Crowding in real-time: an artificial intelligence-based model to manage crowding in the emergency department (CRAMMED Study)
E E Schippers, S P Willemsen, L A M Collée, K L M Koenraadt, S Schol-Gelok · 2026
Read Crowding in real-time: an artificial intelligence-based model to manage crowding in the emergency department (CRAMMED Study) by E E Schippers, S P Willemsen, L A M Collée, K L M Koenraadt, S Schol-Gelok (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/PMC13520244.txt.
Description
E E Schippers and four colleagues build in 2026 an artificial intelligence model that warns a Dutch emergency department of crowding an hour before it hits. Standard crowding scores react rather than predict. Trained on electronic records and staffing data, their memory-based neural network used ambulance diversion status as the truth signal for real crowding.
Feeding the model the previous hour's data to forecast the next hour produced an accuracy score of 0.84, beating the modified standard score's 0.73. Pre-notified arrivals, mid-acuity patient counts, and supervisor numbers carried the most predictive weight. Calibration stayed reasonable. Schippers and colleagues say real-time forecasts could help staff act before corridors fill, though validation so far covers one center only.
Catalog record
| CREATOR | E E Schippers, S P Willemsen, L A M Collée, K L M Koenraadt, S Schol-Gelok |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 34269 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |