AI-powered models for overcrowding prediction at TUMS hospitals
Mohammad Javad Shaibani, Ali Akbar Fazaeli, Rajabali Daroudi, Maryam Radinmanesh, Sara Emamgholipour Sefiddashti · 2025
Read AI-powered models for overcrowding prediction at TUMS hospitals by Mohammad Javad Shaibani, Ali Akbar Fazaeli, Rajabali Daroudi, Maryam Radinmanesh, Sara Emamgholipour Sefiddashti (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-12780012.txt.
Description
Shaibani and co-authors build AI models that forecast emergency department crowding at five Tehran hospitals, in this 2025 paper. A packed emergency room raises waiting times, errors, and deaths. A good forecast works like an alarm bell, letting managers act before the surge hits.
The team gathered time series data with over a hundred candidate signals per site. New selection methods trimmed those to the most telling few. Eight model types were trained and then blended by ensemble rules. Careful tuning used growing time windows to mimic real forecasting. The paper reports which blend predicted daily crowding best, and how feature trimming helped.
Catalog record
| CREATOR | Mohammad Javad Shaibani, Ali Akbar Fazaeli, Rajabali Daroudi, Maryam Radinmanesh, Sara Emamgholipour Sefiddashti |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 123 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |