Summary
Identifying patients at highest risk of serious adverse prognostic events (AE) in neurosyphilis could enable risk-stratified treatment beyond clinical judgment. We developed machine-learning models using electronic health records from six Chinese infectious-diseases hospitals, with two centers for external validation and four for discovery. Five models incorporated demographic, clinical, laboratory, and treatment variables from 602 observations (402 discovery, 200 validation). AE occurred in 20.90% and 20.50% respectively. DEFEAT-NS-M1 achieved AUROC 0.975 (95% CI 0.949-0.995) internally and 0.863 (0.801-0.920) externally, with Brier scores 0.027 and 0.128. Decision curve analysis demonstrated favorable clinical utility; treating 1-2 high-risk patients prevents one AE. DEFEAT-NS-M1 supports population-level risk estimation and stratified care, potentially guiding targeted monitoring and therapy. Further external validation and health-economic assessment are warranted.
Citation
@article{RN1585,
author = {Lu, Zhen and Zou, Jun and Zhang, Hanlin and Zou, Meiyin and Fu, Yanhua and Zhang, Renfang and Shi, Haoran and Wu, Weibo and Xue, Bichen and Wang, Ruonan and Yang, Xiaoyan and Cai, Jing and Gan, Lin and Liu, Shangbin and Cai, Yong and Peng, Zhihang and Li, Jun and Yang, Liuqing and Chen, Jun and Zou, Huachun},
title = {A machine learning model for predicting adverse prognostic events in patients with neurosyphilis: results from the DEFEAT-NS study},
journal = {iScience},
pages = {115104},
ISSN = {2589-0042},
DOI = {10.1016/j.isci.2026.115104},
url = {https://www.sciencedirect.com/science/article/pii/S2589004226004797},
year = {2026},
type = {Journal Article}
}