Early recognition of sepsis-associated acute kidney injury based on BioBERT-BPNN multimodal clinical data analysis
Yufeng Chen, Hongyang Bian, Yuye Li · 2026
Read Early recognition of sepsis-associated acute kidney injury based on BioBERT-BPNN multimodal clinical data analysis by Yufeng Chen, Hongyang Bian, Yuye Li (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-0357602.txt.
Description
Yufeng Chen, Hongyang Bian, and Yuye Li published a 2026 methods paper in PLOS ONE on spotting kidney injury early in sepsis patients. Sepsis often damages the kidneys quickly, but early signs are vague and outcomes are poor. The team built a dataset from two centers, an American public intensive care database and a Chinese hospital's records, extracting dozens of risk factors per patient as both text and numbers.
Their model reads those two streams with separate networks, one tuned for medical language and one for numerical patterns, then fuses them to classify risk. It performed steadily at the first center and carried over well to the second hospital, and the combined model beat versions using text or numbers alone. Training on two centers made it more adaptable to local patients. It is offered as decision support for earlier intervention, not a replacement for clinical judgment.
Catalog record
| CREATOR | Yufeng Chen, Hongyang Bian, Yuye Li |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 32413 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |