LASSO regression-based machine learning model for differentiating spinal tuberculosis, pyogenic spondylitis, and endplate osteochondritis: development and clinical application
Tuo Liang, Wenyang Chen, Yunfeng Nie, Zide Zhang, Xingming Lai, Kelin Li, Yonghui Wang, Yanjian Tang, Xubin Quan, Binhao Chen, Tongqing Luo · 2026
Read LASSO regression-based machine learning model for differentiating spinal tuberculosis, pyogenic spondylitis, and endplate osteochondritis: development and clinical application by Tuo Liang, Wenyang Chen, Yunfeng Nie, Zide Zhang, Xingming Lai, Kelin Li, Yonghui Wang, Yanjian Tang, Xubin Quan, Binhao Chen, Tongqing Luo (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-13269071.txt.
Description
Tuo Liang and co-authors build in 2026 a machine learning aid for separating three look-alike spine diseases. The three are spinal tuberculosis, bacterial spine infection, and a worn endplate condition called osteochondritis. Mistakes between them delay the right treatment. Their study gathered 481 patients from a Liuzhou hospital between 2020 and 2024 and split them into training and test groups.
Six algorithms competed, and a regularized regression model using twelve chosen features won. It spotted spinal tuberculosis and the endplate condition well, while the bacterial infection proved hardest to pin down. A scoring method ranked how much each feature drove each prediction. The team also released a free web calculator that walks clinicians through the differential.
Catalog record
| CREATOR | Tuo Liang, Wenyang Chen, Yunfeng Nie, Zide Zhang, Xingming Lai, Kelin Li, Yonghui Wang, Yanjian Tang, Xubin Quan, Binhao Chen, Tongqing Luo |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 35 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |