Deep learning to predict emergency department revisit using static and dynamic features (Deep Revisit): development and validation study
Su-Yin Hsu, Jhe-Yi Jhu, Jun-Wan Gao, Chien-Hua Huang, Chu-Lin Tsai, Li-Chen Fu · 2025
Read Deep learning to predict emergency department revisit using static and dynamic features (Deep Revisit): development and validation study by Su-Yin Hsu, Jhe-Yi Jhu, Jun-Wan Gao, Chien-Hua Huang, Chu-Lin Tsai, Li-Chen Fu (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-12750547.txt.
Description
Six authors present a study in two thousand twenty-five on predicting which emergency patients will come back. Return visits strain emergency departments, and the dangerous ones, ending in intensive care, arrest, or emergency surgery, matter most. Earlier prediction work leaned on fixed facts and rarely used changing vital signs.
Using records from a major Taiwan hospital across four years, the team built a hybrid deep learning model. It joins a temporal network for the vital-sign streams with a transformer for fixed facts like age and triage level. The model scored well at flagging the rare high-risk returns.
Catalog record
| CREATOR | Su-Yin Hsu, Jhe-Yi Jhu, Jun-Wan Gao, Chien-Hua Huang, Chu-Lin Tsai, Li-Chen Fu |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 78 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |