An interpretable machine learning model integrating mucosal and cellular immunity to predict SARS-CoV-2 reinfection: a multicenter cohort study.
8 affiliations
- 1Department of Infectious Disease, Nanjing Drum Tower Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, People's Republic of China.
- 2Department of Laboratory Medicine, Nanjing Drum Tower Hospital, Joint Institute of Nanjing Drum Tower Hospital for Life and Health, College of Life Science, Nanjing Normal University, Nanjing, People's Republic of China.
- 3Department of Laboratory Medicine, Nanjing Drum Tower Hospital Clinical College of Nanjing Medical University, Nanjing, People's Republic of China.
- 4Center of Medical Big Data, Nanjing Drum Tower Hospital, Affiliated Drum Tower Hospital, Medical School of Nanjing University, Nanjing, People's Republic of China.
- 5School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, People's Republic of China.
- 6Department of Laboratory Medicine, Nanjing Drum Tower Hospital, Clinical College of Jiangsu University, Nanjing, People's Republic of China.
- 7Department of Acute Infectious Disease Control and Prevention, Jiangsu Provincial Center for Disease Control and Prevention, Nanjing, People's Republic of China.
- 8Department of Laboratory Medicine, Nanjing Drum Tower Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, People's Republic of China.
Abstract
SARS-CoV-2 reinfection remains a significant public health challenge that requires accurate risk assessment across populations. Using prospectively collected data from two independent cohorts, we developed and externally validated an interpretable machine learning model for predicting symptomatic SARS-CoV-2 reinfection. The cohort comprised 1,156 adults from Wuxi and Nantong, China, with a median follow-up duration of 10 months. Reinfection occurred in 128 participants (11.1%). The model integrated eighteen clinical and immune features, and ultimately identified spike-specific nasal secretory immunoglobulin A (sIgA) and spike-specific CD4⁺ central memory T cells (TCM) as key predictors. Developed using the extreme gradient boosting (XGB) algorithm, the prediction model achieved an AUC of 0.835 in the internal validation cohort and demonstrated strong discrimination in the external validation cohort. SHAP analysis revealed that higher nasal spike-specific sIgA was associated with lower risk, while spike-specific CD4⁺ TCM cells exhibited a non-linear association with reinfection. This interpretable immune-based model provides a framework for immune-informed risk stratification, enabling better prediction and management of SARS-CoV-2 reinfection risk in settings with heterogeneous population immunity.
Related
- Multicenter evaluation of AI-based intraocular lens formulas and interpretable machine learning for cataract refractive prediction
- Radiomics-based interpretable machine learning model for identifying high-risk patients with small bowel obstruction: a multicenter study.
- Development and Validation of an Interpretable Machine‐Learning Model for Predicting Suboptimal Clinical Response After Sleeve Gastrectomy: A Multicenter Study
- Systemic immune dysregulation and local barrier failure as predictors of septic shock in acute appendicitis: a large-scale multicenter interpretable machine learning study
- An Interpretable Machine Learning Framework Integrating Multi-Window Environmental Exposure for Hypertension Risk Assessment.
BibTeX
@article{ran2026interpretable,
title = {{An interpretable machine learning model integrating mucosal and cellular immunity to predict SARS-CoV-2 reinfection: a multicenter cohort study.}},
author = {Jinqiu Ran and Wen Zhang and Wanying Zhang and Hui Huang and Lejun Gong and Shengxia Yin and Yu Chen and Aofan Wang and Huijin Min and Liguo Zhu and Jinjin Chu and Yuanfang Qin and Rui Huang and Chao Wu and Yuxin Chen},
journal = {Emerging microbes \& infections},
year = {2026},
month = oct,
doi = {10.1080/22221751.2026.2746253},
url = {https://europepmc.org/article/MED/42908321},
note = {CC BY},
}
RIS
TY - JOUR
TI - An interpretable machine learning model integrating mucosal and cellular immunity to predict SARS-CoV-2 reinfection: a multicenter cohort study.
AU - Jinqiu Ran
AU - Wen Zhang
AU - Wanying Zhang
AU - Hui Huang
AU - Lejun Gong
AU - Shengxia Yin
AU - Yu Chen
AU - Aofan Wang
AU - Huijin Min
AU - Liguo Zhu
AU - Jinjin Chu
AU - Yuanfang Qin
AU - Rui Huang
AU - Chao Wu
AU - Yuxin Chen
PY - 2026
DA - 2026/10/21
JO - Emerging microbes & infections
DO - 10.1080/22221751.2026.2746253
UR - https://europepmc.org/article/MED/42908321
AB - SARS-CoV-2 reinfection remains a significant public health challenge that requires accurate risk assessment across populations. Using prospectively collected data from two independent cohorts, we developed and externally validated an interpretable machine learning model for predicting symptomatic SARS-CoV-2 reinfection. The cohort comprised 1,156 adults from Wuxi and Nantong, China, with a median follow-up duration of 10 months. Reinfection occurred in 128 participants (11.1%). The model integrated eighteen clinical and immune features, and ultimately identified spike-specific nasal secretory immunoglobulin A (sIgA) and spike-specific CD4⁺ central memory T cells (TCM) as key predictors. Developed using the extreme gradient boosting (XGB) algorithm, the prediction model achieved an AUC of 0.835 in the internal validation cohort and demonstrated strong discrimination in the external validation cohort. SHAP analysis revealed that higher nasal spike-specific sIgA was associated with lower risk, while spike-specific CD4⁺ TCM cells exhibited a non-linear association with reinfection. This interpretable immune-based model provides a framework for immune-informed risk stratification, enabling better prediction and management of SARS-CoV-2 reinfection risk in settings with heterogeneous population immunity.
SN - 2222-1751
ER -