Predicting the incidence of syphilis in China using Baidu search index and an ARIMAX model
Jianbo Yuan, Zuyi Chen, Yanqiong Yuan, ShiXu Li, Jinlie Long, Renqing Yan, Xinpeng Zhang, Lian Huang, Jian Huang, Jida Li, Junqiong Huang · 2026
Read Predicting the incidence of syphilis in China using Baidu search index and an ARIMAX model by Jianbo Yuan, Zuyi Chen, Yanqiong Yuan, ShiXu Li, Jinlie Long, Renqing Yan, Xinpeng Zhang, Lian Huang, Jian Huang, Jida Li, Junqiong Huang (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-13455269.txt.
Description
Jianbo Yuan and colleagues built a 2026 forecast for syphilis cases in China from public web search data. Case counts for the sexually spread infection have climbed for years in China, while routine watch systems react slowly and cannot warn ahead. The team paired monthly case reports from January 2011 to March 2025 with Baidu search volumes for linked terms, then blended the strongest terms into one search index.
A seasonal time model using that index beat the same model without it on every error measure. Mean absolute error fell from about 9,008 cases to about 5,184 cases. Mean percentage error fell from 16.0 percent to 10.0 percent in the test period. The gain matters because earlier warning could let health teams ready clinics and outreach before a rise peaks. Search data cannot replace case reports, but here it sharpened a plain forecast in a useful way.
Catalog record
| CREATOR | Jianbo Yuan, Zuyi Chen, Yanqiong Yuan, ShiXu Li, Jinlie Long, Renqing Yan, Xinpeng Zhang, Lian Huang, Jian Huang, Jida Li, Junqiong Huang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 40 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |