Machine learning-based high-specificity diagnostic model for Talaromyces marneffei infection in febrile patients using routine clinical laboratory data

Aug 5, 2026

This study developed and validated a machine learning predictive model to screen febrile patients for Talaromyces marneffei infection using routine clinical laboratory data, supporting feature selection for a future, more precise early-warning system. A retrospective cohort of febrile patients from January 2021 to April 2025 was analyzed; informative variables were extracted via sparse partial least squares discriminant analysis and multiple algorithms were compared using 1000 bootstrap resamplings, then tested on an independent clinical dataset.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages12

Reading Time30 min

AccessFree to download

Introduction

Objective

Methods

Data collection and cohort design

Feature selection and model development

Validation strategy

Results

Conclusion

TYPE Original Research PUBLISHED 04 September 2025 DOI 10.3389/fmicb.2025.1654918 OPEN ACCESS EDITED BY Xiaoli Qin, Hunan Agricultural University, China REVIEWED BY Xing-bei Weng, The First Affiliated Hospital of Ningbo University, China Xiaoman Chen, Guangzhou Eighth People’s Hospital, China *CORRESPONDENCE Kui Fang [20165061@zcmu.edu.cn](20165061@zcmu.edu.cn)[ ](20165061@zcmu.edu.cn)Peng Xu [600xup@163.com](600xup@163.com) †These authors have contributed equally to this work and share first authorship RECEIVED 30 June 2025 ACCEPTED 16 August 2025 PUBLISHED 04 September 2025 CITATION Xiao Y, Chen X, Ou X, Dong Z, Zhang X, Liang W, Nan X, Xu C, Lai X, Xu P and Fang K (2025) Machine learning-based high-specificity diagnostic model for Talaromyces marneffei infection in febrile patients using routine clinical laboratory data. Front. Microbiol. 16:1654918 . doi: 10.3389/fmicb.2025.1654918 COPYRIGHT © 2025 Xiao, Chen, Ou, Dong, Zhang, Liang, Nan, Xu, Lai, Xu and Fang. This is an 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. Machine learning-based high-specificity diagnostic model for Talaromyces marneffei infection in febrile patients using routine clinical laboratory data Yingjun Xiao1†, Xiling Chen1†, Xiping Ou2†, Zheqing Dong1 , Xiaoyan Zhang3 , Wei Liang4 , Xiaojing Nan1 , Chan Xu1 , Xiaobo Lai5 , Peng Xu1,5* and Kui Fang1* 1The Third Affiliated Hospital of Zhejiang Chinese Medical University, Hangzhou, Zhejiang, China, 2The Third School of Clinical Medicine, Zhejiang Chinese Medical University, Hangzhou, Zhejiang, China, 3The First People’s Hospital of Yuhang District, Hangzhou, Zhejiang, China, 4 Luqiao Hospital of Traditional Chinese Medicine, Taizhou, Zhejiang, China, 5 School of Medical Technology and Information Engineering, Zhejiang Chinese Medical University, Hangzhou, Zhejiang, China Objective: This study developed and validated a machine learning (ML)-based predictive model utilizing febrile patients’ routine clinical laboratory data for the purpose of screening such patients for Talaromyces marneffei infection and to provide reference information for feature selection in the subsequent establishment of a more precise early warning model. Methods: This retrospective study enrolled febrile patients who visited Zhejiang Provincial People’s Hospital and the Third Affiliated Hospital of Zhejiang Chinese Medical University from January 2021–April 2025. Patient data, including sex, age, and laboratory test results, were collected. Through sparse partial least squares discriminant analysis, the most informative features were extracted from the dataset. Six classic machine learning algorithms were utilized to develop the optimal predictive model through 1000 bootstrap resamplings. Finally, the model was validated on an independent clinical validation dataset. Results: The training dataset comprised 485 febrile patients (141 with T. marneffei infection) . The clinical validation dataset comprised 1,953 febrile patients (13 with T. marneffei infection) . The random forest model demonstrated the highest performance in classifying T. marneffei-infected patients, with an area under the receiver operating characteristic curve of 0.987 in out-ofbag validation and 0.989 in clinical validation. The model also exhibited good specificity (0 .999) for T. marneffei infection and good sensitivity (0 . 845) in predicting bacteraemia in clinical validation. Conclusion: A random forest model can effectively utilize routine clinical laboratory data to predict T. marneffei infection and bact

FAQs

What is the main objective of the machine learning model in this study?

To develop and validate a machine learning-based predictive model that screens febrile patients for Talaromyces marneffei infection using routine clinical laboratory data.

How were the most informative features selected for model building?

Sparse partial least squares discriminant analysis was used to extract the most informative features from the dataset.

What performance did the random forest model achieve in validation?

It showed the highest classification performance, with AUC values of 0.987 in out-of-bag validation and 0.989 in clinical validation, alongside high specificity (0.999) for T. marneffei infection.

Aug 5, 2026

Upload by Clementine