Systematic Review and Meta-Analysis of Prehospital Machine Learning Scores as Screening Tools for Early Detection of Large Vessel Occlusion in Patients With Suspected Stroke

• Published in: Journal of the American Heart Association Vol. 13; no. 12; p. e033298
• Main Authors: Alobaida, Muath, Joddrell, Martha, Zheng, Yalin, Lip, Gregory Y H, Rowe, Fiona J, El-Bouri, Wahbi K, Hill, Andrew, Lane, Deirdre A, Harrison, Stephanie L
• Format: Journal Article
• Language: English
• Published: Hoboken John Wiley and Sons Inc 18.06.2024; Wiley
• Subjects: artificial intelligence; endovascular thrombectomy; large vessel occlusion; machine learning; Original Research; prehospital; stroke
• ISSN: 2047-9980; 2047-9980
• DOI: 10.1161/JAHA.123.033298

Enhanced detection of large vessel occlusion (LVO) through machine learning (ML) for acute ischemic stroke appears promising. This systematic review explored the capabilities of ML models compared with prehospital stroke scales for LVO prediction.BACKGROUNDEnhanced detection of large vessel occlusion (LVO) through machine learning (ML) for acute ischemic stroke appears promising. This systematic review explored the capabilities of ML models compared with prehospital stroke scales for LVO prediction.Six bibliographic databases were searched from inception until October 10, 2023. Meta-analyses pooled the model performance using area under the curve (AUC), sensitivity, specificity, and summary receiver operating characteristic curve. Of 1544 studies screened, 8 retrospective studies were eligible, including 32 prehospital stroke scales and 21 ML models. Of the 9 prehospital scales meta-analyzed, the Rapid Arterial Occlusion Evaluation had the highest pooled AUC (0.82 [95% CI, 0.79-0.84]). Support Vector Machine achieved the highest AUC of 9 ML models included (pooled AUC, 0.89 [95% CI, 0.88-0.89]). Six prehospital stroke scales and 10 ML models were eligible for summary receiver operating characteristic analysis. Pooled sensitivity and specificity for any prehospital stroke scale were 0.72 (95% CI, 0.68-0.75) and 0.77 (95% CI, 0.72-0.81), respectively; summary receiver operating characteristic curve AUC was 0.80 (95% CI, 0.76-0.83). Pooled sensitivity for any ML model for LVO was 0.73 (95% CI, 0.64-0.79), specificity was 0.85 (95% CI, 0.80-0.89), and summary receiver operating characteristic curve AUC was 0.87 (95% CI, 0.83-0.89).METHODS AND RESULTSSix bibliographic databases were searched from inception until October 10, 2023. Meta-analyses pooled the model performance using area under the curve (AUC), sensitivity, specificity, and summary receiver operating characteristic curve. Of 1544 studies screened, 8 retrospective studies were eligible, including 32 prehospital stroke scales and 21 ML models. Of the 9 prehospital scales meta-analyzed, the Rapid Arterial Occlusion Evaluation had the highest pooled AUC (0.82 [95% CI, 0.79-0.84]). Support Vector Machine achieved the highest AUC of 9 ML models included (pooled AUC, 0.89 [95% CI, 0.88-0.89]). Six prehospital stroke scales and 10 ML models were eligible for summary receiver operating characteristic analysis. Pooled sensitivity and specificity for any prehospital stroke scale were 0.72 (95% CI, 0.68-0.75) and 0.77 (95% CI, 0.72-0.81), respectively; summary receiver operating characteristic curve AUC was 0.80 (95% CI, 0.76-0.83). Pooled sensitivity for any ML model for LVO was 0.73 (95% CI, 0.64-0.79), specificity was 0.85 (95% CI, 0.80-0.89), and summary receiver operating characteristic curve AUC was 0.87 (95% CI, 0.83-0.89).Both prehospital stroke scales and ML models demonstrated varying accuracies in predicting LVO. Despite ML potential for improved LVO detection in the prehospital setting, application remains limited by the absence of prospective external validation, limited sample sizes, and lack of real-world performance data in a prehospital setting.CONCLUSIONSBoth prehospital stroke scales and ML models demonstrated varying accuracies in predicting LVO. Despite ML potential for improved LVO detection in the prehospital setting, application remains limited by the absence of prospective external validation, limited sample sizes, and lack of real-world performance data in a prehospital setting.