Performance of AI vs radiology residents in the detection of intracranial hemorrhage on emergency CT : a real-world analysis

Article Article scientifique Article Performance of AI vs radiology residents in the detection of intracranial hemorrhage on emergency CT : a real-world analysis eng 2026-02-21 2026-07 author Pedrini Quentin Division of Radiology, Diagnostic Department, Geneva University Hospitals, Geneva, Switzerland. 656157 author Chrysostomou Periktioni Crina Division of Radiology, Diagnostic Department, Geneva University Hospitals, Geneva, Switzerland. author Poletti Pierre-Alexandre Alois Division of Radiology, Diagnostic Department, Geneva University Hospitals, Geneva, Switzerland. 34563 Département de radiologie et informatique médicale (RADIO) author Becker Minerva Division of Radiology, Diagnostic Department, Geneva University Hospitals, Geneva, Switzerland. 134255 Département de radiologie et informatique médicale (RADIO) author Perneger Thomas Faculty of Medicine, University of Geneva, Geneva, Switzerland. 28462 Décanat et administration de la faculté de médecine (ADMED) author Meyer Rodolphe Department of Information Systems, Geneva University Hospitals, Geneva, Switzerland. 683534 author Platon Alexandra 0000-0003-1754-8702 Division of Radiology, Diagnostic Department, Geneva University Hospitals, Geneva, Switzerland. alexandra.platon@hug.ch. 554893 Département de radiologie et informatique médicale (RADIO) 5996-6006 10.1007/s00330-026-12385-y 41721849 0938-7994 https://link.springer.com/10.1007/s00330-026-12385-y Objective: To evaluate the performance of a commercial artificial intelligence (AI) software in detecting intracranial hemorrhage (ICH) in emergency settings, compared to on-call radiology residents. Materials and methods: All consecutive unenhanced cerebral CT-scans performed in a single center over a 3-month period in the emergency department in patients with suspected ICH, initially interpreted by radiology residents on-call and subsequently verified and approved by a board-certified radiologist, were concomitantly analyzed by an AI software for the presence of ICH. Results from the AI software were stored in a separate PACS partition and were unavailable to the radiologists for the case reading. We assessed the diagnostic performance of the AI software and of the radiology residents in detecting ICH. The reference standard was the final report of the board-certified radiologist. Results: Radiology reports of 2153 CT-scans were analyzed, and ICH prevalence was 15.4% (331/2153). The AI software achieved an overall sensitivity of 84% and a specificity of 94.4%, and radiology residents achieved a sensitivity of 96.4% and a specificity of 99.6%, respectively (p-values < 0.001). The sensitivity was 97.7% for AI and 98.5% for residents when CT examinations displayed an association of multiple hemorrhagic types (p = 1). The sensitivity was 95.2% for AI and 98.4% for radiology residents in the presence of multiple ICH sites (p = 0.11). Conclusion: Radiology residents demonstrated a significantly higher performance in detecting ICH compared to the AI software. AI exhibited very good diagnostic performance only in the presence of multiple hemorrhagic sites or multiple hemorrhage types. Key points: QuestionHow does the performance of the AI software compare to that of radiology residents in detecting ICH on unenhanced CT in real-life emergency workflow conditions? FindingsIn the emergency setting, the AI software demonstrated lower overall sensitivity and specificity than radiology residents for detecting ICH. Clinical relevanceIn real-life emergency conditions at a university hospital, the AI software did not offer a superior performance compared to radiology residents in detecting ICH. The integration of AI in this specific setting remains to be defined. Artificial intelligence Emergencies Intracranial hemorrhages Tomography (X-ray computed) Dewey 616.0757 62 Département de radiologie et informatique médicale 227 false 88 Epidémiologie clinique et biostatistique 115 411 Groupe Becker Minerva (imagerie ORL) 683 469 Radiologie des urgences 800 European radiology 36 7 636eb9a4-f8a5-45fd-ad4b-3ee62857f537 Article (Published version) Restricted Article_scientifique_from_crossref.pdf 5891560 application/pdf eda2897e18cf3a2fa991d3dc0c5c338ab6b4743f0108426e326c40754314c3d1 Vignette Public Sans titre.jpg 302745 image/png restrictedAccess Faculté de médecine / Section de médecine clinique / Département de radiologie et informatique médicale

Title	Published in	Access level	OA Policy	Year	Views	Downloads

Performance of AI vs radiology residents in the detection of intracranial hemorrhage on emergency CT : a real-world analysis	European radiology			2026	10	1

Archive ouverte UNIGE

Pedrini, Quentin