Deep learning predicts stent implantation in borderline coronary lesions from angiography

Jingsong Xia, Di Zhao, Yiming Zhang, Leilei Chen, Zhenhua Yang, Dengqing Shi, Chao Liu, Haoyu Meng, Liansheng Wang, Jiabao Liu · 2026

Read Deep learning predicts stent implantation in borderline coronary lesions from angiography by Jingsong Xia, Di Zhao, Yiming Zhang, Leilei Chen, Zhenhua Yang, Dengqing Shi, Chao Liu, Haoyu Meng, Liansheng Wang, Jiabao 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/pmc-13624263.txt.

Description

Jingsong Xia and colleagues built a deep-learning tool that predicts whether a borderline coronary narrowing needs a stent, using angiography images alone, in a 2026 multicenter study. Narrowings that block fifty to seventy percent of a vessel sit in a gray zone: eyeballing angiograms is subjective, while pressure-wire and imaging tests that settle the question are invasive or costly. The team trained an attention-enhanced network on 1,298 patients, with labels drawn from pressure and imaging reference tests.

Internal testing reached about 97.6 percent accuracy, while external testing at independent hospitals held at 80.7 percent accuracy with strong discrimination. Heat maps showed the model attending to the narrowed segments clinicians themselves judge, which builds trust in its reasoning. Cardiologists get a decision-support candidate that could cut extra invasive testing, though prospective trials must confirm it before it guides real stent choices.

Catalog record

CREATORJingsong Xia, Di Zhao, Yiming Zhang, Leilei Chen, Zhenhua Yang, Dengqing Shi, Chao Liu, Haoyu Meng, Liansheng Wang, Jiabao Liu
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE93 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13624263

Browse the full library · About the Tower of Babel