Predicting ankylosing spondylitis disease activity via patient-reported outcome measures: Building prediction models based on machine learning
Yifan Gong, Aomei Liu, Li Zhuo, Xueyuan Xu, Hongxiao Liu · 2026
Read Predicting ankylosing spondylitis disease activity via patient-reported outcome measures: Building prediction models based on machine learning by Yifan Gong, Aomei Liu, Li Zhuo, Xueyuan Xu, Hongxiao Liu (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/plos-pone-0353486.txt.
Description
Yifan Gong and four colleagues teach machine-learning models to estimate spinal disease activity in ankylosing spondylitis from patients' own answers, in this 2026 PLOS ONE study. The standard activity score needs a blood test for inflammation, which clinics cannot always run quickly. Their data came from a Chinese registry of nearly four hundred patients, with thirty-four variables spanning clinical measures and questionnaires on pain, stiffness, function, fatigue, and mood.
Ten model combinations were built and tested on held-out patients. The best agreed strongly with the blood-based score. A reliable questionnaire-only estimate could let patients report from home between visits, flagging flares early and sparing stable patients unnecessary trips — though wider validation comes first.
Catalog record
| CREATOR | Yifan Gong, Aomei Liu, Li Zhuo, Xueyuan Xu, Hongxiao Liu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 29045 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |