Retrospective comparison of three commercial artificial intelligence algorithms for detection of intracranial hemorrhage (ICH) in the emergency radiology department
Acta Radiologica · 2026
DOI: 10.1177/02841851261484026 ↗Kurz gefasst
Vergleichsstudie in der Zeitschrift Acta Radiologica, 2026. Verfasst von Kristoffer Järlevi und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Diagnostic Radiology, Södersjukhuset, Stockholm, Sweden. Hauptthemen laut MEDLINE: Artificial Intelligence, Intracranial Hemorrhages, Algorithms, Tomography, X-Ray Computed. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background
Several commercial artificial intelligence (Al) algorithms are available for detecting intracranial hemorrhage (ICH), but independent clinical validation remains limited.
Purpose
To compare three commercially available Al algorithms for ICH detection on non- contrast head computed tomography (NCHCT). Material and Methods In 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 disclosing participation. Reports from two radiologists and all Al outputs were evaluated. Human-AI performance was assessed using an idealized logical OR model, assuming radiologists perfectly dismissed all false-positive Al flags to calculate system specificity. All positive or discrepant cases underwent expert manual review using two-tier consensus adjudication as the reference standard.
Results
Of 3902 evaluable examinations, 3517 were consistently negative by all readers. The remaining 385 cases underwent manual review, confirming ICH in 176 cases (4.5% prevalence) and excluding it in 209. Eight ICH cases missed by both radiologists were detected by at least one Al system. Aidoc performed best, with 90.3% sensitivity and 99.0% specificity. A simulated mathematical combination of Aidoc with a human reader increased sensitivity to 96.0% while maintaining 99.4% specificity ( P < 0.001), comparable to two radiologists.
Conclusion
Al performance varied substantially, with only one system demonstrating clinically relevant accuracy. Combining Al with human interpretation improved ICH detection and shows promise for future clinical implementation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Diagnostic Radiology, Södersjukhuset, Stockholm, Sweden.
- Department of Clinical Science, Intervention and Technology, Karolinska Institutet, Stockholm, Sweden.
- Department of Molecular Medicine and Surgery, Karolinska Institutet, Stockholm, Sweden.
ORCID-Profile: Gustav Alvfeldt, Chikako Suzuki, Michael L Wilczek
Zitieren
APA
Järlevi, K., Lindbom, D., Lindholm, A., Alvfeldt, G., Suzuki, C., & Wilczek, M. L. (2026). Retrospective comparison of three commercial artificial intelligence algorithms for detection of intracranial hemorrhage (ICH) in the emergency radiology department. Acta Radiologica. https://doi.org/10.1177/02841851261484026
Vancouver
Järlevi K, Lindbom D, Lindholm A, Alvfeldt G, Suzuki C, Wilczek ML. Retrospective comparison of three commercial artificial intelligence algorithms for detection of intracranial hemorrhage (ICH) in the emergency radiology department. Acta Radiologica. 2026. doi:10.1177/02841851261484026
BibTeX
@article{Jrlevi2026,
author = {Järlevi, Kristoffer and Lindbom, Daniel and Lindholm, Andreas and Alvfeldt, Gustav and Suzuki, Chikako and Wilczek, Michael L},
title = {Retrospective comparison of three commercial artificial intelligence algorithms for detection of intracranial hemorrhage (ICH) in the emergency radiology department},
journal = {Acta Radiologica},
year = {2026},
doi = {10.1177/02841851261484026}
}
EUVIMED