A multicenter prospective cohort study developing and validating a SIRI-based machine learning model and simplified risk score for predicting postherpetic neuralgia
Mengying Mao, Fangzheng Cao, Yongxing Yan, Huili Liu, Wenjing Wu, Bin Xu · 2026
Read A multicenter prospective cohort study developing and validating a SIRI-based machine learning model and simplified risk score for predicting postherpetic neuralgia by Mengying Mao, Fangzheng Cao, Yongxing Yan, Huili Liu, Wenjing Wu, Bin Xu (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13279421.txt.
Description
Mengying Mao and colleagues published a 2026 multi-site study building a prediction model for postherpetic neuralgia, the persistent nerve pain that follows shingles. The team followed 1,361 patients from two hospitals in Hangzhou and Zhejiang, of whom 511, about 37.6 percent, developed the outcome. They screened 36 candidate factors and focused on SIRI, a blood index combining several immune cell counts that reflects body-wide inflammation.
Inflammation measured by SIRI predicted who developed lasting pain on its own. Selection narrowed the model to six factors: age, SIRI, initial pain strength, delay before treatment, rash location, and a neutrophil-to-albumin ratio. Among eight machine learning methods, the XGBoost model performed best, with accuracy scores between about 0.86 and 0.90 across training, internal test, and external patient groups. The authors also converted the model into a simple paper risk score, aiming at a first-visit tool to flag patients for early, aggressive pain prevention.
Catalog record
| CREATOR | Mengying Mao, Fangzheng Cao, Yongxing Yan, Huili Liu, Wenjing Wu, Bin Xu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 62 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |