aceRetrospective comparison of three commercial artificial intelligence algorithms for detection of intracranial hemorrhage (ICH) in the emergency radiology department
BackgroundSeveral commercial artificial intelligence (Al) algorithms are available for detecting intracranial hemorrhage (ICH), but independent clinical validation remains limited.PurposeTo compare three commercially available Al algorithms for ICH detection on non- contrast head computed tomography (NCHCT).Material and MethodsIn this retrospective study, 4027 consecutive NCHCT examinations from a large emergency hospital in southwest Sweden were analyzed. Three Al algorithms were applied, with one vendor disclo…
Combining Aidoc AI with a human radiologist increased sensitivity for intracranial hemorrhage on non-contrast head CT to 96.0% while maintaining 99.4% specificity, detecting cases missed by radiologists alone.
Performance across three commercial ICH detection algorithms varied substantially, with only one system showing clinically relevant accuracy, indicating limited independent validation for routine emergency use.
Human-AI performance was estimated using an idealized model that assumes perfect dismissal of false positives, and the data come from a single-center retrospective cohort, limiting generalizability to prospective clinical implementation.
Evidence
- Peer-reviewedActa Radiologica2026-09-15
How should this claim be treated?
Truvace Impact Record TRV-2026-1107, v1: “Retrospective comparison of three commercial artificial intelligence algorithms for detection of intracranial hemorrhage (ICH) in the emergency radiology department.” Truvace, 2026-09-16. /record/TRV-2026-1107 (accessed at citation time). sha256 2a159c625dbcd4e0…
Calibration history
Every change to this record since certification, in the open. None yet — the reading has held since it entered the record.
Certified into the record
How to verify without trusting this page
Fetch the canonical text of any version from /api/record/TRV-2026-1107 and hash it yourself — for example shasum -a 256 on the saved canonical field. The result must equal content_hash, and each version’s text ends with prev:followed by the prior version’s hash (version 1 chains to 64 zeros). If a single character of any version had been altered since certification, the chain would not reproduce.