Retrospective comparison of three commercial artificial intelligence algorithms for detection of intracranial hemorrhage (ICH) in the emergency radiology department
Kristoffer Järlevi, Daniel Lindbom, Andreas Lindholm, Gustav Alvfeldt, Chikako Suzuki, Michael L Wilczek · 2026
Read Retrospective comparison of three commercial artificial intelligence algorithms for detection of intracranial hemorrhage (ICH) in the emergency radiology department by Kristoffer Järlevi, Daniel Lindbom, Andreas Lindholm, Gustav Alvfeldt, Chikako Suzuki, Michael L Wilczek (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-13680731.txt.
Description
Bleeding inside the skull is an emergency, and AI tools now offer to flag it on head scans. Kristoffer Järlevi and co-authors compared three commercial tools in this 2026 study. Sellers market such tools for emergency radiology, yet outside checks of their real performance are rare. The team used scans from a large emergency hospital in southwest Sweden.
Just over four thousand head CT scans were run through all three tools. Two radiologists' reports served as the human side of the comparison. Cases where the tools and humans disagreed went to expert review for a final call. One maker agreed to be named, while the others stayed blinded. The authors also modeled a best case where radiologists perfectly clear every false alarm. Head-to-head trials help hospitals buy with open eyes.
Catalog record
| CREATOR | Kristoffer Järlevi, Daniel Lindbom, Andreas Lindholm, Gustav Alvfeldt, Chikako Suzuki, Michael L Wilczek |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 36 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |