Risk prediction model for non-/hypo- response to hepatitis B vaccine of infants born to HBsAg positive mothers in Taiyuan City on machine learning algorithms

WANG Huixin; XU Xiuyang; LI Yandi; YAO Tian; QU Yiqun; FENG Shuying; LI Yuping; FENG Yongliang; WANG Keke; WANG Suping

doi:10.16462/j.cnki.zhjbkz.2025.07.007

Volume 29 Issue 7

Jul. 2025

Turn off MathJax

Article Contents

Article Navigation > CHINESE JOURNAL OF DISEASE CONTROL & PREVENTION > 2025 > 29(7): 790-797

WANG Huixin, XU Xiuyang, LI Yandi, YAO Tian, QU Yiqun, FENG Shuying, LI Yuping, FENG Yongliang, WANG Keke, WANG Suping. Risk prediction model for non-/hypo- response to hepatitis B vaccine of infants born to HBsAg positive mothers in Taiyuan City on machine learning algorithms[J]. CHINESE JOURNAL OF DISEASE CONTROL & PREVENTION, 2025, 29(7): 790-797. doi: 10.16462/j.cnki.zhjbkz.2025.07.007

Citation:

WANG Huixin, XU Xiuyang, LI Yandi, YAO Tian, QU Yiqun, FENG Shuying, LI Yuping, FENG Yongliang, WANG Keke, WANG Suping. Risk prediction model for non-/hypo- response to hepatitis B vaccine of infants born to HBsAg positive mothers in Taiyuan City on machine learning algorithms[J]. CHINESE JOURNAL OF DISEASE CONTROL & PREVENTION, 2025, 29(7): 790-797. doi: 10.16462/j.cnki.zhjbkz.2025.07.007

Citation:

WANG Huixin, XU Xiuyang, LI Yandi, YAO Tian, QU Yiqun, FENG Shuying, LI Yuping, FENG Yongliang, WANG Keke, WANG Suping. Risk prediction model for non-/hypo- response to hepatitis B vaccine of infants born to HBsAg positive mothers in Taiyuan City on machine learning algorithms[J]. CHINESE JOURNAL OF DISEASE CONTROL & PREVENTION, 2025, 29(7): 790-797. doi: 10.16462/j.cnki.zhjbkz.2025.07.007

PDF( 986 KB)

Risk prediction model for non-/hypo- response to hepatitis B vaccine of infants born to HBsAg positive mothers in Taiyuan City on machine learning algorithms

doi: 10.16462/j.cnki.zhjbkz.2025.07.007

WANG Huixin^{1, 2, 3, 4},
XU Xiuyang¹,
LI Yandi^{1, 2, 3, 4},
YAO Tian^{2, 5},
QU Yiqun⁶,
FENG Shuying⁶,
LI Yuping⁶,
FENG Yongliang^{1, 2, 3, 4},
WANG Keke^{5
,
,},
WANG Suping^{1, 2, 3, 4
,
,}

1.
Department of Epidemiology, School of Public Health, Shanxi Medical University, Taiyuan 030001, China
2.
Center of Clinical Epidemiology and Evidence Based Medicine, Shanxi Medical University, Taiyuan 030001, China
3.
MOE Key Laboratory of Coal Environmental Pathogenicity and Prevention, Shanxi Medical University, Taiyuan 030001, China
4.
Research Center for Reverse Etiology, Workstation of Academician, Shanxi Medical University, Taiyuan 030001, China
5.
First Clinical Medical College of Shanxi Medical University, Taiyuan 030001, China
6.
Department of Obstetrics and Gynaecology, Third People Hospital of Taiyuan, Taiyuan 030001, China

Funds:

National Natural Science Foundation of China 81872677

National Natural Science Foundation of China 82073622

Fundamental Research Program of Shanxi Province 202303021211122

Four "Batches" Innovation Project of Invigorating Medical through Science and Technology of Shanxi Province 2023XM037

Research Project Supported by Shanxi Scholarship Council of China 2023-096

More Information

Corresponding author: WANG Keke, E-mail: kkwang86@163.com; WANG Suping, E-mail: supingwang@sxmu.edu.cn
Received Date: 2024-10-24
Rev Recd Date: 2025-01-22

Available Online: 2025-08-11

Publish Date: 2025-07-10

Abstract

Abstract

Objective Based on machine learning algorithms, risk prediction models for non-/hypo- response to hepatitis B vaccine of infants born to HBsAg-positive mothers in Taiyuan city were constructed to provide a reference for early identification and prevention of such high-risk infants. Methods HBsAg-positive mothers and their infants born in the Department of Obstetrics and Gynecology of the Third People′s Hospital of Taiyuan City between November 2019 and October 2023 were selected as the study population. The data were collected through questionnaire surveys and medical record reviews. The multivariate logistic regression model was used to screen risk factors. The dataset was divided using five-fold cross-validation. After that, the synthetic minority over-sampling technique resampling technique was applied to the training set data. The logistic regression, extreme gradient boosting), decision tree and random forest prediction models were constructed. The area under the curve (AUC) was used to evaluate the prediction performance of the models. Results A total of 253 HBsAg-positive maternal and infant cases were collected, and the non-/hypo- response rate was 10.28% (26/253) among infants after hepatitis B vaccination. The logistic regression model showed that maternal hepatitis B virus DNA load, the percentage of neonatal myeloid differentiation factor 88 protein, the percentage of phosphorylation of nuclear factor kappa-B protein and the percentage of plasma cell were influencing factors for the non-/hypo-response to hepatitis B vaccine in infants. Considering the above factors, the AUC of each model was above 0.800 in the validation set. The XGBoost model had the highest predictive performance, and the AUC value was 0.919. Conclusions The risk prediction model for the non-/hypo- response to hepatitis B vaccine in infants of HBsAg-positive mothers in Taiyuan city based on machine learning algorithms, especially the XGBoost algorithm, has good efficacy, which helps predict the occurrence of the non-/hypo- response to hepatitis B vaccine in infants.
- Machine learning,
- Hepatitis B surface antigen,
- Hepatitis B vaccine,
- Non-/hypo- response,
- Risk prediction model

FullText(HTML)

References(16)

References

[1]	World Health Organization. Global hepatitis report 2024: action for access in low- and middle-income countries[EB/OL]. (2024-04-09)[2025-01-03]. https://www.who.int/publications/i/item/9789240091672.
[2]	WHO. Hepatitis B vaccines: WHO position paper, July 2017- Recommendations[J]. Vaccine, 2019, 37(2): 223- 225. DOI: 10.1016/j.vaccine.2017.07.046.
[3]	Saco TV, Strauss AT, Ledford DK. Hepatitis B vaccine nonresponders: possible mechanisms and solutions[J]. Ann Allergy Asthma Immunol, 2018, 121(3): 320-327. DOI: 10.1016/j.anai.2018.03.017.
[4]	王雪飞, 史晓红, 许喜喜, 等. 白介素-6和白介素-12在HBsAg阳性母亲婴儿乙肝疫苗免疫应答中的作用[J]. 中华流行病学杂志, 2017, 38(7): 950-953. DOI: 10.3760/cma.j.issn.0254-6450.2017.07.020. Wang XF, Shi XH, Xu XX, et al. Effect of interleukin-6 and interleukin-12 on immune response to hepatitis B vaccination in infants of HBsAg-positive mothers[J]. Chin J Epidemiol, 2017, 38(7): 950-953. DOI: 10.3760/cma.j.issn.0254-6450.2017.07.020.
[5]	Lu Y, Liang XF, Wang FZ, et al. Hepatitis B vaccine alone may be enough for preventing hepatitis B virus transmission in neonates of HBsAg (+)/HBeAg (-) mothers[J]. Vaccine, 2017, 35(1): 40-45. DOI: 10.1016/j.vaccine.2016.11.061.
[6]	Song YR, Zhang X, Liu MM, et al. A booster hepatitis B vaccine for children with maternal HBsAg positivity before 2 years of age could effectively prevent vaccine breakthrough infections[J]. BMC Infect Dis, 2022, 22(1): 863. DOI: 10.1186/s12879-022-07854-w.
[7]	Jeng WJ, Papatheodoridis GV, Lok ASF. Hepatitis B[J]. Lancet, 2023, 401(10381): 1039-1052. DOI: 10.1016/S0140-6736(22)01468-4.
[8]	中华医学会肝病学分会, 中华医学会感染病学分会, 尤红, 等. 慢性乙型肝炎防治指南(2022年版)[J]. 中华临床感染病杂志, 2022, 15(6): 401-427. DOI: 10.3760/cma.j.issn.1674-2397.2022.06.001. Chinese Society of Hepatology, Chinese Society of Infectious Diseases, You H, et al. Guidelines for prevention and treatment of chronic hepatitis B (2022 edition)[J]. Chin J Clin Infect Dis, 2022, 15(6): 401-427. DOI: 10.3760/cma.j.issn.1674-2397.2022.06.001.
[9]	Joshi SS, Coffin CS. Hepatitis B and pregnancy: virologic and immunologic characteristics[J]. Hepatol Commun, 2020, 4(2): 157-171. DOI: 10.1002/hep4.1460.
[10]	Jiang HX, Chen C, Yuan DP, et al. The relationship of maternal hepatitis B e antigen and response to vaccination of infants born to women with chronic infection[J]. BMC Pregnancy Childbirth, 2023, 23(1): 518. DOI: 10.1186/s12884-023-05815-y.
[11]	Lu HH, Cao WH, Zhang LX, et al. Effects of hepatitis B virus infection and strategies for preventing mother-to-child transmission on maternal and fetal T-cell immunity[J]. Front Immunol, 2023, 14: 1122048. DOI: 10.3389/fimmu.2023.1122048.
[12]	Zhao XL, Bai XX, Xi YM. Intrauterine infection and mother-to-child transmission of hepatitis B virus: route and molecular mechanism[J]. Infect Drug Resist, 2022, 15: 1743-1751. DOI: 10.2147/IDR.S359113.
[13]	Lee YT, Ko EJ, Kim KH, et al. Cellular immune correlates preventing disease against respiratory syncytial virus by vaccination with virus-like nanoparticles carrying fusion proteins[J]. J Biomed Nanotechnol, 2017, 13(1): 84-98. DOI: 10.1166/jbn.2017.2341.
[14]	Liu X, Yao JC, Zhao YS, et al. Heterogeneous plasma cells and long-lived subsets in response to immunization, autoantigen and microbiota[J]. Nat Immunol, 2022, 23(11): 1564-1576. DOI: 10.1038/s41590-022-01345-5.
[15]	Wu JF, Yang K, Cai SW, et al. A p38α-BLIMP1 signalling pathway is essential for plasma cell differentiation[J]. Nat Commun, 2022, 13(1): 7321. DOI: 10.1038/s41467-022-34969-0.
[16]	Bentéjac C, Csörgö A, Martínez-Muñoz G. A comparative analysis of gradient boosting algorithms[J]. Artif Intell Rev, 2021, 54(3): 1937-1967. DOI: 10.1007/s10462-020-09896-5.