Spatial Prediction of Opisthorchis viverrini Infection Risk Using Multi-Source Remote Sensing, Hexagonal Grid Optimization, and Ensemble Machine Learning: A Case Study From Northeastern Thailand.
5 affiliations
- 1Research Unit of Geoinformatics for Spatial Management Department of Geoinformatics Faculty of Informatics Mahasarakham University Maha Sarakham Thailand.
- 2Program in Animal Science Faculty of Agricultural Technology Sakon Nakhon Rajabhat University Sakon Nakhon Thailand.
- 3Department of Parasitology Faculty of Medicine Khon Kaen University Khon Kaen Thailand.
- 4Department of Agriculture and Resources Faculty of Natural Resources and Agro-Industry Kasetsart University Sakon Nakhon Thailand.
- 5Department of Civil & Architectural Engineering & Mechanics University of Arizona Tucson AZ USA.
Abstract
Opisthorchis viverrini (OV) infection is a major public health problem in northeastern Thailand, where it causes cholangiocarcinoma. This study developed a spatial prediction model for OV infection risk in Sakon Nakhon Province by integrating Sentinel-2, Sentinel-3, and CHIRPS data with hexagonal grid optimization and ensemble machine learning. Eleven environmental indices were aggregated using a newly developed Hd index, which identified an optimal hexagonal grid size of d = 2,100 m. Three models-Random Forest, XGBoost, and Multi-scale Geographically Weighted Regression (MGWR)-were compared using R2, root mean square error, ROC-AUC at exceedance thresholds (1%, 2%, 3%), 5-fold cross-validation, and SHAP analysis. XGBoost outperformed the other models, achieving the highest test-set R2 (0.894) and AUC (0.955) at the >3% threshold, with stable cross-validated performance (mean R2 = 0.83). SHAP analysis identified GVMI as the most influential predictor (mean |SHAP| = 0.125), followed by MNDWI (0.090) and SPI-6 (0.070). Moderate moisture conditions and above-average rainfall increased risk, whereas deep open water reduced it. The resulting risk map supports targeted surveillance and resource allocation for OV control in endemic areas.
Related
- Opisthorchis viverrini Control and Cholangiocarcinoma Incidence in Thailand: A Systematic Narrative Review and Proposed Interrupted Time Series Design
- Evaluating Autonomous LLM Agents Across Molecular Prediction and Optimization Benchmarks
- Prediction of early Toxoplasma gondii infection during pregnancy combining host biomarkers and machine learning
- Advanced machine learning framework for hole quality prediction and optimization in polycarbonate AWJD
- Ethnotaxonomy and phenotypic evidence for a zone of high common bean (Phaseolus vulgaris L.) diversity in northeastern Amazonian Peru
BibTeX
@article{littidej2026spatial,
title = {{Spatial Prediction of Opisthorchis viverrini Infection Risk Using Multi-Source Remote Sensing, Hexagonal Grid Optimization, and Ensemble Machine Learning: A Case Study From Northeastern Thailand.}},
author = {Patiwat Littidej and Benjamabhorn Pumhirunroj and Thidarut Boonmars and Atchara Artchayasawat and Nutchanat Buasri and Donald Slack},
journal = {GeoHealth},
year = {2026},
month = nov,
doi = {10.1029/2026gh002245},
url = {https://europepmc.org/article/MED/42999529},
note = {CC BY-NC},
}
RIS
TY - JOUR
TI - Spatial Prediction of Opisthorchis viverrini Infection Risk Using Multi-Source Remote Sensing, Hexagonal Grid Optimization, and Ensemble Machine Learning: A Case Study From Northeastern Thailand.
AU - Patiwat Littidej
AU - Benjamabhorn Pumhirunroj
AU - Thidarut Boonmars
AU - Atchara Artchayasawat
AU - Nutchanat Buasri
AU - Donald Slack
PY - 2026
DA - 2026/11/06
JO - GeoHealth
DO - 10.1029/2026gh002245
UR - https://europepmc.org/article/MED/42999529
AB - Opisthorchis viverrini (OV) infection is a major public health problem in northeastern Thailand, where it causes cholangiocarcinoma. This study developed a spatial prediction model for OV infection risk in Sakon Nakhon Province by integrating Sentinel-2, Sentinel-3, and CHIRPS data with hexagonal grid optimization and ensemble machine learning. Eleven environmental indices were aggregated using a newly developed Hd index, which identified an optimal hexagonal grid size of d = 2,100 m. Three models-Random Forest, XGBoost, and Multi-scale Geographically Weighted Regression (MGWR)-were compared using R2, root mean square error, ROC-AUC at exceedance thresholds (1%, 2%, 3%), 5-fold cross-validation, and SHAP analysis. XGBoost outperformed the other models, achieving the highest test-set R2 (0.894) and AUC (0.955) at the >3% threshold, with stable cross-validated performance (mean R2 = 0.83). SHAP analysis identified GVMI as the most influential predictor (mean |SHAP| = 0.125), followed by MNDWI (0.090) and SPI-6 (0.070). Moderate moisture conditions and above-average rainfall increased risk, whereas deep open water reduced it. The resulting risk map supports targeted surveillance and resource allocation for OV control in endemic areas.
SN - 2471-1403
ER -