111536
论文已发表
注册即可获取德孚的最新动态
IF 收录期刊
- 3.4 Breast Cancer (Dove Med Press)
- 3.2 Clin Epidemiol
- 2.6 Cancer Manag Res
- 2.9 Infect Drug Resist
- 3.7 Clin Interv Aging
- 5.1 Drug Des Dev Ther
- 3.1 Int J Chronic Obstr
- 6.6 Int J Nanomed
- 2.6 Int J Women's Health
- 2.9 Neuropsych Dis Treat
- 2.8 OncoTargets Ther
- 2.0 Patient Prefer Adher
- 2.2 Ther Clin Risk Manag
- 2.5 J Pain Res
- 3.0 Diabet Metab Synd Ob
- 3.2 Psychol Res Behav Ma
- 3.4 Nat Sci Sleep
- 1.8 Pharmgenomics Pers Med
- 2.0 Risk Manag Healthc Policy
- 4.1 J Inflamm Res
- 2.0 Int J Gen Med
- 3.4 J Hepatocell Carcinoma
- 3.0 J Asthma Allergy
- 2.2 Clin Cosmet Investig Dermatol
- 2.4 J Multidiscip Healthc
已发表论文
开发用于预测分娩镇痛期间与硬膜外相关的产妇发热的机器学习模型：多算法比较研究及前瞻性实施框架
Authors Zhang G, Yang Y, An R, Tan Z
Received 14 August 2025
Accepted for publication 3 December 2025
Published 15 December 2025 Volume 2025:17 Pages 5439—5451
DOI https://doi.org/10.2147/IJWH.S560693
Checked for plagiarism Yes
Review by Single anonymous peer review
Peer reviewer comments 2
Editor who approved publication: Dr Everett Magann
Guoxiu Zhang,1 Yihui Yang,2 Rugang An,2 Zhengquan Tan2
1Department of Critical Care Medicine, Zunyi First People’s Hospital (Third Affiliated Hospital of Zunyi Medical College), Zunyi, 563000, People’s Republic of China; 2Department of Anesthesiology, Zunyi First People’s Hospital (Third Affiliated Hospital of Zunyi Medical College), Zuni, 563000, People’s Republic of China
Correspondence: Zhengquan Tan, Department of Anesthesiology, Zunyi First People’s Hospital (Third Affiliated Hospital of Zunyi Medical College), No. 98 Fenghuang Road, Huichuan District, Zunyi, Guizhou, 563000, People’s Republic of China, Tel +86 15985082482, Email zhengquantantzq01@126.com
Objective: To develop and validate a machine learning-based predictive model for assessing the risk of epidural-related maternal fever (ERMF)- a common complication during labor analgesia.
Methods: A prospective cohort study was conducted among 500 parturients with term singleton pregnancies who received epidural labor analgesia between September 2022 and August 2023. Key variables collected include maternal demographic characteristics, anesthesia-related indicators for complications, and obstetric features. Following application of exclusion criteria, 422 parturients were included and allocated into a modeling cohort (n = 337) and a validation cohort (n = 85) using stratified random sampling at an 8:2 ratio. Eleven machine learning algorithms were utilized to construct predictive models. Model performance was assessed using the area under the receiver operating characteristic curve (AUC), area under the precision-recall curve (AUPRC), accuracy, precision, recall, and F1-score.
Results: The incidence of ERMF was 28.1% (119/422). Among the evaluated algorithms, Categorical Boosting (CatBoost) demonstrated the highest performance, with an AUC of 0.94 (95% CI: 0.86– 0.98), accuracy of 90.59%, precision of 0.88, and average precision (AP) of 0.86 in the validation cohort. Analysis using SHapley Additive exPlanations (SHAP)-an interpretable artificial intelligence method- identified prolonged duration of rupture of membranes, higher maternal body mass index, and nulliparity as the top predictors of ERMF risk. An interactive web-based interface was developed to facilitate real-time clinical risk evaluation.
Conclusion: A machine learning model with high discriminative ability was constructed to predict the risk of ERMF. The CatBoost algorithm effectively identified parturients at elevated risk, and the accompanying visual tool offers evidence-based support for stratified management of intrapartum fever in clinical practice.
Keywords: epidural analgesia for labor, fever, intrapartum, labor analgesia, machine learning, predictive model
1Department of Critical Care Medicine, Zunyi First People’s Hospital (Third Affiliated Hospital of Zunyi Medical College), Zunyi, 563000, People’s Republic of China; 2Department of Anesthesiology, Zunyi First People’s Hospital (Third Affiliated Hospital of Zunyi Medical College), Zuni, 563000, People’s Republic of China
Correspondence: Zhengquan Tan, Department of Anesthesiology, Zunyi First People’s Hospital (Third Affiliated Hospital of Zunyi Medical College), No. 98 Fenghuang Road, Huichuan District, Zunyi, Guizhou, 563000, People’s Republic of China, Tel +86 15985082482, Email zhengquantantzq01@126.com
Objective: To develop and validate a machine learning-based predictive model for assessing the risk of epidural-related maternal fever (ERMF)- a common complication during labor analgesia.
Methods: A prospective cohort study was conducted among 500 parturients with term singleton pregnancies who received epidural labor analgesia between September 2022 and August 2023. Key variables collected include maternal demographic characteristics, anesthesia-related indicators for complications, and obstetric features. Following application of exclusion criteria, 422 parturients were included and allocated into a modeling cohort (n = 337) and a validation cohort (n = 85) using stratified random sampling at an 8:2 ratio. Eleven machine learning algorithms were utilized to construct predictive models. Model performance was assessed using the area under the receiver operating characteristic curve (AUC), area under the precision-recall curve (AUPRC), accuracy, precision, recall, and F1-score.
Results: The incidence of ERMF was 28.1% (119/422). Among the evaluated algorithms, Categorical Boosting (CatBoost) demonstrated the highest performance, with an AUC of 0.94 (95% CI: 0.86– 0.98), accuracy of 90.59%, precision of 0.88, and average precision (AP) of 0.86 in the validation cohort. Analysis using SHapley Additive exPlanations (SHAP)-an interpretable artificial intelligence method- identified prolonged duration of rupture of membranes, higher maternal body mass index, and nulliparity as the top predictors of ERMF risk. An interactive web-based interface was developed to facilitate real-time clinical risk evaluation.
Conclusion: A machine learning model with high discriminative ability was constructed to predict the risk of ERMF. The CatBoost algorithm effectively identified parturients at elevated risk, and the accompanying visual tool offers evidence-based support for stratified management of intrapartum fever in clinical practice.
Keywords: epidural analgesia for labor, fever, intrapartum, labor analgesia, machine learning, predictive model