Machine Learning Algorithms to Predict Delayed Cerebral Ischemia After Subarachnoid Hemorrhage: A Systematic Review and Meta-analysis

• Published in: Neurocritical care 2024-06, Vol.40 (3), p.1171-1181
• Main Authors: Santana, Laís Silva, Diniz, Jordana Borges Camargo, Rabelo, Nicollas Nunes, Teixeira, Manoel Jacobsen, Figueiredo, Eberval Gadelha, Telles, João Paulo Mota
• Format: Article
• Language: English
• Subjects: Accuracy; Algorithms; Aneurysms; Bias; Brain Ischemia - etiology; Collaboration; Coma; CRD; CRD42023441586; Critical Care Medicine; Diabetes; Hemorrhage; Humans; Hypertension; Intensive; Internal Medicine; Ischemia; Machine Learning; Medicine; Medicine & Public Health; Meta-analysis; Neural networks; Neurology; Neurosurgery; Patients; Regression analysis; Review Article; Sensitivity and Specificity; Subarachnoid Hemorrhage - complications; Support vector machines; Systematic review
• ISSN: 1541-6933; 1556-0961; 1556-0961
• DOI: 10.1007/s12028-023-01832-z

Delayed cerebral ischemia (DCI) is a common and severe complication after subarachnoid hemorrhage (SAH). Logistic regression (LR) is the primary method to predict DCI, but it has low accuracy. This study assessed whether other machine learning (ML) models can predict DCI after SAH more accurately than conventional LR. PubMed, Embase, and Web of Science were systematically searched for studies directly comparing LR and other ML algorithms to forecast DCI in patients with SAH. Our main outcome was the accuracy measurement, represented by sensitivity, specificity, and area under the receiver operating characteristic. In the six studies included, comprising 1828 patients, about 28% (519) developed DCI. For LR models, the pooled sensitivity was 0.71 (95% confidence interval [CI] 0.57–0.84; p