Multimodal Deep Learning for Predicting Deep Vein Thrombosis Risk After Total Knee Arthroplasty: A Clinical Study
Kejia Zhu, Hang Li, Hui Zhang, Biao Wang, Bin Shen, Yong Nie · 2026
Read Multimodal Deep Learning for Predicting Deep Vein Thrombosis Risk After Total Knee Arthroplasty: A Clinical Study by Kejia Zhu, Hang Li, Hui Zhang, Biao Wang, Bin Shen, Yong Nie (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/PMC13398790.txt.
Description
Kejia Zhu and co-authors train a deep learning system that reads X-rays and medical records together to flag clot risk after knee replacement. Their 2026 study covers 1,200 patients at one centre from January 2018 to June 2023, where deep vein thrombosis struck 18.0 percent after surgery. The standard Caprini score predicts only modestly, with accuracy areas of 0.65 to 0.72 in the literature cited.
One network branch reads standardised post-surgery radiographs while a language model digests the written record, and an attention module weighs the two streams per patient. A held-out test set of 180 patients graded the system. Beating the old score would let wards aim blood-thinning cover at the patients who truly need it.
Catalog record
| CREATOR | Kejia Zhu, Hang Li, Hui Zhang, Biao Wang, Bin Shen, Yong Nie |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 29138 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |