Bathini, Abhijith

BACKGROUND AND OBJECTIVES: The artery of Davidoff and Schechter (ADS) is a dural branch of the posterior cerebral artery, supplying the falcotentorial junction. It is not commonly depicted on angiography due to its small size; thus, its visibility is usually indicative of a pathology, such as a dural arteriovenous fistula (DAVF). Recognizing the ADS as a feeder could be vital in enhancing management success, and understanding its anatomy is important for preventing complications during embolization or microsurgery. We present a scoping review of DAVFs fed by the ADS followed by an illustrative case report encountered at our institution. METHODS: An extensive literature review was conducted using PubMed, Embase, Web of Science, Scopus, and Cochrane databases. The search included the keywords: “Davidoff,” “Schechter,” “Davidoff and Schechter,” “dural branch,” “tentorial branch,” “medial branch,” and “meningeal branch,” in combination with “arteriovenous fistula,” “posterior cerebral artery,” and “superior cerebellar artery.” Only articles published in English or Spanish were included, with no restriction on publication date. Case reports and series were further screened based on best relevance. Data extraction and synthesis were performed in accordance with Preferred Reporting Items for Systematic reviews and Meta-Analyses guidelines. RESULTS: A total of 16 articles describing 32 cases of DAVFs supplied by the ADS were identified. The most common onset was headache (43.8%), followed by altered mental status (21.2%). Most DAVFs were classified as high grade based on Borden/Cognard scales. Transarterial embolization was the most used treatment (81.3%), achieving complete occlusion in 76.9% of cases. Among patients with complete occlusion, approximately half experienced full resolution of symptoms. In a mean follow-up of 27.4 months (IQR: 30), 2 cases reported complications due to reflux of the embolic agent. CONCLUSION: A comprehensive understanding of the ADS's angioarchitecture is essential to take full advantage of this artery's features in the treatment, mitigating potential complications and optimizing patient outcomes.

BACKGROUND AND OBJECTIVES: Aneurysm risk prediction remains an imprecise science that places patients at risk for either over or undertreatment. Machine learning (ML) models may improve clinical practice by adding precision to risk assessment. This study aims to comprehensively assess the current landscape of ML applications in predicting the risk of aneurysm rupture and compare the performance with the widely used PHASES score. METHODS: A systematic review of PubMed, Scopus, and Web of Science was conducted. All studies using ML tools to predict the rupture risk of intracranial aneurysms were included. Meta-analysis was conducted with consideration to the ML algorithms and compared with the PHASES score. RESULTS: Thirty-six studies involving 22 462 patients were included in the final analysis. ML techniques, including 124 models using 25 algorithms, were employed. Among various ML models, while they had comparable diagnostic performance, deep learning exhibited a slightly better performance profile (sensitivity = 0.792, specificity = 0.788, and accuracy = 0.778 in external validation). Based on our analysis, ML, regardless of the algorithm, provides comparable sensitivity (0.743 vs 0.771, P = .60) and higher specificity (0.763 vs 0.507, P < .01) compared with the PHASES score. Consistently, pooling the area under the receiver operating characteristic curve (AUC) for 60 ML models and 5 PHASES score data, ML models exhibited higher AUC (0.84 vs 0.64, P < .01). Using hemodynamic parameters as input for models improved specificity ( P < .01) in the test sets without any significant changes in the sensitivity. The later improvement was not observed in the external validation sets. CONCLUSION: ML techniques have the potential to enhance the prediction of intracranial aneurysm rupture compared with traditional approaches, like the PHASES score. Incorporating hemodynamic parameters may further enhance the accuracy of ML models. Feature prospective studies are required to validate the utility of ML models for clinical integration.