The diagnostic performance of artificial intelligence algorithms for identifying M2 segment middle cerebral artery occlusions: A systematic review and meta-analysis.

Autor: Ghozy S; Department of Radiology, Mayo Clinic, Rochester, MN, USA; Nuffield Department of Primary Care Health Sciences and Department for Continuing Education (EBHC program), Oxford University, Oxford, UK. Electronic address: Ghozy.Sherief@mayo.edu., Azzam AY; Nested Knowledge, St. Paul MN, USA., Kallmes KM; Nested Knowledge, St. Paul MN, USA; Superior Medical Experts, St. Paul MN, USA., Matsoukas S; Department of Neurosurgery, Icahn School of Medicine at Mount Sinai, New York, New York, USA., Fifi JT; Department of Neurosurgery, Icahn School of Medicine at Mount Sinai, New York, New York, USA; Department of Diagnostic, Molecular and Interventional Radiology, Icahn School of Medicine at Mount Sinai, New York, New York, USA; Department of Neurology, Icahn School of Medicine at Mount Sinai, New York, New York, USA., Luijten SPR; Department of Radiology & Nuclear Medicine, Erasmus MC University Medical Center, Rotterdam, The Netherlands., van der Lugt A; Department of Radiology & Nuclear Medicine, Erasmus MC University Medical Center, Rotterdam, The Netherlands., Adusumilli G; Department of Surgery, Stanford University, Palo Alto, CA, USA., Heit JJ; Departments of Neuroradiology and Neurosurgery, Stanford University, Palo Alto, CA, USA., Kadirvel R; Department of Radiology, Mayo Clinic, Rochester, MN, USA; Department of Neurologic Surgery, Mayo Clinic, Rochester, MN, USA., Kallmes DF; Department of Radiology, Mayo Clinic, Rochester, MN, USA.
Jazyk: angličtina
Zdroj: Journal of neuroradiology = Journal de neuroradiologie [J Neuroradiol] 2023 Jun; Vol. 50 (4), pp. 449-454. Date of Electronic Publication: 2023 Feb 10.
DOI: 10.1016/j.neurad.2023.02.001
Abstrakt: Background: Artificial intelligence (AI)-based algorithms have been developed to facilitate rapid and accurate computed tomography angiography (CTA) assessment in proximal large vessel occlusion (LVO) acute ischemic stroke, including internal carotid artery and M1 occlusions. In clinical practice, however, the detection of medium vessel occlusion (MeVO) represents an ongoing diagnostic challenge in which the added value of AI remains unclear.
Purpose: To assess the diagnostic performance of AI platforms for detecting M2 occlusions.
Methods: Studies that report the diagnostic performance of AI-based detection of M2 occlusions were screened, and sensitivity and specificity data were extracted using the semi-automated AutoLit software (Nested Knowledge, MN) platform. STATA (version 16 IC; Stata Corporation, College Station, Texas, USA) was used to conduct all analyses.
Results: Eight studies with a low risk of bias and significant heterogeneity were included in the quantitative and qualitative synthesis. The pooled estimates of sensitivity and specificity of AI platforms for M2 occlusion detection were 64% (95% CI, 53 to 74%) and 97% (95% CI, 84 to 100%), respectively. The area under the curve (AUC) in the SROC curve was 0.79 (95% CI, 0.74 to 0.83).
Conclusion: The current performance of the AI-based algorithm makes it more suitable as an adjunctive confirmatory tool rather than as an independent one for M2 occlusions. With the rapid development of such algorithms, it is anticipated that newer generations will likely perform much better.
Competing Interests: Declaration of Competing Interest KMK works for and holds equity in Nested Knowledge, Inc., works for Conway Medical LLC, and holds equity in Superior Medical Experts, Inc. JJH is a consultant for Medtronic and MicroVention and a member of the Medical and Scientific Advisory Board for iSchemaView. DFK holds equity in Nested Knowledge, Superior Medical Editors, and Conway Medical, Marblehead Medical; a consultant for MicroVention, Medtronic, Balt, and Insera Therapeutics; Data Safety Monitoring Board for Vesalio; and receiving royalties from Medtronic. AvdL received research support from Stryker, Medtronic, Penumbra and Cerenovus.
(Copyright © 2023 Elsevier Masson SAS. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: