Prediction of tuberculosis treatment outcomes using biochemical makers with machine learning

Abstract Background Tuberculosis (TB) continues to pose a significant threat to global public health. Enhancing patient prognosis is essential for alleviating the disease burden. Objective This study aims to evaluate TB prognosis by incorporating treatment discontinuation into the assessment framewo...

Full description

Saved in:
Bibliographic Details
Main Authors: Zheyue Wang, Zhenpeng Guo, Weijia Wang, Qiang Zhang, Suya Song, Yuan Xue, Zhixin Zhang, Jianming Wang
Format: Article
Language:English
Published: BMC 2025-02-01
Series:BMC Infectious Diseases
Subjects:
Online Access:https://doi.org/10.1186/s12879-025-10609-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849715676967600128
author Zheyue Wang
Zhenpeng Guo
Weijia Wang
Qiang Zhang
Suya Song
Yuan Xue
Zhixin Zhang
Jianming Wang
author_facet Zheyue Wang
Zhenpeng Guo
Weijia Wang
Qiang Zhang
Suya Song
Yuan Xue
Zhixin Zhang
Jianming Wang
author_sort Zheyue Wang
collection DOAJ
description Abstract Background Tuberculosis (TB) continues to pose a significant threat to global public health. Enhancing patient prognosis is essential for alleviating the disease burden. Objective This study aims to evaluate TB prognosis by incorporating treatment discontinuation into the assessment framework, expanding beyond mortality and drug resistance. Methods Seven feature selection methods and twelve machine learning algorithms were utilized to analyze admission test data from TB patients, identifying predictive features and building prognostic models. SHapley Additive exPlanations (SHAP) were applied to evaluate feature importance in top-performing models. Results Analysis of 1,086 TB cases showed that a K-Nearest Neighbor classifier with Mutual Information feature selection achieved an area under the receiver operation curve (AUC) of 0.87 (95% CI: 0.83–0.92). Key predictors of treatment failure included elevated levels of 5’-nucleotidase, uric acid, globulin, creatinine, cystatin C, and aspartate transaminase. SHAP analysis highlighted 5’-nucleotidase, uric acid, and globulin as having the most significant influence on predicting treatment discontinuation. Conclusion Our model provides valuable insights into TB outcomes based on initial patient tests, potentially guiding prevention and control strategies. Elevated biomarker levels before therapy are associated with increased risk of treatment discontinuation, indicating their potential as early warning indicators.
format Article
id doaj-art-7d665d6092d54fd79614cb51ca60e5d4
institution DOAJ
issn 1471-2334
language English
publishDate 2025-02-01
publisher BMC
record_format Article
series BMC Infectious Diseases
spelling doaj-art-7d665d6092d54fd79614cb51ca60e5d42025-08-20T03:13:14ZengBMCBMC Infectious Diseases1471-23342025-02-012511910.1186/s12879-025-10609-yPrediction of tuberculosis treatment outcomes using biochemical makers with machine learningZheyue Wang0Zhenpeng Guo1Weijia Wang2Qiang Zhang3Suya Song4Yuan Xue5Zhixin Zhang6Jianming Wang7Department of Epidemiology, Center for Global Health, School of Public Health, National Vaccine Innovation Platform, Nanjing Medical UniversityDepartment of Epidemiology, Center for Global Health, School of Public Health, National Vaccine Innovation Platform, Nanjing Medical UniversitySchool of Information and Software, University of Electronic Science and Technology of ChinaDepartment of Epidemiology, Center for Global Health, School of Public Health, National Vaccine Innovation Platform, Nanjing Medical UniversityChangzhou Medical Center, Nanjing Medical UniversityChangzhou Medical Center, Nanjing Medical UniversityChangzhou Medical Center, Nanjing Medical UniversityDepartment of Epidemiology, Center for Global Health, School of Public Health, National Vaccine Innovation Platform, Nanjing Medical UniversityAbstract Background Tuberculosis (TB) continues to pose a significant threat to global public health. Enhancing patient prognosis is essential for alleviating the disease burden. Objective This study aims to evaluate TB prognosis by incorporating treatment discontinuation into the assessment framework, expanding beyond mortality and drug resistance. Methods Seven feature selection methods and twelve machine learning algorithms were utilized to analyze admission test data from TB patients, identifying predictive features and building prognostic models. SHapley Additive exPlanations (SHAP) were applied to evaluate feature importance in top-performing models. Results Analysis of 1,086 TB cases showed that a K-Nearest Neighbor classifier with Mutual Information feature selection achieved an area under the receiver operation curve (AUC) of 0.87 (95% CI: 0.83–0.92). Key predictors of treatment failure included elevated levels of 5’-nucleotidase, uric acid, globulin, creatinine, cystatin C, and aspartate transaminase. SHAP analysis highlighted 5’-nucleotidase, uric acid, and globulin as having the most significant influence on predicting treatment discontinuation. Conclusion Our model provides valuable insights into TB outcomes based on initial patient tests, potentially guiding prevention and control strategies. Elevated biomarker levels before therapy are associated with increased risk of treatment discontinuation, indicating their potential as early warning indicators.https://doi.org/10.1186/s12879-025-10609-yTuberculosisMachine learningTreatment outcomesDiscontinuation
spellingShingle Zheyue Wang
Zhenpeng Guo
Weijia Wang
Qiang Zhang
Suya Song
Yuan Xue
Zhixin Zhang
Jianming Wang
Prediction of tuberculosis treatment outcomes using biochemical makers with machine learning
BMC Infectious Diseases
Tuberculosis
Machine learning
Treatment outcomes
Discontinuation
title Prediction of tuberculosis treatment outcomes using biochemical makers with machine learning
title_full Prediction of tuberculosis treatment outcomes using biochemical makers with machine learning
title_fullStr Prediction of tuberculosis treatment outcomes using biochemical makers with machine learning
title_full_unstemmed Prediction of tuberculosis treatment outcomes using biochemical makers with machine learning
title_short Prediction of tuberculosis treatment outcomes using biochemical makers with machine learning
title_sort prediction of tuberculosis treatment outcomes using biochemical makers with machine learning
topic Tuberculosis
Machine learning
Treatment outcomes
Discontinuation
url https://doi.org/10.1186/s12879-025-10609-y
work_keys_str_mv AT zheyuewang predictionoftuberculosistreatmentoutcomesusingbiochemicalmakerswithmachinelearning
AT zhenpengguo predictionoftuberculosistreatmentoutcomesusingbiochemicalmakerswithmachinelearning
AT weijiawang predictionoftuberculosistreatmentoutcomesusingbiochemicalmakerswithmachinelearning
AT qiangzhang predictionoftuberculosistreatmentoutcomesusingbiochemicalmakerswithmachinelearning
AT suyasong predictionoftuberculosistreatmentoutcomesusingbiochemicalmakerswithmachinelearning
AT yuanxue predictionoftuberculosistreatmentoutcomesusingbiochemicalmakerswithmachinelearning
AT zhixinzhang predictionoftuberculosistreatmentoutcomesusingbiochemicalmakerswithmachinelearning
AT jianmingwang predictionoftuberculosistreatmentoutcomesusingbiochemicalmakerswithmachinelearning