From bedside to bench: towards clinical predictive AI research that achieves real-world impact
Shuqing Si, Gary S Collins, Joseph E Alderman, Ben Van Calster, Laure Wynants, Matthew R Broome, Paulina Daw, Alastair K Denniston, Joie Ensor, Benjamin I Perry · 2026
Read From bedside to bench: towards clinical predictive AI research that achieves real-world impact by Shuqing Si, Gary S Collins, Joseph E Alderman, Ben Van Calster, Laure Wynants, Matthew R Broome, Paulina Daw, Alastair K Denniston, Joie Ensor, Benjamin I Perry (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/pmc-13528389.txt.
Description
Si and co-authors diagnose why clinical prediction tools powered by artificial intelligence so rarely reach patients, despite thousands of published models. Their 2026 narrative review argues the failure is planned in from the start: researchers build models first and wonder about deployment later. The authors propose reversing the direction, a bedside-to-bench discipline. It begins by defining the clinical question, the intended user, and the exact point in the care pathway where a score would change a decision.
Around that core they arrange the neglected homework: early and continuing engagement with clinicians and patients, and a programme theory linking model outputs to changed outcomes. Regulatory routes, funding models that keep software alive, equity checks, and the engineering of implementation and monitoring complete the list. Methodological hygiene still matters, they note, since reviews keep finding sloppy methods and incomplete reporting, but rigour alone cannot cross the translational gap.
Catalog record
| CREATOR | Shuqing Si, Gary S Collins, Joseph E Alderman, Ben Van Calster, Laure Wynants, Matthew R Broome, Paulina Daw, Alastair K Denniston, Joie Ensor, Benjamin I Perry |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 43 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |