Charbel, Fady T.

BACKGROUND AND OBJECTIVES: Unruptured intracranial aneurysms (UIAs) are increasingly detected and require careful management to prevent rupture. No externally validated score currently predicts procedural risk to guide treatment decisions. We developed and validated 2 predictive scores for complications after endovascular treatment (EVT) or neurosurgical treatment (NT) of UIA using routinely collected clinical and aneurysmal features. METHODS: We conducted a multicenter retrospective study including patients with UIA treated with EVT or NT across 15 neurovascular centers (2014-2024). Predictive models were built using multivariable logistic regression, with variables derived from Delphi consensus. The primary outcome was a composite safety end point: new neurological deficits, modified Rankin Scale (mRS) worsening (≥1 point or mRS 2-5 within 30 days), or procedural death. Internal validation used bootstrapping, and external validation was performed temporally and institutionally. Model performance was assessed using area under the receiver operating characteristic curve (AUROC) and calibration. Final scores, named Morbidity and Mortality Associated Risk in the Treatment of UIAs (MARTA)-EVT and MARTA-NT, were compared with existing models identified through systematic review. RESULTS: Among 2647 patients (1907 EVT and 740 NT), procedural complications occurred in 6.3% (EVT) and 12.8% (NT). Independent predictors included age, baseline mRS, aneurysm location, size, morphology, and procedural factors. MARTA-EVT (AUROC = 0.68, 95% CI = 0.57-0.78) and MARTA-NT (AUROC = 0.65, 95% CI = 0.54-0.77) showed moderate discrimination and good calibration. MARTA-EVT outperformed existing models; MARTA-NT performed similarly to SAFETEA. Predictive models are available open-source: https://martascoreapp.shinyapps.io/martascoreapp/. CONCLUSION: MARTA-EVT and MARTA-NT are validated tools for predicting procedural risks in UIA treatment and may support patient counseling and clinical decision making.

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.

Brain arteriovenous malformations (bAVMs) are complex, and rare arteriovenous shunts that present with a wide range of signs and symptoms, with intracerebral hemorrhage being the most severe. Despite prior societal position statements, there is no consensus on the management of these lesions. ARISE (Aneurysm/bAVM/cSDH Roundtable Discussion With Industry and Stroke Experts) was convened to discuss evidence-based approaches and enhance our understanding of these complex lesions. ARISE identified the need to develop scales to predict the risk of rupture of bAVMs, and the use of common data elements to perform prospective registries and clinical studies. Additionally, the group underscored the need for comprehensive patient management with specialized centers with expertise in cranial and spinal microsurgery, neurological endovascular surgery, and stereotactic radiosurgery. The collection of prospective multicenter data and gross specimens was deemed essential for improving bAVM characterization, genetic evaluation, and phenotyping. Finally, bAVMs should be managed within a multidisciplinary framework, with clinical studies and research conducted collaboratively across multiple centers, harnessing the collective expertise and centralization of resources.

Background: Cranial dural arteriovenous fistulas with cortical venous drainage are rare lesions that can present with hemorrhage. A high rate of rebleeding in the early period following hemorrhage has been reported, but published long-term rates are much lower. No study has examined how risk of rebleeding changes over time. Our objective was to quantify the relative incidence of rebleeding in the early and later periods following hemorrhage. Methods: Patients with dural arteriovenous fistula and cortical venous drainage presenting with hemorrhage were identified from the multinational CONDOR (Consortium for Dural Fistula Outcomes Research) database. Natural history follow-up was defined as time from hemorrhage to first treatment, rebleed, or last follow-up. Rebleeding in the first 2 weeks and first year were compared using incidence rate ratio and difference. Results: Of 1077 patients, 250 met the inclusion criteria and had 95 cumulative person-years natural history follow-up. The overall annualized rebleed rate was 7.3% (95% CI, 3.2–14.5). The incidence rate of rebleeding in the first 2 weeks was 0.0011 per person-day; an early rebleed risk of 1.6% in the first 14 days (95% CI, 0.3–5.1). For the remainder of the first year, the incidence rate was 0.00015 per person-day; a rebleed rate of 5.3% (CI, 1.7–12.4) over 1 year. The incidence rate ratio was 7.3 (95% CI, 1.4–37.7; P , 0.026). Conclusions: The risk of rebleeding of a dural arteriovenous fistula with cortical venous drainage presenting with hemorrhage is increased in the first 2 weeks justifying early treatment. However, the magnitude of this increase may be considerably lower than previously thought. Treatment within 5 days was associated with a low rate of rebleeding and appears an appropriate timeframe.

OBJECTIVE There is a reported elevated risk of cerebral aneurysms in patients with intracranial dural arteriovenous fistulas (dAVFs). However, the natural history, rate of spontaneous regression, and ideal treatment regimen are not well characterized. In this study, the authors aimed to describe the characteristics of patients with dAVFs and intracranial aneurysms and propose a classification system. METHODS The Consortium for Dural Arteriovenous Fistula Outcomes Research (CONDOR) database from 12 centers was retrospectively reviewed. Analysis was performed to compare dAVF patients with (dAVF+ cohort) and without (dAVF-only cohort) concomitant aneurysm. Aneurysms were categorized based on location as a dAVF flow-related aneurysm (FRA) or a dAVF non–flow-related aneurysm (NFRA), with further classification as extra- or intradural. Patients with traumatic pseudoaneurysms or aneurysms with associated arteriovenous malformations were excluded from the analysis. Patient demographics, dAVF anatomical information, aneurysm information, and follow-up data were collected. RESULTS Of the 1077 patients, 1043 were eligible for inclusion, comprising 978 (93.8%) and 65 (6.2%) in the dAVF-only and dAVF+ cohorts, respectively. There were 96 aneurysms in the dAVF+ cohort; 10 patients (1%) harbored 12 FRAs, and 55 patients (5.3%) harbored 84 NFRAs. Dural AVF+ patients had higher rates of smoking (59.3% vs 35.2%, p < 0.001) and illicit drug use (5.8% vs 1.5%, p = 0.02). Sixteen dAVF+ patients (24.6%) presented with aneurysm rupture, which represented 16.7% of the total aneurysms. One patient (1.5%) had aneurysm rupture during follow-up. Patients with dAVF+ were more likely to have a dAVF located in nonconventional locations, less likely to have arterial supply to the dAVF from external carotid artery branches, and more likely to have supply from pial branches. Rates of cortical venous drainage and Borden type distributions were comparable between cohorts. A minority (12.5%) of aneurysms were FRAs. The majority of the aneurysms underwent treatment via either endovascular (36.5%) or microsurgical (15.6%) technique. A small proportion of aneurysms managed conservatively either with or without dAVF treatment spontaneously regressed (6.2%). CONCLUSIONS Patients with dAVF have a similar risk of harboring a concomitant intracranial aneurysm unrelated to the dAVF (5.3%) compared with the general population (approximately 2%–5%) and a rare risk (0.9%) of harboring an FRA. Only 50% of FRAs are intradural. Dural AVF+ patients have differences in dAVF angioarchitecture. A subset of dAVF+ patients harbor FRAs that may regress after dAVF treatment.

Abstract BACKGROUND Low-grade intracranial dural arteriovenous fistulas (dAVF) have a benign natural history in the majority of cases. The benefit from treatment of these lesions is controversial. OBJECTIVE To compare the outcomes of observation versus intervention for low-grade dAVFs. METHODS We retrospectively reviewed dAVF patients from institutions participating in the CONsortium for Dural arteriovenous fistula Outcomes Research (CONDOR). Patients with low-grade (Borden type I) dAVFs were included and categorized into intervention or observation cohorts. The intervention and observation cohorts were matched in a 1:1 ratio using propensity scores. Primary outcome was modified Rankin Scale (mRS) at final follow-up. Secondary outcomes were excellent (mRS 0-1) and good (mRS 0-2) outcomes, symptomatic improvement, mortality, and obliteration at final follow-up. RESULTS The intervention and observation cohorts comprised 230 and 125 patients, respectively. We found no differences in primary or secondary outcomes between the 2 unmatched cohorts at last follow-up (mean duration 36 mo), except obliteration rate was higher in the intervention cohort (78.5% vs 24.1%, P < .001). The matched intervention and observation cohorts each comprised 78 patients. We also found no differences in primary or secondary outcomes between the matched cohorts except obliteration was also more likely in the matched intervention cohort ( P < .001). Procedural complication rates in the unmatched and matched intervention cohorts were 15.4% and 19.2%, respectively. CONCLUSION Intervention for low-grade intracranial dAVFs achieves superior obliteration rates compared to conservative management, but it fails to improve neurological or functional outcomes. Our findings do not support the routine treatment of low-grade dAVFs.