Machine learning-based prognostic model for bloodstream infections in hematological malignancies using Th1/Th2 cytokines
Abstract Objective Bloodstream infection (BSI) is a significant cause of mortality in patients with hematologic malignancies(HMs), particularly amid rising antibiotic resistance. This study aimed to analyze pathogen distribution, drug-resistance patterns and develop a novel predictive model for 30-d...
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-03-01
|
| Series: | BMC Infectious Diseases |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12879-025-10808-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849392181219950592 |
|---|---|
| author | Qin Li Nan Lin Zuheng Wang Yuexi Chen Yuli Xie Xuemei Wang Jirui Tang Yuling Xu Min Xu Na Lu Yiqian Huang Jiamin Luo Zhenfang Liu Li Jing |
| author_facet | Qin Li Nan Lin Zuheng Wang Yuexi Chen Yuli Xie Xuemei Wang Jirui Tang Yuling Xu Min Xu Na Lu Yiqian Huang Jiamin Luo Zhenfang Liu Li Jing |
| author_sort | Qin Li |
| collection | DOAJ |
| description | Abstract Objective Bloodstream infection (BSI) is a significant cause of mortality in patients with hematologic malignancies(HMs), particularly amid rising antibiotic resistance. This study aimed to analyze pathogen distribution, drug-resistance patterns and develop a novel predictive model for 30-day mortality in HM patients with BSIs. Methods A retrospective analysis of 231 HM patients with positive blood cultures was conducted. Logistic regression identified risk factors for 30-day mortality. Th1/Th2 cytokines were collected at BSI onset, with LASSO regression and restricted cubic spline analysis used to refine predictors. Seven machine learning(ML) algorithm (XGBoost, Logistic Regression, LightGBM, RandomForest, AdaBoost, GBDT and GNB) were trained using 10-fold cross-validation and model performance was evaluated with the ROC, calibration plots, decision and learning curves and the Shapley Additive Explanations (SHAP) analysis. The predictive model was developed by integrating Th1/Th2 cytokines with clinical features, aiming to enhance the accuracy of 30-day mortality prediction. Results Among the cohort, acute myeloid leukemia (38%) was the most common HM, while gram negative bacteria (64%) were the predominant pathogens causing BSI. Age, polymicrobial BSI, IL-4, IL-6 and AST levels were significant predictors of 30-day mortality. The Logistic Regression model achieved AUCs of 0.802, 0.792, and 0.822 in training, validation, and test cohorts, respectively, with strong calibration and clinical benefit shown in decision curves. SHAP analysis highlighted IL-4 and IL-6 as key predictors. Conclusions This study introduces a novel ML-based model integrating Th1/Th2 cytokines and clinical features to predict 30-day mortality in HM patients with BSIs, demonstrating strong performance and clinical applicability. |
| format | Article |
| id | doaj-art-375dedfd81cf4969bf592cc86d0928a7 |
| institution | Kabale University |
| issn | 1471-2334 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Infectious Diseases |
| spelling | doaj-art-375dedfd81cf4969bf592cc86d0928a72025-08-20T03:40:50ZengBMCBMC Infectious Diseases1471-23342025-03-0125111510.1186/s12879-025-10808-7Machine learning-based prognostic model for bloodstream infections in hematological malignancies using Th1/Th2 cytokinesQin Li0Nan Lin1Zuheng Wang2Yuexi Chen3Yuli Xie4Xuemei Wang5Jirui Tang6Yuling Xu7Min Xu8Na Lu9Yiqian Huang10Jiamin Luo11Zhenfang Liu12Li Jing13Department of Hematology, The First Affiliated Hospital of Guangxi Medical UniversityDepartment of Internal Medicine, Longmatan District Hospital of Traditional Chinese MedicineDepartment of Urology, The First Affiliated Hospital of Guangxi Medical UniversityThe Affiliated Hospital of Traditional Chinese Medicine, Southwest Medical UniversityDepartment of lmmunology, School of Basic Medical Sciences, Guangxi Medical UniversityDepartment of Hematology, The Affiliated Hospital of Southwest Medical UniversityDepartment of Hematology, The Affiliated Hospital of Southwest Medical UniversityDepartment of Hematology, The First Affiliated Hospital of Guangxi Medical UniversityDepartment of Hematology, The First Affiliated Hospital of Guangxi Medical UniversityDepartment of Hematology, The First Affiliated Hospital of Guangxi Medical UniversityDepartment of Hematology, The First Affiliated Hospital of Guangxi Medical UniversityDepartment of Hematology, The First Affiliated Hospital of Guangxi Medical UniversityDepartment of Hematology, The First Affiliated Hospital of Guangxi Medical UniversityDepartment of Hematology, The Affiliated Hospital of Southwest Medical UniversityAbstract Objective Bloodstream infection (BSI) is a significant cause of mortality in patients with hematologic malignancies(HMs), particularly amid rising antibiotic resistance. This study aimed to analyze pathogen distribution, drug-resistance patterns and develop a novel predictive model for 30-day mortality in HM patients with BSIs. Methods A retrospective analysis of 231 HM patients with positive blood cultures was conducted. Logistic regression identified risk factors for 30-day mortality. Th1/Th2 cytokines were collected at BSI onset, with LASSO regression and restricted cubic spline analysis used to refine predictors. Seven machine learning(ML) algorithm (XGBoost, Logistic Regression, LightGBM, RandomForest, AdaBoost, GBDT and GNB) were trained using 10-fold cross-validation and model performance was evaluated with the ROC, calibration plots, decision and learning curves and the Shapley Additive Explanations (SHAP) analysis. The predictive model was developed by integrating Th1/Th2 cytokines with clinical features, aiming to enhance the accuracy of 30-day mortality prediction. Results Among the cohort, acute myeloid leukemia (38%) was the most common HM, while gram negative bacteria (64%) were the predominant pathogens causing BSI. Age, polymicrobial BSI, IL-4, IL-6 and AST levels were significant predictors of 30-day mortality. The Logistic Regression model achieved AUCs of 0.802, 0.792, and 0.822 in training, validation, and test cohorts, respectively, with strong calibration and clinical benefit shown in decision curves. SHAP analysis highlighted IL-4 and IL-6 as key predictors. Conclusions This study introduces a novel ML-based model integrating Th1/Th2 cytokines and clinical features to predict 30-day mortality in HM patients with BSIs, demonstrating strong performance and clinical applicability.https://doi.org/10.1186/s12879-025-10808-7Bloodstream infectionHematological malignancyMachine learningModelMicrobiologyResistance |
| spellingShingle | Qin Li Nan Lin Zuheng Wang Yuexi Chen Yuli Xie Xuemei Wang Jirui Tang Yuling Xu Min Xu Na Lu Yiqian Huang Jiamin Luo Zhenfang Liu Li Jing Machine learning-based prognostic model for bloodstream infections in hematological malignancies using Th1/Th2 cytokines BMC Infectious Diseases Bloodstream infection Hematological malignancy Machine learning Model Microbiology Resistance |
| title | Machine learning-based prognostic model for bloodstream infections in hematological malignancies using Th1/Th2 cytokines |
| title_full | Machine learning-based prognostic model for bloodstream infections in hematological malignancies using Th1/Th2 cytokines |
| title_fullStr | Machine learning-based prognostic model for bloodstream infections in hematological malignancies using Th1/Th2 cytokines |
| title_full_unstemmed | Machine learning-based prognostic model for bloodstream infections in hematological malignancies using Th1/Th2 cytokines |
| title_short | Machine learning-based prognostic model for bloodstream infections in hematological malignancies using Th1/Th2 cytokines |
| title_sort | machine learning based prognostic model for bloodstream infections in hematological malignancies using th1 th2 cytokines |
| topic | Bloodstream infection Hematological malignancy Machine learning Model Microbiology Resistance |
| url | https://doi.org/10.1186/s12879-025-10808-7 |
| work_keys_str_mv | AT qinli machinelearningbasedprognosticmodelforbloodstreaminfectionsinhematologicalmalignanciesusingth1th2cytokines AT nanlin machinelearningbasedprognosticmodelforbloodstreaminfectionsinhematologicalmalignanciesusingth1th2cytokines AT zuhengwang machinelearningbasedprognosticmodelforbloodstreaminfectionsinhematologicalmalignanciesusingth1th2cytokines AT yuexichen machinelearningbasedprognosticmodelforbloodstreaminfectionsinhematologicalmalignanciesusingth1th2cytokines AT yulixie machinelearningbasedprognosticmodelforbloodstreaminfectionsinhematologicalmalignanciesusingth1th2cytokines AT xuemeiwang machinelearningbasedprognosticmodelforbloodstreaminfectionsinhematologicalmalignanciesusingth1th2cytokines AT jiruitang machinelearningbasedprognosticmodelforbloodstreaminfectionsinhematologicalmalignanciesusingth1th2cytokines AT yulingxu machinelearningbasedprognosticmodelforbloodstreaminfectionsinhematologicalmalignanciesusingth1th2cytokines AT minxu machinelearningbasedprognosticmodelforbloodstreaminfectionsinhematologicalmalignanciesusingth1th2cytokines AT nalu machinelearningbasedprognosticmodelforbloodstreaminfectionsinhematologicalmalignanciesusingth1th2cytokines AT yiqianhuang machinelearningbasedprognosticmodelforbloodstreaminfectionsinhematologicalmalignanciesusingth1th2cytokines AT jiaminluo machinelearningbasedprognosticmodelforbloodstreaminfectionsinhematologicalmalignanciesusingth1th2cytokines AT zhenfangliu machinelearningbasedprognosticmodelforbloodstreaminfectionsinhematologicalmalignanciesusingth1th2cytokines AT lijing machinelearningbasedprognosticmodelforbloodstreaminfectionsinhematologicalmalignanciesusingth1th2cytokines |