Interpretable machine learning analysis of environmental characteristics on bacillary dysentery in Sichuan Province

BackgroundBacterial dysentery (BD) is a leading cause of diarrhea-related mortality globally, with its incidence heavily influenced by environmental factors. However, a climate zone-specific predictive model for BD was currently lacking in Sichuan Province.ObjectiveThis study aims to employ interpre...

Full description

Saved in:
Bibliographic Details
Main Authors: Yao Zhang, Qiao-Lin Wang, Wei Peng, Meng-Yuan Zhang, Yao Qin, Lun Zhang, Rong-Jie Wei, Dian-Ju Kang
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-07-01
Series:Frontiers in Public Health
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fpubh.2025.1598247/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849318329866518528
author Yao Zhang
Qiao-Lin Wang
Wei Peng
Meng-Yuan Zhang
Yao Qin
Lun Zhang
Rong-Jie Wei
Dian-Ju Kang
author_facet Yao Zhang
Qiao-Lin Wang
Wei Peng
Meng-Yuan Zhang
Yao Qin
Lun Zhang
Rong-Jie Wei
Dian-Ju Kang
author_sort Yao Zhang
collection DOAJ
description BackgroundBacterial dysentery (BD) is a leading cause of diarrhea-related mortality globally, with its incidence heavily influenced by environmental factors. However, a climate zone-specific predictive model for BD was currently lacking in Sichuan Province.ObjectiveThis study aims to employ interpretable machine learning to explore the influence of environmental factors on BD incidence across different climate zones and to elucidate their interaction mechanisms.MethodsMonthly data on meteorological and ecological factors, along with BD case reports, were collected from 183 counties in Sichuan Province (2005–2023). The eXtreme Gradient Boosting (XGBoost) algorithm was employed to assess the influence of key environmental features, including precipitation, temperature, PM10, potential evaporation, vegetation cover, and NDVI, on BD incidence. To enhance interpretability, the model’s outputs were visualized and explained using SHapley Additive Explanations (SHAP).ResultsA machine learning model was developed to assess the impact of environmental factors on BD incidence across different climate zones. The findings revealed significant spatial heterogeneity in key drivers of BD. In the Central Subtropical Humid Climate Zone, BD incidence was predominantly influenced by average temperature, PM10, and minimum temperature. In the Subtropical Semi-Humid Climate Zone, potential evaporation, PM10, and precipitation emerged as the primary determinants. In the Plateau Cold Climate Zone, PM10, minimum temperature, and precipitation were the most significant factors. Notably, PM10 consistently showed a positive correlation with BD across all climate zones. Furthermore, average temperature showed a positive association with BD in the Central Subtropical Humid Climate Zone, while potential evaporation and minimum temperature demonstrated similar positive relationships in the Subtropical Semi-Humid and Plateau Cold Climate Zones, respectively. Additionally, precipitation displayed a U-shaped relationship with BD risk in both the Subtropical Semi-Humid and Plateau Cold Climate Zones.ConclusionThis study developed a climate zone-specific predictive model for BD, systematically evaluating the interactions between environmental factors and BD dynamics. The findings provide a scientific basis for refining targeted public health intervention strategies.
format Article
id doaj-art-38f9eb82ea6e411ba324cd5d70177e28
institution Kabale University
issn 2296-2565
language English
publishDate 2025-07-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Public Health
spelling doaj-art-38f9eb82ea6e411ba324cd5d70177e282025-08-20T03:50:53ZengFrontiers Media S.A.Frontiers in Public Health2296-25652025-07-011310.3389/fpubh.2025.15982471598247Interpretable machine learning analysis of environmental characteristics on bacillary dysentery in Sichuan ProvinceYao Zhang0Qiao-Lin Wang1Wei Peng2Meng-Yuan Zhang3Yao Qin4Lun Zhang5Rong-Jie Wei6Dian-Ju Kang7Department of Emergency Management, Sichuan Center for Diseases Control and Prevention, Chengdu, ChinaWest China School of Public Health/West China Fourth Hospital, Sichuan University, Chengdu, ChinaDepartment of Health Education Institute, Sichuan Center for Diseases Control and Prevention, Chengdu, ChinaDepartment of Emergency Management, Sichuan Center for Diseases Control and Prevention, Chengdu, ChinaDepartment of Emergency Management, Sichuan Center for Diseases Control and Prevention, Chengdu, ChinaDepartment of Emergency Management, Sichuan Center for Diseases Control and Prevention, Chengdu, ChinaDepartment of Emergency Management, Sichuan Center for Diseases Control and Prevention, Chengdu, ChinaDepartment of Emergency Management, Sichuan Center for Diseases Control and Prevention, Chengdu, ChinaBackgroundBacterial dysentery (BD) is a leading cause of diarrhea-related mortality globally, with its incidence heavily influenced by environmental factors. However, a climate zone-specific predictive model for BD was currently lacking in Sichuan Province.ObjectiveThis study aims to employ interpretable machine learning to explore the influence of environmental factors on BD incidence across different climate zones and to elucidate their interaction mechanisms.MethodsMonthly data on meteorological and ecological factors, along with BD case reports, were collected from 183 counties in Sichuan Province (2005–2023). The eXtreme Gradient Boosting (XGBoost) algorithm was employed to assess the influence of key environmental features, including precipitation, temperature, PM10, potential evaporation, vegetation cover, and NDVI, on BD incidence. To enhance interpretability, the model’s outputs were visualized and explained using SHapley Additive Explanations (SHAP).ResultsA machine learning model was developed to assess the impact of environmental factors on BD incidence across different climate zones. The findings revealed significant spatial heterogeneity in key drivers of BD. In the Central Subtropical Humid Climate Zone, BD incidence was predominantly influenced by average temperature, PM10, and minimum temperature. In the Subtropical Semi-Humid Climate Zone, potential evaporation, PM10, and precipitation emerged as the primary determinants. In the Plateau Cold Climate Zone, PM10, minimum temperature, and precipitation were the most significant factors. Notably, PM10 consistently showed a positive correlation with BD across all climate zones. Furthermore, average temperature showed a positive association with BD in the Central Subtropical Humid Climate Zone, while potential evaporation and minimum temperature demonstrated similar positive relationships in the Subtropical Semi-Humid and Plateau Cold Climate Zones, respectively. Additionally, precipitation displayed a U-shaped relationship with BD risk in both the Subtropical Semi-Humid and Plateau Cold Climate Zones.ConclusionThis study developed a climate zone-specific predictive model for BD, systematically evaluating the interactions between environmental factors and BD dynamics. The findings provide a scientific basis for refining targeted public health intervention strategies.https://www.frontiersin.org/articles/10.3389/fpubh.2025.1598247/fullbacterial dysenteryclimate zonesenvironmental characteristicsXGBoostSHAP
spellingShingle Yao Zhang
Qiao-Lin Wang
Wei Peng
Meng-Yuan Zhang
Yao Qin
Lun Zhang
Rong-Jie Wei
Dian-Ju Kang
Interpretable machine learning analysis of environmental characteristics on bacillary dysentery in Sichuan Province
Frontiers in Public Health
bacterial dysentery
climate zones
environmental characteristics
XGBoost
SHAP
title Interpretable machine learning analysis of environmental characteristics on bacillary dysentery in Sichuan Province
title_full Interpretable machine learning analysis of environmental characteristics on bacillary dysentery in Sichuan Province
title_fullStr Interpretable machine learning analysis of environmental characteristics on bacillary dysentery in Sichuan Province
title_full_unstemmed Interpretable machine learning analysis of environmental characteristics on bacillary dysentery in Sichuan Province
title_short Interpretable machine learning analysis of environmental characteristics on bacillary dysentery in Sichuan Province
title_sort interpretable machine learning analysis of environmental characteristics on bacillary dysentery in sichuan province
topic bacterial dysentery
climate zones
environmental characteristics
XGBoost
SHAP
url https://www.frontiersin.org/articles/10.3389/fpubh.2025.1598247/full
work_keys_str_mv AT yaozhang interpretablemachinelearninganalysisofenvironmentalcharacteristicsonbacillarydysenteryinsichuanprovince
AT qiaolinwang interpretablemachinelearninganalysisofenvironmentalcharacteristicsonbacillarydysenteryinsichuanprovince
AT weipeng interpretablemachinelearninganalysisofenvironmentalcharacteristicsonbacillarydysenteryinsichuanprovince
AT mengyuanzhang interpretablemachinelearninganalysisofenvironmentalcharacteristicsonbacillarydysenteryinsichuanprovince
AT yaoqin interpretablemachinelearninganalysisofenvironmentalcharacteristicsonbacillarydysenteryinsichuanprovince
AT lunzhang interpretablemachinelearninganalysisofenvironmentalcharacteristicsonbacillarydysenteryinsichuanprovince
AT rongjiewei interpretablemachinelearninganalysisofenvironmentalcharacteristicsonbacillarydysenteryinsichuanprovince
AT dianjukang interpretablemachinelearninganalysisofenvironmentalcharacteristicsonbacillarydysenteryinsichuanprovince