A multicenter study on developing a prognostic model for severe fever with thrombocytopenia syndrome using machine learning

Aug 5, 2026

Upload by Riley

Severe Fever with Thrombocytopenia Syndrome (SFTS) requires accurate prognostic assessment to support individualized prevention and treatment. This multicenter retrospective study develops and validates an interpretable machine-learning–based prognostic model using routinely available clinical features. Model training and internal validation draw on 292 patients, while external validation uses 104 patients from a separate center. Feature selection is performed with Boruta, performance is evaluated by AUC and related metrics, and clinical value is assessed with decision curve analysis, with interpretability supported by SHAP.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

Background

Objective

Methods

Study design and cohorts

Feature selection and model development

Model evaluation and interpretability

Results

Conclusion

TYPE Original Research PUBLISHED 19 March 2025 DOI 10. 3389/fmicb.2025.1557922 OPEN ACCESS EDITED BY Pei-Hui Wang, Shandong University, China REVIEWED BY Yuanchia Chu, Taipei Veterans General Hospital, Taiwan Mehmet Huyut, Erzincan University, Türkiye Fida Hussain, Iqra University, Pakistan *CORRESPONDENCE Yi-Shan Zheng [284159264@qq.com](284159264@qq.com) †These authors have contributed equally to this work and share ﬁrst authorship RECEIVED 09 January 2025 ACCEPTED 05 March 2025 PUBLISHED 19 March 2025 CITATION Xu J-S, Yang K, Quan B, Xie J and Zheng Y-S (2025) A multicenter study on developing a prognostic model for severe fever with thrombocytopenia syndrome using machine learning. Front. Microbiol. 16:1557922 . doi: 10.3389/fmicb.2025.1557922 COPYRIGHT © 2025 Xu, Yang, Quan, Xie and Zheng. This isan open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. A multicenter study on developing a prognostic model for severe fever with thrombocytopenia syndrome using machine learning Jian-She Xu1†, Kai Yang2†, Bin Quan3 , Jing Xie2 and Yi-Shan Zheng1,2* 1 School of Public Health, Nanjing Medical University, Nanjing, China, 2 Department of Intensive Care Unit, The Second Hospital of Nanjing, A􀀈liated of Nanjing University of Chinese Medicine, Nanjing, China, 3 Department of Infectious Disease, The First A􀀈liated Hospital of Wannan Medical College, Wuhu, China Background: Severe Fever with Thrombocytopenia Syndrome (SFTS) is a disease caused by infection with the Severe Fever with Thrombocytopenia Syndrome virus (SFTSV), a novel Bunyavirus. Accurate prognostic assessment is crucial for developing individualized prevention and treatment strategies. However, machine learning prognostic models for SFTS are rare and need further improvement and clinical validation. Objective: This study aims to develop and validate an interpretable prognostic model based on machine learning (ML) methods to enhance the understanding of SFTS progression. Methods: This multicenter retrospective study analyzed patient data from two provinces in China. The derivation cohort included 292 patients treated at The Second Hospital of Nanjing from January 2022 to December 2023, with a 7:3 split for model training and internal validation. The external validation cohort consisted of 104 patients from The First A􀀈liated Hospital of Wannan Medical College during the same period. Twenty-four commonly available clinical features were selected, and the Boruta algorithm identiﬁed 12 candidate predictors, ranked by Z-scores, which were progressively incorporated into 10 machine learning models to develop prognostic models. Model performance was assessed using the area under the receiver-operating-characteristic curve (AUC), accuracy, recall, and F1 score. The clinical utility of the best-performing model was evaluated through decision curve analysis (DCA) based on net beneﬁt. Robustness was tested with 10-fold cross-validation, and feature importance was explained using SHapley Additive exPlanation (SHAP) both globally and locally. Results: Among the 10 machine learning models, the XGBoost model demonstrated the best overall discriminatory ability. Considering both AUC index and feature simplicity, a ﬁnal interpretable XGBoost model with 7 key features was constructed. The model showed high predictive accuracy for patient outcomes in both internal (AUC = 0.911, 95% CI: 0 .842–0.967) and external validations (AUC = 0.891, 95% CI: 0 .786–0.977) . A clinical tool based on this model has been developed and implemented using the Streamlit fram

FAQs

What is the main goal of this study?

To develop and validate an interpretable prognostic model for severe fever with thrombocytopenia syndrome using machine learning to better understand disease progression.

How were patients selected and how were cohorts used?

The study used a multicenter retrospective design with an internal derivation cohort of 292 patients and an external validation cohort of 104 patients from different hospitals during the same period.

Which model performed best and how was clinical usefulness assessed?

XGBoost showed the best overall discriminatory ability, and the clinical utility of the best-performing model was evaluated using decision curve analysis based on net benefit.

Aug 5, 2026

Upload by Riley