https://doi.org/10.4081/gh.2026.1535
Nonlinear analysis of factors influencing tuberculosis outpatient visits in China: an explainable machine learning approach
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.
Accepted: 15 September 2026
Published: 8 October 2026
This study aims to analyze the temporal trends, interprovincial differences, and key predictors of Tuberculosis Outpatient Visits (TOV) in China. It provides empirical evidence for understanding regional differences in tuberculosis-related outpatient service uti- lization. Panel data from 30 Chinese provinces from 2012 to 2024 were used. The study included variables related to economic development, health resources, education resources, environmental governance, pollutant emissions, and technological innovation. Correlation analysis, model comparison, and XGBoost-SHAP analysis were applied. From 2012 to 2024, TOV showed a gradual upward trend and clear interprovincial differences. Shanghai, Fujian, Guangdong, and Zhejiang had relatively higher total recorded outpatient volumes. XGBoost showed the best predictive performance among all candidate models (R2 = 0.8154). SHAP results identified Disposable Income Per Capita (DIPC), University Staff (USTF), Domestic Patent Applications (DPA), Hospital Beds (HBED), and Technology Market Turnover (TMT) as the main predictors. Environmental governance and pollutant emission vari- ables had lower overall contributions, but they still showed nonlinear predictive contributions in some value ranges. The findings suggest that interprovincial differences in TOV are jointly associated with economic development, health resources, education resources, environmental governance, and technological innovation. TOV mainly reflects outpatient service utilization and case detection capacity. It should not be interpreted as a direct measure of tuberculosis incidence risk.
Downloads
Chen J, Jiang Y, Li Z, Zhang M, Liu L, Li A, Lu H, 2024. Predictive machine learning models for anticipating loss to follow-up in tuberculosis patients throughout anti-TB treatment journey. Sci Rep 14;24685. DOI: https://doi.org/10.1038/s41598-024-74942-z
Chen T, Guestrin C, 2016. XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794). Association for Computing Machinery, New York, NY, USA, 785–94. DOI: https://doi.org/10.1145/2939672.2939785
Chen X, Zhou J, Yuan Q, Zhang R, Huang C, Li Y, 2024. Challenge of ending TB in China: Tuberculosis control in primary healthcare sectors under integrated TB control model—A systematic review and meta-analysis. BMC Public Health 24;163. DOI: https://doi.org/10.1186/s12889-023-16292-5
Deng L, Zhao F, Li Z, Zhang W, He G, Ren X, 2024. Epidemiological characteristics of tuberculosis incidence and its macro-influence factors in Chinese mainland during 2014–2021. Infect Dis Poverty 13:34. DOI: https://doi.org/10.1186/s40249-024-01203-6
Dimala CA, Kadia BM, 2022. A systematic review and meta-analysis on the association between ambient air pollution and pulmonary tuberculosis. Sci Rep 12;11282. DOI: https://doi.org/10.1038/s41598-022-15443-9
Fan M, Liu Y, Liu K, Liu X, Li Y, Li T, Zhang C, Zhang H, Cheng J, 2025. Health system delay and risk factors in pulmonary tuberculosis diagnosis before and during the COVID-19 epidemic: A multi-center survey in China. Front Public Health 13;1526774. DOI: https://doi.org/10.3389/fpubh.2025.1526774
Ferreira MRL, Bonfim RO, Bossonario PA, Maurin VP, Valença ABM, Abreu,PD de, Andrade RL de P, Fronteira I, Monroe AA, 2023. Social protection as a right of people affected by tuberculosis: A scoping review and conceptual framework. Infect Dis Poverty 12;104. DOI: https://doi.org/10.1186/s40249-023-01157-1
Guo J, Liu C, Liu F, Zhou E, Ma R, Zhang L, Luo B, 2025. Tuberculosis disease burden in China: A spatio-temporal clustering and prediction study. Front Public Health 12:1436515. DOI: https://doi.org/10.3389/fpubh.2024.1436515
Huang G, Xu Z, Bai L, Liu J, Yu S, Yao H, 2024. Spatiotemporal analysis of tuberculosis in the Hunan Province, China, 2014–2022. Front Public Health 12:1426503. DOI: https://doi.org/10.3389/fpubh.2024.1426503
Jiang W, Chen J, Lou Z, Jia Y, Tang S, Xiao X, Shen X, Chen X, Long, Q, 2025. Differences between the local and migrant populations in healthcare service use and direct cost of tuberculosis treatment—Shanghai Municipality, China, 2020–2021. China CDC Weekly 7;428–434.
Lundberg SM, Lee S-I, 2017. A unified approach to interpreting model predictions. Advances in Neural Information Processing Syst 30.
Ma K, Fang FM, Lin YS, Yao YR, Tong F, 2026. Spatiotemporal inequalities in the burden of tuberculosis attributable to long-term particulate matter exposure in mainland of China. GeoHealth 10:e2025GH001481. DOI: https://doi.org/10.1029/2025GH001481
Pan S, Chen L, Xin X, Li S, Zhang Y, Chen Y, Xiao S, 2024. Spatiotemporal analysis and seasonality of tuberculosis in Pudong New Area of Shanghai, China, 2014–2023. BMC Infect Dis 24;761. DOI: https://doi.org/10.1186/s12879-024-09645-x
Peng A, Kong X, Liu S, Zhang H, Xie L, Ma L, Zhang Q, Chen Y, 2024. Explainable machine learning for early predicting treatment failure risk among patients with TB-diabetes comorbidity. Sci Reports 14;6814. DOI: https://doi.org/10.1038/s41598-024-57446-8
Sun Q, Zhang K, Xu Y, Luo M, Yang Z, Liu Q, Liu S, Liu A, 2025. Explainable machine learning for predicting clinical outcomes in HIV/TB co-infection: A comparative retrospective study. BMC Infect Dis 25;1589. DOI: https://doi.org/10.1186/s12879-025-11998-w
Sun R, Wang L, Xia H, 2025. Disease burden of tuberculosis in China from 1990 to 2021 and its prediction to 2036. Front Public Health 12;1506266. DOI: https://doi.org/10.3389/fpubh.2024.1506266
Sun R, Wu Z, Zhang H, Huang J, Liu Y, Chen M, Lv Y, Zhao F, Zhang Y, Li M, Yan J, Jiang H, Zhan Y, Xu J, Xu Y, Yuan J, Zhao Y, Shen X, Yang C, 2024. Assessing heterogeneity of patient and health system delay among TB in a population with internal migrants in China. Front Public Health 12;1354515. DOI: https://doi.org/10.3389/fpubh.2024.1354515
Tao Y, Zhao J, Cui H, Liang Z, Li J, Ren J, Zhu H, 2026. Data-driven model analysis of the impact of environmental and socioeconomic factors on tuberculosis incidence. Infect Dis Modelling 11;930–46. DOI: https://doi.org/10.1016/j.idm.2026.02.002
Wang L, Li Y, Chen J, Zhang D, Zhang Z, Li X, 2025. Spatiotemporal distribution and detection of spatial clusters of tuberculosis in Hubei Province, China using FleXScan (2017–2023). BMC Public Health 25;2758. DOI: https://doi.org/10.1186/s12889-025-23620-4
Wang Y, Zhu W, Li T, Chen W, Wang W, 2021. Changes in newly notified cases and control of tuberculosis in China: Time-series analysis of surveillance data. Infect Dis Poverty 10:16. DOI: https://doi.org/10.1186/s40249-021-00806-7
World Health Organization, 2024. Global tuberculosis report 2024. World Health Organization. Available from: https://www.who.int/teams/global-programme-on-tuberculosis-and-lung-health/tb-reports/global-tuberculosis-report-2024
Wu S, Litvinjenko S, Magwood O, Wei X, 2023. Defining tuberculosis vulnerability based on an adapted social determinants of health framework: A narrative review. Global Public Health 18:2221729. DOI: https://doi.org/10.1080/17441692.2023.2221729
Xiao Y, Chen Y, Huang R, Jiang F, Zhou J, Yang T, 2024. Interpretable machine learning in predicting drug-induced liver injury among tuberculosis patients: Model development and validation study. BMC Med Res Methodol 24;92. DOI: https://doi.org/10.1186/s12874-024-02214-5
Xu C, Xia Y, Hu D, Zhang X, Zhao Y, 2023. Financial burden of tuberculosis patients—China, 2020. China CDC Weekly 5;266–70.
Zhang J, Zhong M, Huang J, Deng W, Li P, Yao Z, Ye X, Zhong X, 2024. Spatiotemporal patterns and socioeconomic determinants of pulmonary tuberculosis in Dongguan city, China, during 2011–2020: An ecological study. BMJ Open 14;e085733. DOI: https://doi.org/10.1136/bmjopen-2024-085733
Zhang K, Yang Z, Sun J, Liu K, Lu, Q, 2025. Spatiotemporal analysis of pulmonary tuberculosis in the central region of the Zhejiang Province, China (2016–2024). Front Public Health 13;1599274. DOI: https://doi.org/10.3389/fpubh.2025.1599274
Zhang L, Ma X, Gao H, Bao C, Wu Y, Wu S, Liu M, Liu Y, Li L, 2024. Analysis of care-seeking and diagnosis delay among pulmonary tuberculosis patients in Beijing, China. Front Public Health 12;1369541. DOI: https://doi.org/10.3389/fpubh.2024.1369541
Ethics Approval
CRediT authorship contribution
Hui Wang designed the experimental procedure, collected and analyzed data, and drafted the manuscript. Dehong Sun plotted all figures. Shanjie Sui retrieved relevant literatures. Yanhong Xu proofread the complete manuscript.
Supporting Agencies
Data Availability Statement
The data used in this study were obtained from the China Statistical Yearbook (http://www.stats.gov.cn/tjsj/ndsj/). The dataset is publicly accessible.
How to Cite
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
PAGEPress has chosen to apply the Creative Commons Attribution NonCommercial 4.0 International License (CC BY-NC 4.0) to all manuscripts to be published.
