The F score ranks diagnostic tests and prediction models inconsistently with their clinical utility
Melissa Assel, Andrew Vickers · 2025
Read The F score ranks diagnostic tests and prediction models inconsistently with their clinical utility by Melissa Assel, Andrew Vickers (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-12683848.txt.
Description
Melissa Assel and Andrew Vickers argue, in 2025 work, that a score widely used to grade tests and forecast models in machine work can mislead doctors. The score blends how many flagged cases are true with how many true cases are found. In most uses both parts count the same, by a fixed setting.
The pair test the score on a cancer-spotting scene, where missing a case can kill and checks are harsh. There, the score crowned a test that missed more cases, while a sound worth-based measure crowned the test that found most. No preset tweak of the score fixed the ranking across scenes, they show. The score also lacks a plain unit. They urge the worth-based route that health guidance backs.
Catalog record
| CREATOR | Melissa Assel, Andrew Vickers |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 30 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |