Projecting lyme disease risk in the United States: A machine learning approach integrating environmental, socioeconomic and vector factors

Objective: Lyme disease, caused by Borrelia burgdorferi and transmitted by blacklegged ticks (Ixodes species), is the most common vector-borne disease in the United States. Its spatiotemporal dynamics are influenced by environmental and socioeconomic factors, yet the impacts of the COVID-19 pandemic...

Full description

Saved in:
Bibliographic Details
Main Authors: Yan-Qun Sun, Xiao-Yan Zhu, Tian-Ci Fan, Tian Ma, Hong-Han Ge, Rui-Fang Shi, Xu Wang, Wei Li, Jie-Yun Yin, Ye Tian
Format: Article
Language:English
Published: Elsevier 2025-12-01
Series:One Health
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2352771425001478
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849682855352860672
author Yan-Qun Sun
Xiao-Yan Zhu
Tian-Ci Fan
Tian Ma
Hong-Han Ge
Rui-Fang Shi
Xu Wang
Wei Li
Jie-Yun Yin
Ye Tian
author_facet Yan-Qun Sun
Xiao-Yan Zhu
Tian-Ci Fan
Tian Ma
Hong-Han Ge
Rui-Fang Shi
Xu Wang
Wei Li
Jie-Yun Yin
Ye Tian
author_sort Yan-Qun Sun
collection DOAJ
description Objective: Lyme disease, caused by Borrelia burgdorferi and transmitted by blacklegged ticks (Ixodes species), is the most common vector-borne disease in the United States. Its spatiotemporal dynamics are influenced by environmental and socioeconomic factors, yet the impacts of the COVID-19 pandemic on Lyme disease remain unclear. Methods: We analyzed county-level Lyme disease surveillance data (2001−2022) alongside environmental, socioeconomic, and tick vector data. Using machine learning models (Random Forest, Boosted Regression Trees, and XGBoost) and Shapley Additive Explanations (SHAP), we evaluated the influence of key predictors on Lyme disease risk. Predicted cases for 2020–2022 were compared with actual reports to assess the pandemic's effects. Results: Lyme disease cases rose from 16,862 in 2001 to 61,802 in 2022, with geographic expansion into southeastern regions. Population density, ecological niche of I. scapularis, and maximum temperature were presented as the key predictors of disease risk. The COVID-19 pandemic severely disrupted reporting dynamics, with 2020 and 2021 cases falling 43.9 % (95 % CI: 41.2–46.7 %) and 22.0 % (95 % CI: 19.5–24.5 %) below predictions, respectively—a decline most pronounced in the Northeast and linked to reduced healthcare access and outdoor activity during lockdowns. Conclusion: Our findings highlight the complex interactions of environmental, socioeconomic, and behavioral factors in Lyme disease dynamics, including the significant impact of the COVID-19 pandemic on disease reporting. These insights underscore the need for integrated, data-driven public health strategies to mitigate Lyme disease risk in the United States.
format Article
id doaj-art-2cc22b2628914edf8b93af640bd77a71
institution DOAJ
issn 2352-7714
language English
publishDate 2025-12-01
publisher Elsevier
record_format Article
series One Health
spelling doaj-art-2cc22b2628914edf8b93af640bd77a712025-08-20T03:24:03ZengElsevierOne Health2352-77142025-12-012110111110.1016/j.onehlt.2025.101111Projecting lyme disease risk in the United States: A machine learning approach integrating environmental, socioeconomic and vector factorsYan-Qun Sun0Xiao-Yan Zhu1Tian-Ci Fan2Tian Ma3Hong-Han Ge4Rui-Fang Shi5Xu Wang6Wei Li7Jie-Yun Yin8Ye Tian9Children's Hospital of Nanjing Medical University, Nanjing, China; Correspondence to: Yan-Qun Sun, Ye Tian, Children's Hospital of Nanjing Medical University, 72 Guangzhou Road, Nanjing 210008, PR China.Suzhou Municipal Center for Disease Control and Prevention, Suzhou, ChinaChildren's Hospital of Nanjing Medical University, Nanjing, ChinaYale Institute for Biospheric Studies, Yale University, New Haven, CT, United States; School of the Environment, Yale University, New Haven, CT, United StatesSchool of Public Health and Health Management, Shandong, Shandong First Medical University, Jinan, ChinaThe Affiliated Yancheng Maternity&Child Health Hospital of Yangzhou University Medical School, Suzhou, ChinaChildren's Hospital of Nanjing Medical University, Nanjing, ChinaChildren's Hospital of Nanjing Medical University, Nanjing, ChinaSchool of Public Health, Medical College of Soochow University, Suzhou, China; Correspondence to: Jie-Yun Yin, School of Public Health, Suzhou Medical College of Soochow University, Suzhou, Jiangsu 215123, PR China.Children's Hospital of Nanjing Medical University, Nanjing, China; Correspondence to: Yan-Qun Sun, Ye Tian, Children's Hospital of Nanjing Medical University, 72 Guangzhou Road, Nanjing 210008, PR China.Objective: Lyme disease, caused by Borrelia burgdorferi and transmitted by blacklegged ticks (Ixodes species), is the most common vector-borne disease in the United States. Its spatiotemporal dynamics are influenced by environmental and socioeconomic factors, yet the impacts of the COVID-19 pandemic on Lyme disease remain unclear. Methods: We analyzed county-level Lyme disease surveillance data (2001−2022) alongside environmental, socioeconomic, and tick vector data. Using machine learning models (Random Forest, Boosted Regression Trees, and XGBoost) and Shapley Additive Explanations (SHAP), we evaluated the influence of key predictors on Lyme disease risk. Predicted cases for 2020–2022 were compared with actual reports to assess the pandemic's effects. Results: Lyme disease cases rose from 16,862 in 2001 to 61,802 in 2022, with geographic expansion into southeastern regions. Population density, ecological niche of I. scapularis, and maximum temperature were presented as the key predictors of disease risk. The COVID-19 pandemic severely disrupted reporting dynamics, with 2020 and 2021 cases falling 43.9 % (95 % CI: 41.2–46.7 %) and 22.0 % (95 % CI: 19.5–24.5 %) below predictions, respectively—a decline most pronounced in the Northeast and linked to reduced healthcare access and outdoor activity during lockdowns. Conclusion: Our findings highlight the complex interactions of environmental, socioeconomic, and behavioral factors in Lyme disease dynamics, including the significant impact of the COVID-19 pandemic on disease reporting. These insights underscore the need for integrated, data-driven public health strategies to mitigate Lyme disease risk in the United States.http://www.sciencedirect.com/science/article/pii/S2352771425001478Lyme diseaseBlacklegged ticksCOVID-19 pandemicMachine learning
spellingShingle Yan-Qun Sun
Xiao-Yan Zhu
Tian-Ci Fan
Tian Ma
Hong-Han Ge
Rui-Fang Shi
Xu Wang
Wei Li
Jie-Yun Yin
Ye Tian
Projecting lyme disease risk in the United States: A machine learning approach integrating environmental, socioeconomic and vector factors
One Health
Lyme disease
Blacklegged ticks
COVID-19 pandemic
Machine learning
title Projecting lyme disease risk in the United States: A machine learning approach integrating environmental, socioeconomic and vector factors
title_full Projecting lyme disease risk in the United States: A machine learning approach integrating environmental, socioeconomic and vector factors
title_fullStr Projecting lyme disease risk in the United States: A machine learning approach integrating environmental, socioeconomic and vector factors
title_full_unstemmed Projecting lyme disease risk in the United States: A machine learning approach integrating environmental, socioeconomic and vector factors
title_short Projecting lyme disease risk in the United States: A machine learning approach integrating environmental, socioeconomic and vector factors
title_sort projecting lyme disease risk in the united states a machine learning approach integrating environmental socioeconomic and vector factors
topic Lyme disease
Blacklegged ticks
COVID-19 pandemic
Machine learning
url http://www.sciencedirect.com/science/article/pii/S2352771425001478
work_keys_str_mv AT yanqunsun projectinglymediseaseriskintheunitedstatesamachinelearningapproachintegratingenvironmentalsocioeconomicandvectorfactors
AT xiaoyanzhu projectinglymediseaseriskintheunitedstatesamachinelearningapproachintegratingenvironmentalsocioeconomicandvectorfactors
AT tiancifan projectinglymediseaseriskintheunitedstatesamachinelearningapproachintegratingenvironmentalsocioeconomicandvectorfactors
AT tianma projectinglymediseaseriskintheunitedstatesamachinelearningapproachintegratingenvironmentalsocioeconomicandvectorfactors
AT honghange projectinglymediseaseriskintheunitedstatesamachinelearningapproachintegratingenvironmentalsocioeconomicandvectorfactors
AT ruifangshi projectinglymediseaseriskintheunitedstatesamachinelearningapproachintegratingenvironmentalsocioeconomicandvectorfactors
AT xuwang projectinglymediseaseriskintheunitedstatesamachinelearningapproachintegratingenvironmentalsocioeconomicandvectorfactors
AT weili projectinglymediseaseriskintheunitedstatesamachinelearningapproachintegratingenvironmentalsocioeconomicandvectorfactors
AT jieyunyin projectinglymediseaseriskintheunitedstatesamachinelearningapproachintegratingenvironmentalsocioeconomicandvectorfactors
AT yetian projectinglymediseaseriskintheunitedstatesamachinelearningapproachintegratingenvironmentalsocioeconomicandvectorfactors