The diagnostic performance of artificial intelligence algorithms for identifying M2 segment middle cerebral artery occlusions: A systematic review and meta-analysis - 23/05/23
, Ahmed Y. Azzam c, Kevin M. Kallmes c, d, Stavros Matsoukas e, Johanna T Fifi e, f, g, Sven P R Luijten h, Aad van der Lugt h, Gautam Adusumilli i, Jeremy J Heit j, Ramanathan Kadirvel a, k, David F Kallmes aAbstract |
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.
Le texte complet de cet article est disponible en PDF.Keywords : Middle cerebral artery, Artificial intelligence, Deep learning, Diagnostic performance
Plan
Vol 50 - N° 4
P. 449-454 - juin 2023 Retour au numéro
Article précédent
- Dual-layer carotid stenting for symptomatic carotid web: Results from the Caroweb study
- Gaultier Marnat, Quentin Holay, Jean Darcourt, Jean-Philippe Desilles, Michael Obadia, Alain Viguier, Jildaz Caroff, Christian Denier, Lisa Papillon, Xavier Barreau, Christophe Cognard, Jerome Berge, Quentin Bourgeois-Beauvais, Anne Landais, Marion Boulanger, Francisco Macian, Benoit Guillon, Fernando Pico, Mathias Lamy, Emmanuelle Robinet-Borgomano, Sébastien Richard, Benjamin Gory, Igor Sibon, Nicolas Gaillard, Nicolas Chausson, Stephane Olindo, CAROWEB investigators (see appendix)
- The relationship between occlusion patterns and outcomes after thrombectomy in patients with acute internal carotid artery occlusion
- Xin Xu, Chuyuan Ni, Kangfei Wu, Mingming Zha, Yi Sun, Hao Wang, Junfeng Xu, Ke Yang, Yapeng Guo, Xianjun Huang, Zhiming Zhou
Bienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.
Déjà abonné à cette revue ?