Development and validation of a deep learning model for severe mitral stenosis detection from chest X-rays
Bo Li, Kankan Zhao, Ang Liu, Wenqing Xu, Yun Tang, Kai Yang, Linlin Dai, Xiuyu Chen, Shihua Zhao, Chaowu Yan · 2025
Read Development and validation of a deep learning model for severe mitral stenosis detection from chest X-rays by Bo Li, Kankan Zhao, Ang Liu, Wenqing Xu, Yun Tang, Kai Yang, Linlin Dai, Xiuyu Chen, Shihua Zhao, Chaowu Yan (2025) 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-12742110.txt.
Description
Bo Li and co-authors build a deep learning model to spot severe mitral stenosis on chest X-rays in this 2025 paper. A narrowed heart valve is hard to diagnose from an X-ray alone, yet X-rays are cheap and common everywhere. An automated reader could screen for the disease where specialists are scarce.
The team trained the model on 515 chest images, 285 from patients with the disease and 230 from healthy controls, split into training, tuning, and test sets. The model scored near-perfect discrimination on both held-out sets, with accuracy of 0.96 and 0.94. Heat maps showed it focused on regions matching known X-ray signs of the disease. The authors offer it as a screening aid.
Catalog record
| CREATOR | Bo Li, Kankan Zhao, Ang Liu, Wenqing Xu, Yun Tang, Kai Yang, Linlin Dai, Xiuyu Chen, Shihua Zhao, Chaowu Yan |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 21 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |