Citation: Xue-Geng Hong, Hong-Han Ge, Ning Cui, Yan-Li Xu, Xin Yang, Jia-Hao Chen, Xiao-Hong Yin, Yi-Mei Yuan, Chao Zhou, Hao Li, Xiao-Ai Zhang, Ming Yue, Ling Lin, Wei Liu. Predicting mortality risk of severe fever with thrombocytopenia syndrome: A multi-center retrospective cohort study .VIROLOGICA SINICA, 2025, 40(6) : 1011-1020.  http://dx.doi.org/10.1016/j.virs.2025.12.008

Predicting mortality risk of severe fever with thrombocytopenia syndrome: A multi-center retrospective cohort study

  • Severe fever with thrombocytopenia syndrome (SFTS) is an emerging tick-borne disease with high mortality, and clinical practice lacks dynamic tools to assess its rapidly evolving course. This study aims to develop stage-specific machine learning models to predict mortality risk using longitudinal biomarker data. We conducted a retrospective analysis of 5359 laboratory-confirmed SFTS patients from two hospitals in the highly endemic region in China. Serial measurements of 46 clinical and laboratory variables were integrated into a three-stage prognostic model developed using extreme gradient boosting (XGBoost). Within each clinical stage, key predictors and their relative contribution (RC) of mortality risk were assessed. Model performance was assessed based on discrimination, calibration, and decision curve analysis (DCA) in internal and external test sets. XGBoost models were constructed across 10 temporal phases, later consolidated into three clinically distinct stages via hierarchical clustering: early (≤7 days), intermediate (days 8-9), and late (≥10 days). Key predictors included age (dominant in early phase; RC, 18.44%), lactate dehydrogenase (LDH; RC peaking at 60.10% in late phase), and monocyte percentage (RC range from 5.25% to 16.04%). Pathophysiological shifts across clinical stages were revealed: early viral cytopathy (dominated by age and MONO%), intermediate immunopathology (marked by LDH surge), and late hepatic failure (dominated by LDH, AST, and TBA). The model showed strong discrimination (Area under the receiver operating characteristic curve, AUCs: 0.84-0.98 internal; 0.91-0.98 external), calibration (Brier scores: 0.04-0.11), and clinical utility via DCA. This study introduces a dynamic staging system that leverages predictive models and real-time patient data to monitor mortality risk and personalize SFTS care, which enables timely interventions to reduce deaths.

  • 加载中
  • 10.1016j.virs.2025.12.008-ESM1.docx
    1. Cai, G., Huang, F., Gao, Y., Li, X., Chi, J., Xie, J., Zhou, L., Feng, Y., Huang, H., Deng, T., Zhou, Y., Zhang, C., Luo, X., Xie, X., Gao, Q., Zhen, X.,Liu, J., 2024. Artificial intelligence-based models enabling accurate diagnosis of ovarian cancer using laboratory tests in China: a multicentre, retrospective cohort study. The Lancet Digital Health, 6, e176-e186.

    2. Casel, M.A., Park, S.J.,Choi, Y.K., 2021. Severe fever with thrombocytopenia syndrome virus: emerging novel phlebovirus and their control strategy. Exp Mol Med, 53, 713-722.

    3. Chen, T.,Guestrin, C. XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016. 785-794.

    4. Chen, T., Zhang, M., Liu, Q., Li, W., Zeng, Z., Chen, C., Zhou, Y., Zhou, T., Li, Y., Wang, W., et al., 2025. Development and validation of a novel mortality risk stratification simplified scoring scale for severe fever with thrombocytopenia syndrome. Clin Microbiol Infect, 31,1378-1388.

    5. Gai, Z.T., Zhang, Y., Liang, M.F., Jin, C., Zhang, S., Zhu, C.B., Li, C., Li, X.Y., Zhang, Q.F., Bian, P.F., Zhang, L.H., Wang, B., Zhou, N., Liu, J.X., Song, X.-G., Xu, A., Bi, Z.Q., Chen, S.J.,Li, D.X., 2012. Clinical Progress and Risk Factors for Death in Severe Fever with Thrombocytopenia Syndrome Patients. The Journal of Infectious Diseases, 206, 1095-1102.

    6. Ge, H., Zhao, J., Zhang, S., Xu, Y., Liu, Y., Peng, X., Wang, G., Gong, X., Zhang, L., Li, S., Li, H., Zhang, X.A., Cui, N., Yuan, C., Lin, L.,Liu, W., 2022. Impact of glycemia and insulin treatment in fatal outcome of severe fever with thrombocytopenia syndrome. Int J Infect Dis, 119, 24-31.

    7. Goh, K.H., Wang, L., Yeow, A.Y.K., Poh, H., Li, K., Yeow, J.J.L.,Tan, G.Y.H., 2021. Artificial intelligence in sepsis early prediction and diagnosis using unstructured data in healthcare. Nat Commun, 12, 711.

    8. Greener, J.G., Kandathil, S.M., Moffat, L.,Jones, D.T., 2022. A guide to machine learning for biologists. Nat Rev Mol Cell Biol, 23, 40-55.

    9. Guo, C., Li, R., Wang, X.,Peng, X., 2024. Aspartate aminotransferase to platelet ratio correlates with poor prognosis and metabolic alterations in Dabie bandavirus infection. Front Immunol, 15, 1471511.

    10. Hou, H., Zou, S., Wei, W., Wang, T., Wang, Y., Wu, S., Wang, F., Liu, W., Huang, M.,Peng, J., 2024. Kinetics and Prognostic Significance of Laboratory Markers in Patients With Severe Fever With Thrombocytopenia Syndrome: Insight From a Comprehensive Analysis. J Infect Dis, 229, 1845-1855.

    11. Jia, B., Yan, X., Chen, Y., Wang, G., Liu, Y., Xu, B., Song, P., Li, Y., Xiong, Y., Wu, W., Hao, Y., Xia, J., Zhang, Z., Huang, R.,Wu, C., 2017. A scoring model for predicting prognosis of patients with severe fever with thrombocytopenia syndrome. PLoS Negl Trop Dis, 11, e0005909.

    12. Jung, I.Y., Ahn, K., Kim, J., Choi, J.Y., Kim, H.Y., Uh, Y.,Kim, Y.K., 2019. Higher Fatality for Severe Fever with Thrombocytopenia Syndrome Complicated by Hemophagocytic Lymphohistiocytosis. Yonsei Med J, 60, 592-596.

    13. Kim, K.H., Yi, J., Kim, G., Choi, S.J., Jun, K.I., Kim, N.H., Choe, P.G., Kim, N.J., Lee, J.K.,Oh, M.D., 2013. Severe fever with thrombocytopenia syndrome, South Korea, 2012. Emerg Infect Dis, 19, 1892-1894.

    14. Lee, J.M., Kim, H.L., Lim, M.N., Kim, C., La, Y.J., Jeon, Y.D., Oh, W.S., Son, S., Lee, S., Baek, H., Hwang, D.D.,Park, J.I., 2024. Acute kidney injury as a prognostic marker in severe fever with thrombocytopenia syndrome. Sci Rep, 14, 20651.

    15. Lekadir, K., Frangi, A.F., Porras, A.R., Glocker, B., Cintas, C., Langlotz, C.P., Weicken, E., Asselbergs, F.W., Prior, F., Collins, G.S., et al., 2025. FUTURE-AI: international consensus guideline for trustworthy and deployable artificial intelligence in healthcare. Bmj, 388, e081554.

    16. Li, H., Lu, Q.B., Xing, B., Zhang, S.F., Liu, K., Du, J., Li, X.K., Cui, N., Yang, Z.D., Wang, L.Y., Hu, J.G., Cao, W.C.,Liu, W., 2018. Epidemiological and clinical features of laboratory-diagnosed severe fever with thrombocytopenia syndrome in China, 2011-17: a prospective observational study. Lancet Infect Dis, 18, 1127-1137.

    17. Li, S., Li, H., Zhang, Y.L., Xin, Q.L., Guan, Z.Q., Chen, X., Zhang, X.A., Li, X.K., Xiao, G.F., Lozach, P.Y., Cui, J., Liu, W., Zhang, L.K.,Peng, K., 2020. SFTSV Infection Induces BAK/BAX-Dependent Mitochondrial DNA Release to Trigger NLRP3 Inflammasome Activation. Cell Rep, 30, 4370-4385.e4377.

    18. Li, H., Li, X., Lv, S., Peng, X., Cui, N., Yang, T., Yang, Z., Yuan, C., Yuan, Y., Yao, J., Yuan, Z., Li, J., Ye, X., Zhang, X., Zhu, S., Peng, K.,Liu, W., 2021. Single-cell landscape of peripheral immune responses to fatal SFTS. Cell Rep, 37, 110039.

    19. Li, Y.H., Huang, W.W., He, W.Q., He, X.Y., Wang, X.H., Lin, Y.L., Zhao, Z.J., Zheng, Y.T.,Pang, W., 2023. Longitudinal analysis of immunocyte responses and inflammatory cytokine profiles in SFTSV-infected rhesus macaques. Front Immunol, 14, 1143796.

    20. Ministry of Health PRC. 2010. Guideline for prevention and treatment of severe fever with thrombocytopenia syndrome (2010 version). Zhonghua Lin Chuang Gan Ran Bing Za Zhi 4, 193-194 (in Chinese).

    21. Park, A., Park, S.J., Jung, K.L., Kim, S.M., Kim, E.H., Kim, Y.I., Foo, S.S., Kim, S., Kim, S.G., Yu, K.M., et al., 2021. Molecular Signatures of Inflammatory Profile and B-Cell Function in Patients with Severe Fever with Thrombocytopenia Syndrome. mBio, 12, e02583-20.

    22. Peng, C., Wang, H., Zhang, W., Zheng, X., Tong, Q., Jie, S., Yang, D.,Zhou, Y., 2016. Decreased monocyte subsets and TLR4-mediated functions in patients with acute severe fever with thrombocytopenia syndrome (SFTS). Int J Infect Dis, 43, 37-42.

    23. Pfaff, E.R., Girvin, A.T., Bennett, T.D., Bhatia, A., Brooks, I.M., Deer, R.R., Dekermanjian, J.P., Jolley, S.E., Kahn, M.G., Kostka, K., Mcmurry, J.A., Moffitt, R., Walden, A., Chute, C.G.,Haendel, M.A., 2022. Identifying who has long COVID in the USA: a machine learning approach using N3C data. Lancet Digit Health, 4, e532-e541.

    24. Song, P., Zheng, N., Liu, Y., Tian, C., Wu, X., Ma, X., Chen, D., Zou, X., Wang, G., Wang, H., Zhang, Y., Lu, S., Wu, C.,Wu, Z., 2018. Deficient humoral responses and disrupted B-cell immunity are associated with fatal SFTSV infection. Nat Commun, 9, 3328.

    25. Song, L., Zou, W., Wang, G., Qiu, L.,Sai, L., 2024. Cytokines and lymphocyte subsets are associated with disease severity of severe fever with thrombocytopenia syndrome. Virol J, 21, 126.

    26. Steyerberg, E.W., Vickers, A.J., Cook, N.R., Gerds, T., Gonen, M., Obuchowski, N., Pencina, M.J.,Kattan, M.W., 2010. Assessing the performance of prediction models: a framework for traditional and novel measures. Epidemiology, 21, 128-138.

    27. Takahashi, T., Maeda, K., Suzuki, T., Ishido, A., Shigeoka, T., Tominaga, T., Kamei, T., Honda, M., Ninomiya, D., Sakai, T., et al., 2014. The first identification and retrospective study of Severe Fever with Thrombocytopenia Syndrome in Japan. J Infect Dis, 209, 816-827.

    28. Tang, N., Yuan, P., Luo, M.,Li, D., 2024. Prolonged coagulation times in severe fever with thrombocytopenia syndrome virus infection, the indicators of heparin-like effect and increased haemorrhagic risk. Br J Haematol, 204, 1999-2006.

    29. Tran, X.C., Yun, Y., Van An, L., Kim, S.H., Thao, N.T.P., Man, P.K.C., Yoo, J.R., Heo, S.T., Cho, N.H.,Lee, K.H., 2019. Endemic Severe Fever with Thrombocytopenia Syndrome, Vietnam. Emerg Infect Dis, 25, 1029-1031.

    30. Walker, P.J., Siddell, S.G., Lefkowitz, E.J., Mushegian, A.R., Adriaenssens, E.M., Alfenas-Zerbini, P., Dempsey, D.M., Dutilh, B.E., Garcia, M.L., Curtis Hendrickson, R., et al., 2022. Recent changes to virus taxonomy ratified by the International Committee on Taxonomy of Viruses (2022). Arch Virol, 167, 2429-2440.

    31. Wang, L., Zou, Z., Hou, C., Liu, X., Jiang, F.,Yu, H., 2017. Score risk model for predicting severe fever with thrombocytopenia syndrome mortality. BMC Infect Dis, 17, 42.

    32. Wang, X., Ren, X., Ge, Z., Cui, S., Wang, L., Chen, Z.,Tian, D., 2021. Clinical manifestations of death with severe fever and thrombocytopenia syndrome: A meta-analysis and systematic review. J Med Virol, 93, 3960-3968.

    33. Wang, L., Xu, Y., Zhang, S., Bibi, A., Xu, Y.,Li, T., 2022. The AST/ALT Ratio (De Ritis Ratio) Represents an Unfavorable Prognosis in Patients in Early-Stage SFTS: An Observational Cohort Study. Front Cell Infect Microbiol, 12, 725642.

    34. Wang, G., Xu, Y.L., Zhu, Y., Yue, M., Zhao, J., Ge, H.H., Ye, X.L., Liu, Y.N., Gong, X.Y., Zhang, L.G., et al., 2023. Clinical efficacy of low-dose glucocorticoid therapy for critically ill patients with severe fever with thrombocytopenia syndrome: A retrospective cohort study. Int J Infect Dis, 130, 153-160.

    35. Win, A.M., Nguyen, Y.T.H., Kim, Y., Ha, N.Y., Kang, J.G., Kim, H., San, B., Kyaw, O., Htike, W.W., Choi, D.O., Lee, K.H.,Cho, N.H., 2020. Genotypic Heterogeneity of Orientia tsutsugamushi in Scrub Typhus Patients and Thrombocytopenia Syndrome Co-infection, Myanmar. Emerg Infect Dis, 26, 1878-1881.

    36. Xu, X., Sun, Z., Liu, J., Zhang, J., Liu, T., Mu, X.,Jiang, M., 2018. Analysis of clinical features and early warning indicators of death from severe fever with thrombocytopenia syndrome. Int J Infect Dis, 73, 43-48.

    37. Yu, X.J., Liang, M.F., Zhang, S.Y., Liu, Y., Li, J.D., Sun, Y.L., Zhang, L., Zhang, Q.F., Popov, V.L., Li, C., et al., 2011. Fever with thrombocytopenia associated with a novel bunyavirus in China. N Engl J Med, 364, 1523-1532.

    38. Zhang, S., Wang, J., Zhang, Q., Pan, Y., Zhang, Z., Geng, Y., Jia, B., Li, Y., Xiong, Y., Yan, X., Li, J., Wang, H., Wu, C.,Huang, R., 2024. Association of liver function and prognosis in patients with severe fever with thrombocytopenia syndrome. PLoS Negl Trop Dis, 18, e0012068.

    39. Zhao, J., Lu, Q.B., Li, H., Yuan, Y., Cui, N., Yuan, C., Zhang, X.A., Yang, Z.D., Ruan, S.M., Liu, L.Z., Du, J., Fang, L.Q.,Liu, W., 2021. Sex Differences in Case Fatality Rate of Patients With Severe Fever With Thrombocytopenia Syndrome. Front Microbiol, 12, 738808.

    40. Zhao, J., Ge, H.-H., Wang, G., Lin, L., Yuan, Y., Xu, Y.-L., Liu, Y.-N., Lu, Q.-B., Zhang, X.-A., Cui, N., Yuan, C., Li, J.-X., Lin, L., Li, H.,Liu, W., 2022. Fatal patients with severe fever with thrombocytopenia syndrome in China. International Journal of Infectious Diseases, 125, 10-16.

  • 加载中

Figures(1)

Article Metrics

Article views(1814) PDF downloads(7) Cited by()

Related
Proportional views

    Predicting mortality risk of severe fever with thrombocytopenia syndrome: A multi-center retrospective cohort study

      Corresponding author: Ming Yue, njym08@163.com
      Corresponding author: Ling Lin, linling4012@163.com
      Corresponding author: Wei Liu, lwbime@163.com
    • a. State Key Laboratory of Pathogen and Biosecurity, Academy of Military Medical Sciences, Beijing 100071, China;
    • b. Department of Medical Services, The 960th Hospital of the PLA Joint Logistics Support Force, Jinan 250031, China;
    • c. School of Public Health, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan 250117, China;
    • d. The 154th Hospital, China RongTong Medical Healthcare Group Co. Ltd, Xinyang 464000, China;
    • e. Department of Infectious Diseases, Yantai Qishan Hospital, Yantai 264001, China;
    • f. Department of Infectious Diseases, The First Affiliated Hospital of Nanjing Medical University, Nanjing 210029, China;
    • g. School of Public Health, Anhui Medical University, Hefei 230032, China

    Abstract: Severe fever with thrombocytopenia syndrome (SFTS) is an emerging tick-borne disease with high mortality, and clinical practice lacks dynamic tools to assess its rapidly evolving course. This study aims to develop stage-specific machine learning models to predict mortality risk using longitudinal biomarker data. We conducted a retrospective analysis of 5359 laboratory-confirmed SFTS patients from two hospitals in the highly endemic region in China. Serial measurements of 46 clinical and laboratory variables were integrated into a three-stage prognostic model developed using extreme gradient boosting (XGBoost). Within each clinical stage, key predictors and their relative contribution (RC) of mortality risk were assessed. Model performance was assessed based on discrimination, calibration, and decision curve analysis (DCA) in internal and external test sets. XGBoost models were constructed across 10 temporal phases, later consolidated into three clinically distinct stages via hierarchical clustering: early (≤7 days), intermediate (days 8-9), and late (≥10 days). Key predictors included age (dominant in early phase; RC, 18.44%), lactate dehydrogenase (LDH; RC peaking at 60.10% in late phase), and monocyte percentage (RC range from 5.25% to 16.04%). Pathophysiological shifts across clinical stages were revealed: early viral cytopathy (dominated by age and MONO%), intermediate immunopathology (marked by LDH surge), and late hepatic failure (dominated by LDH, AST, and TBA). The model showed strong discrimination (Area under the receiver operating characteristic curve, AUCs: 0.84-0.98 internal; 0.91-0.98 external), calibration (Brier scores: 0.04-0.11), and clinical utility via DCA. This study introduces a dynamic staging system that leverages predictive models and real-time patient data to monitor mortality risk and personalize SFTS care, which enables timely interventions to reduce deaths.

    Figure (1)  Reference (40) Relative (20)

    目录

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return