ABSTRACT NUMBER: ESOC2026A1793 WHEN EXPERTISE MEETS ALGORITHMS: EVALUATING MODEL-ASSISTED PROGNOSTICATION IN ACUTE ISCHEMIC STROKE
Nicole Maria Radley, Nelly Blindenbacher, Christoph Globas, Philipp Baumgartner, Corinne Inauen, Beate Sick, Charles Majoie, Wim Van Zwam, Susanne Wegener · 2026
Read ABSTRACT NUMBER: ESOC2026A1793 WHEN EXPERTISE MEETS ALGORITHMS: EVALUATING MODEL-ASSISTED PROGNOSTICATION IN ACUTE ISCHEMIC STROKE by Nicole Maria Radley, Nelly Blindenbacher, Christoph Globas, Philipp Baumgartner, Corinne Inauen, Beate Sick, Charles Majoie, Wim Van Zwam, Susanne Wegener (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-13146251.txt.
Description
Predicting how a stroke patient will fare shapes hard treatment choices. Nicole Maria Radley and co-authors test whether a respected prediction tool truly helps doctors. Six neurologists forecast early and three-month outcomes for forty patients with blocked brain arteries. They worked first on their own, then with the MR PREDICTS model at hand. A deep learning system read the same cases.
The tool improved forecasts modestly. But doctors often misjudged the scan details the model needs, such as where the blockage sat. That blunted its benefit. The model alone and the learning system performed on par with the assisted doctors. The lesson is double-edged. Prediction tools help, yet their value depends on fallible human inputs. Systems that read scans directly may matter more.
Catalog record
| CREATOR | Nicole Maria Radley, Nelly Blindenbacher, Christoph Globas, Philipp Baumgartner, Corinne Inauen, Beate Sick, Charles Majoie, Wim Van Zwam, Susanne Wegener |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 2 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |