of Oceans, Hopkins Marine Station, Stanford University, Pacific Grove, California, United States of America
- Marine Science Institute, University of California Santa Barbara, Santa Barbara, California, United States of America
| | - Erin A. Mordecai
- Department of Biology, Stanford University, Stanford, California, United States of America
- Woods Institute for the Environment, Stanford University, Stanford, California, United States of America
| | - Giulio A. De Leo
- Department of Oceans, Hopkins Marine Station, Stanford University, Pacific Grove, California, United States of America
- Woods Institute for the Environment, Stanford University, Stanford, California, United States of America
| |
Collapse
|
2
|
Glidden CK, Singleton AL, Chamberlin A, Tuan R, Palasio RGS, Caldeira RL, Monteiro AMV, Lwiza KMM, Liu P, Silva V, Athni TS, Sokolow SH, Mordecai EA, De Leo GA. Climate and urbanization drive changes in the habitat suitability of Schistosoma mansoni competent snails in Brazil. Nat Commun 2024; 15:4838. [PMID: 38898012 PMCID: PMC11186836 DOI: 10.1038/s41467-024-48335-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/11/2024] [Accepted: 04/29/2024] [Indexed: 06/21/2024] Open
Abstract
Schistosomiasis is a neglected tropical disease caused by Schistosoma parasites. Schistosoma are obligate parasites of freshwater Biomphalaria and Bulinus snails, thus controlling snail populations is critical to reducing transmission risk. As snails are sensitive to environmental conditions, we expect their distribution is significantly impacted by global change. Here, we used machine learning, remote sensing, and 30 years of snail occurrence records to map the historical and current distribution of forward-transmitting Biomphalaria hosts throughout Brazil. We identified key features influencing the distribution of suitable habitat and determined how Biomphalaria habitat has changed with climate and urbanization over the last three decades. Our models show that climate change has driven broad shifts in snail host range, whereas expansion of urban and peri-urban areas has driven localized increases in habitat suitability. Elucidating change in Biomphalaria distribution-while accounting for non-linearities that are difficult to detect from local case studies-can help inform schistosomiasis control strategies.
Collapse
Grants
- R01 AI102918 NIAID NIH HHS
- R01 AI168097 NIAID NIH HHS
- R35 GM133439 NIGMS NIH HHS
- T32 GM144273 NIGMS NIH HHS
- This work was supported by the Belmont Collaborative Forum on Climate, Environment and Health (US-NSF ICER-2024383, FAPESP), by a grant of the Stanford Center for Innovation in Global Health, and the Stanford Program for Disease Ecology, Health and the Environment. GADL was partially supported also by an NSF EEID grant (DEB – 2011179). EAM and CKG were supported by the National Science Foundation and the Fogarty International Center (grant no. DEB-2011147). EAM was additionally supported by the National Institute of Allergy and Infectious Diseases (grant nos R01AI168097 and R01AI102918), the National Institutes of Health (grant no. R35GM133439), and by seed grants from the Stanford Woods Institute for the Environment, King Center on Global Development, Center for Innovation in Global Health, and the Terman Award. CKG was additionally supported by a Stanford Institute for Human-centered Artificial Intelligence Postdoctoral Fellowship. TSA was supported by the National Institute of General Medical Sciences under grant number T32GM144273. SHS was supported by NSF grant number 2024385.
Collapse
Affiliation(s)
- Caroline K Glidden
- Stanford University, Department of Biology, Institute for Human-Centered AI, Stanford, CA, USA.
- Stanford University, Department of Biology, Stanford, CA, USA.
| | - Alyson L Singleton
- Stanford University, Emmett Interdisciplinary Program in Environment and Resources, Stanford, CA, USA
| | - Andrew Chamberlin
- Stanford University, Department of Oceans, Hopkins Marine Station, Pacific Grove, CA, USA
| | | | | | | | | | | | - Ping Liu
- Stony Brook University, Stony Brook, New York, NY, USA
| | - Vivian Silva
- National Institute for Space Research, São José dos Campos, Brazil
| | | | - Susanne H Sokolow
- Stanford University, Woods Institute for the Environment, Stanford, CA, USA
- Marine Science Institute, University of California, Santa Barbara, CA, USA
| | - Erin A Mordecai
- Stanford University, Department of Biology, Institute for Human-Centered AI, Stanford, CA, USA
- Stanford University, Department of Biology, Stanford, CA, USA
| | - Giulio A De Leo
- Stanford University, Department of Oceans, Hopkins Marine Station, Pacific Grove, CA, USA
| |
Collapse
|
3
|
Glidden CK, Singleton AL, Chamberlin A, Tuan R, Palasio RGS, Caldeira RL, Monteiro AMV, Lwiza KMM, Liu P, Silva V, Athni TS, Sokolow SH, Mordecai EA, De Leo GA. Climate and urbanization drive changes in the habitat suitability of Schistosoma mansoni competent snails in Brazil. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2024:2024.01.03.574120. [PMID: 38260310 PMCID: PMC10802398 DOI: 10.1101/2024.01.03.574120] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/24/2024]
Abstract
Schistosomiasis is a neglected tropical disease caused by Schistosoma parasites. Schistosoma are obligate parasites of freshwater Biomphalaria snails, so controlling snail populations is critical to reducing transmission risk. As snails are sensitive to environmental conditions, we expect their distribution is significantly impacted by global change. Here, we leveraged machine learning, remote sensing, and 30 years of snail occurrence records to map the historical and current distribution of competent Biomphalaria throughout Brazil. We identified key features influencing the distribution of suitable habitat and determined how Biomphalaria habitat has changed with climate and urbanization over the last three decades. Our models show that climate change has driven broad shifts in snail host range, whereas expansion of urban and peri-urban areas has driven localized increases in habitat suitability. Elucidating change in Biomphalaria distribution - while accounting for non-linearities that are difficult to detect from local case studies - can help inform schistosomiasis control strategies.
Collapse
|