Search

Subtotal coil embolization followed by subsequent flow diversion is often pursued for treatment of acutely ruptured aneurysms. Owing to the need for anti-platelet therapy, the optimal time of safely pursuing flow diversion treatment has not been fully elucidated. In this study, we aim to demonstrate the safety and feasibility of staged treatment of acutely ruptured aneurysms with early coil embolization followed by flow diversion prior to discharge.A retrospective study to evaluate clinical outcomes of patients who presented with aneurysmal subarachnoid hemorrhage and underwent coil embolization followed by subacute flow diversion treatment during the same hospitalization.A total of 18 patients are included in our case series. Eight patients presented with Hunt-Hess (H-H) grade 2 bleed, 6 patients with H-H grade 3, and 2 patients each with H-H grade 4 and H-H grade 1. Eight patients required placement of an external ventricular drain on admission. After initial coil embolization, 12 achieved Raymond-Roy grade 2 occlusion, and 6 attained grade 3a/b occlusion. The mean duration between coil embolization and subsequent flow diversion was 9.83 days (range: 1-30). There were no instances of re-hemorrhage between initial coil embolization and subsequent flow diversion treatment. Sixteen patients had a minimum of 6-month follow-up, of which 15 were found to have complete occlusion, and 1 required subsequent clipping.Subtotal coil embolization followed by definitive treatment using flow diversion during the same hospitalization is feasible and achieves excellent aneurysm occlusion rates while avoiding dual anti-platelet therapy during the initial hemorrhage period.

The outcomes of A Randomized Trial of Unruptured Brain Arteriovenous Malformations (ARUBA) were controversial, and they suggested that intervention is inferior to medical management for unruptured brain arteriovenous malformations (AVMs). However, several studies have shown that stereotactic radiosurgery (SRS) is an acceptable therapy for unruptured AVMs.To test the hypothesis that ARUBA intervention arm's SRS results are meaningfully inferior to those from similar populations reported by other studies.We performed a literature review to identify SRS studies of patients who met the eligibility criteria for ARUBA. Patient, AVM, treatment, and outcome data were extracted for statistical analysis. Regression analyses were pooled to identify factors associated with post-SRS obliteration and hemorrhage.The study cohort included 8 studies comprising 1620 ARUBA-eligible patients who underwent SRS. At the time of AVM diagnosis, 36% of patients were asymptomatic. The mean follow-up duration was 80 months. Rates of radiologic, symptomatic, and permanent radiation-induced changes were 45%, 11%, and 2%, respectively. The obliteration rate was 68% at last follow-up. The post-SRS hemorrhage and mortality rates were 8%, and 2%, respectively. Lower Spetzler-Martin grade (odds ratios [OR] = 0.84 [0.74-0.95], P = .005), lower radiosurgery-based AVM score (OR = 0.75 [0.64-0.95], P = .011), lower Virginia Radiosurgery AVM Scale (OR = 0.86 [0.78-0.95], P = .003), and higher margin dose (OR = 1.13 [1.02-1.25], P = .025) were associated with obliteration.SRS carries a favorable risk to benefit profile for appropriately selected ARUBA-eligible patients, particularly those with smaller volume AVMs. Our findings suggest that the results of ARUBA do not reflect the real-world safety and efficacy of SRS for unruptured AVMs.

Traditional Gamma Knife radiosurgery (GKRS) of brain arteriovenous malformations (AVMs) using digital subtraction angiography (DSA) requires head immobilization using a stereotactic frame.We describe our protocol of frameless GKRS using DSA while maintaining high spatial resolution for precision.This study is a retrospective review of patients with unruptured AVMs who underwent frameless GKRS. Magnetic resonance imaging and 3-dimensional DSA were obtained without a stereotactic frame for all patients. The imaging studies were merged for contouring of the AVM nidus. During GKRS treatment, patients were immobilized using an individually molded thermoplastic mask.Thirty-one patients were included in the analysis. The median age is 45.0 years (interquartile range [IQR]: 28.0-55.0). The median nidus size is 3.0 cm (IQR: 2.0-3.4). One patient had a Spetzler-Martin grade I, 11 had a grade II, 11 had a grade III, 6 had a grade IV, and 2 had a grade V AVM. Eleven patients underwent preradiosurgical embolization, 3 patients had previous microsurgical resection and/or embolization, and 1 patient had prior radiosurgery. The median administered dose was 20 Gy (IQR: 18.0-21.0). All patients completed their treatment with the planned radiation dose without complications.This is the first study that integrates DSA in the treatment planning of brain AVMs using GKRS without utilizing a stereotactic head frame. Frameless GKRS provides numerous advantages over frame-based techniques including improved patient experience and the capability of fractionation and thus expanding the eligibility of more AVMs for radiosurgery, while maintaining high spatial resolution of the AVM using angiography data.

OBJECTIVE Wide-neck bifurcation cerebral aneurysms have historically required either clip ligation or stent- or balloon-assisted coil embolization. This predicament led to the development of the Woven EndoBridge (WEB) aneurysm embolization system, a self-expanding mesh device that achieves intrasaccular flow disruption and does not require antithrombotic medications. The authors report their operative experience and 6-month follow-up occlusion outcomes with the first 115 aneurysms they treated via WEB embolization. METHODS The authors reviewed the first 115 cerebral aneurysms they treated by WEB embolization after FDA approval of the WEB embolization device (from February 2019 to January 2021). Data were collected on patient demographics and clinical presentation, aneurysm characteristics, procedural details, postembolization angiographic contrast stasis, and functional outcomes. RESULTS A total of 110 patients and 115 aneurysms were included in our study (34 ruptured and 81 unruptured aneurysms). WEB embolization was successful in 106 (92.2%) aneurysms, with a complication occurring in 6 (5.5%) patients. Contrast clearance was seen in the arterial phase in 14 (12.2%) aneurysms, in the capillary phase in 16 (13.9%), in the venous phase in 63 (54.8%), and no contrast was seen in 13 (11.3%) of the aneurysms studied. Follow-up angiography was performed on 60 (52.6%) of the aneurysms, with complete occlusion in 38 (63.3%), neck remnant in 14 (23.3%), and aneurysmal remnant in 8 (13.3%). Six (5.5%) patients required re-treatment for persistent aneurysmal residual on follow-up angiography. CONCLUSIONS The WEB device has been successfully used for the treatment of both unruptured and ruptured wide-neck bifurcation aneurysms by achieving intrasaccular flow diversion. Here, the authors have shared their experience with its unique technical considerations and device size selection, as well as critically reviewed complications and aneurysm occlusion rates.

We aim to determine the incidence of decompressive hemicraniectomy (DHC) in the modern era of mechanical thrombectomy techniques and improved revascularization outcomes.We performed a retrospective analysis of 512 patients admitted with acute ischemic strokes with anterior circulation large-vessel occlusion that were treated by mechanical thrombectomy from 2010-2019. The primary endpoint was the need for surgical decompression. Secondary endpoints were infarct size, hemorrhagic conversion, and functional outcome at hospital discharge.Of the 512 patients, 18 (3.5%) underwent DHC at a median 2.0 days from stroke onset. The DHC group was significantly younger than the non-DHC group (P0.001), had worse reperfusion rates (P = 0.024) and larger infarct size (P0.001). Hemorrhagic conversion was more frequent in the DHC group but did not reach statistical significance (P = 0.08). From 2010-2015, 196 patients underwent a mechanical thrombectomy, 13 of whom (6.6%) required a DHC, while 316 patients underwent mechanical thrombectomy from 2016-2019 and only 5 patients required a DHC (1.6%; P = 0.002). Younger age (P0.001), urinary tract infection (P0.001) and increasing infarct size were significantly associated with needing a DHC. When controlling for other risk factors, higher thrombolysis in cerebral infarction score significantly reduced the need for decompressive hemicraniectomy (P = 0.004).This is one of the largest single-center experiences demonstrating that improved recanalization decreased the need for DHC without increasing the risk of hemorrhagic conversion.

The Woven EndoBridge (WEB) device is becoming increasingly popular for treatment of wide-neck aneurysms. As experience with this device grows, it is important to identify factors associated with occlusion following WEB treatment to guide decision making and screen patients at high risk for recurrence. The aim of this study was to identify factors associated with adequate aneurysm occlusion following WEB device treatment in the neurosurgical literature and in our case series. A systematic review of the present literature was conducted to identify studies related to the prediction of WEB device occlusion. In addition, a retrospective review of our institutional data for patients treated with the WEB device was performed. Demographics, aneurysm characteristics, procedural variables, and 6-month follow-up angiographic outcomes were recorded. Seven articles totaling 450 patients with 456 aneurysms fit our criteria. Factors in the literature associated with inadequate occlusion included larger size, increased neck width, partial intrasaccular thrombosis, irregular shape, and tobacco use. Our retrospective review identified 43 patients with 45 aneurysms. A total of 91.1% of our patients achieved adequate occlusion at a mean follow-up time of 7.32 months. Increasing degree of contrast stasis after WEB placement on the post-deployment angiogram was significantly associated with adequate occlusion on follow-up angiogram (p = 0.005) and with Raymond-Roy classification (p = 0.048), but not with retreatment (p = 0.617). In our systematic review and case series totaling 450 patients with 456 aneurysms, contrast stasis on post-deployment angiogram was identified as a predictor of adequate aneurysm occlusion, while morphological characteristics such as larger size and wide neck negatively impact occlusion.

With the development of the Flow Re-Direction Endoluminal Device Junior (FRED Jr), treatment of distal aneurysms and/or aneurysms with small parent vessels has become a viable option.To assess the efficacy and safety of FRED Jr in the treatment of distal aneurysms with small parent vessels.This is a single center retrospective study and meta-analysis of patients treated with FRED Jr for intracranial aneurysms. The primary outcome was complete aneurysm occlusion at final follow-up. Secondary outcomes included stroke rates, mortality rates, need for retreatment and clinical outcomes.There were a total of 7 patients with 7 aneurysms treated with FRED Jr. Mean aneurysm neck, width, height, and parent artery diameter were 2.6 ± 0.8 mm, 3.1 ± 0.9 mm, 2.5 ± 1.0 mm, and 1.8 ± 0.6 mm respectively. The complete occlusion rate was 57.1 % at 6 months, and favorable outcome (mRS 0-2) was observed in all patients in follow-up. Stroke complication occurred in none of the patients. Seven studies from 1360 articles were identified for inclusion in the meta-analysis, comprising 227 patients with 244 aneurysms treated with FRED Jr. Mean aneurysm height, width, neck and parent artery diameter were 6.9 ± 3.3 mm (pooled=5.6 [0.1-11.47] mm), 6.6 ± 2.2 mm (pooled=6.6 [4.2-9.1] mm), 4.4 ± 1.4 mm (pooled=4.1 [3.3 -4.9] mm), and 2.0 ± 0.2 mm (pooled=2.1 [1.7-2.5]), respectively. At final follow-up, the pooled complete occlusion and complication rates were 69.9 % and 0 %, respectively.FRED Jr demonstrated moderate efficacy and good safety in the treatment of distal aneurysms with small parent vessels at mid-term follow-up.

Background The radial approach has been gaining more widespread use by neurointerventionalists fueled by data from the cardiology literature showing better safety and overall reduced morbidity. Objective To present our institution's experience with the radial approach for neuroendovascular interventions in 614 consecutive patients who underwent a cumulative of 760 procedures. Methods A retrospective analysis was performed and identified neuroendovascular procedures performed via the upper extremity vasculature access site. Results Amongst 760 procedures, 34.2% (260) were therapeutic, and 65.7% (500) were nontherapeutic angiograms. Access sites were 71.5% (544) via a conventional radial artery, 27.8% (211) via a distal radial artery, 0.5% (4) via an ulnar artery, and 0.1% (1) via the brachial artery. Most of the procedures (96.9%) were performed via the right-sided (737), 2.9% (22) via the left-sided, and 0.1% (1) via a bilateral approach. Major access site complications occurred at a rate of 0.9% (7). The rate of transfemoral conversion was 4.7% (36). There was a statistically higher incidence of transfemoral conversion when repeat procedures were performed using the same access site. Also, there was no significant difference between nontherapeutic procedures performed using the right and left radial access, and conventional versus distal radial access. Procedural metrics improved after completion of 14 procedures, indicating a learning curve that should be surpassed by operators to reach optimal outcomes. Conclusion Radial artery catheterization is a safe and effective means of carrying out a wide range of neuroendovascular procedures associated with excellent clinical outcomes and an overall low rate of periprocedural complications.

Spontaneous intracerebral hemorrhage (sICH) is a disease process with high morbidity and mortality. In particular, hematoma expansion (HE) is a feared complication of sICH. With 15-40% of patients experiencing HE, it has become increasingly important to predict which sICH will remain stable and which will expand.With new treatment options being developed, it is becoming increasingly important to be able to predict which hemorrhages are at high versus low risk for expansion. The authors of this study hope to reexamine variables associated with hematoma expansion in hopes of generating newer data on risk factors for expansion.A retrospective analysis identified 334 patients who presented with sICH. The primary outcome was HE on follow up head CT. HE was defined as a greater than 33% increase or an absolute increase in 6 mL or more in overall volume between the two sets of CT images. Analysis was performed using unpaired t-test, Chi-square, and Fisher's exact tests, as appropriate.Of the 334 patients, 247 (74.0%) did not experience an expansion of their ICH while 87 (26.0%) did. Multivariable logistic regression was performed demonstrating ICH score of 3 or greater (4.76 (95% CI 2.60-8.72, p 0.001) , cortical location of the sICH (1.77 (95% CI 1.03-3.04, p = 0.038), and presence of a fluid level (6.46 (95% CI 2.28-18.3, p 0.001) as significant predictors of HE.Our study found that fluid-fluid levels on non-contrast CT, an ICH score 3 or greater, and lobar sICH were all more likely to expand.

OBJECTIVE The aim of this review is to provide a summary of the epidemiology, clinical presentation, pathophysiology, and treatment of traumatic brain injury in collision athletes, particularly those participating in American football. DATA SOURCES A literature search was conducted using the PubMed/MEDLINE and Google Scholar databases for publications between 1990 and 2019. The following search phrases were used: "concussion," "professional athletes," "collision athletes," "mild traumatic brain injury," "severe traumatic brain injury," "management of concussion," "management of severe traumatic brain injury," and "chronic traumatic encephalopathy." Publications that did not present epidemiology, clinical presentation, pathophysiology, radiological evaluation, or management were omitted. Classic articles as per senior author recommendations were retrieved through reference review. RESULTS The results of the literature review yielded 147 references: 21 articles discussing epidemiology, 16 discussing clinical presentation, 34 discussing etiology and pathophysiology, 10 discussing radiological evaluation, 34 articles for on-field management, and 32 articles for medical and surgical management. CONCLUSION Traumatic brain injuries are frequent in professional collision athletes, and more severe injuries can have devastating and lasting consequences. Although sport-related concussions are well studied in professional American football, there is limited literature on the epidemiology and management of severe traumatic brain injuries. This article reviews the epidemiology, as well as the current practices in sideline evaluation, acute management, and surgical treatment of concussions and severe traumatic brain injury in professional collision athletes. Return-to-play decisions should be based on individual patient symptoms and recovery.

BACKGROUND United States (U.S.) healthcare is a volume-based inefficient delivery system. Value requires the consideration of quality, which is lacking in most healthcare disciplines. OBJECTIVE To assess whether patients who met specific evidence-based medicine (EBM)-based criteria preoperatively for lumbar fusion would achieve higher rates of achieving the minimal clinical important difference (MCID) than those who did not meet the EBM indications. METHODS All elective lumbar fusion cases, March 2018 to August 2019, were prospectively evaluated and categorized based on EBM guidelines for surgical indications. The MCID was defined as a reduction of ≥5 points in Oswestry Disability Index (ODI). Multiple logistic regression identified multivariable-adjusted odds ratio of EBM concordance. RESULTS A total of 325 lumbar fusion patients were entered with 6-mo follow-up data available for 309 patients (95%). The median preoperative ODI score was 24.4 with median 6-mo improvement of 7.0 points (P

Background The transradial access (TRA) is rapidly gaining popularity for neuroendovascular procedures as there is strong evidence for its benefits compared to the traditional transfemoral access (TFA). However, the transition to TRA bears some challenges including optimization of the interventional suite set-up and workflow as well as its impact on fellowship training. Objective To compare the learning curves of TFA and TRA for diagnostic cerebral angiograms in neuroendovascular fellowship training. Methods We prospectively collected diagnostic angiogram procedural data on the performance of 2 neuroendovascular fellows with no prior endovascular experience who trained at our institution from July 2018 until June 2019. Metrics for operator proficiency were minutes of fluoroscopy time, procedure time, and volume of contrast used. Results A total of 293 diagnostic angiograms were included in the analysis. Of those, 57.7% were TRA and 42.3% were TFA. The median contrast dose was 60 cc, and the median radiation dose was 14 000 μGy. The overall complication rate was 1.4% consisting of 2 groin hematomas, 1 wrist hematoma, and 1 access-site infection using TFA. The crossover rate to TFA was 2.1%. Proficiency was achieved after 60 femoral and 95 radial cases based on fluoroscopy time, 52 femoral and 77 radial cases based on procedure time, and 53 femoral and 64 radial cases based on contrast volume. Conclusion Our study demonstrates that the use of TRA can be safely incorporated into neuroendovascular training without causing an increase in complications or significantly prolonging procedure time or contrast use.

Background In patients with brain parenchyma extending beyond the craniectomy defect, cerebrospinal fluid diversion may be necessary to facilitate proper bone flap replacement during cranioplasty. In this study, we present our case series of patients who underwent ultrasound-guided ventricular puncture during cranioplasty and report periprocedural metrics and clinical outcomes. Methods A retrospective study of patients who presented for cranioplasty that required ultrasound-guided ventricular puncture was performed. We also describe our operative technique for safely and accurately performing ultrasound-guided ventricular puncture. Results Ten consecutive patients were included in the overall patient cohort, all of whom required intraoperative ventricular puncture to achieve brain relaxation. The mean time between decompressive hemicraniectomy and cranioplasty was 145.4 days (range 19–419). The mean duration of cranioplasty operation was 146 minutes (range 74–193). All patients underwent ultrasound-guided ventricular puncture, and 5 patients had an external ventricular drain left in place for postoperative intracranial pressure monitoring and possible cerebrospinal fluid drainage. There were no instances of pericatheter hemorrhage. One patient presented postoperatively with wound infection, and this same patient was the only one in the cohort who required subsequent ventriculoperitoneal shunt for symptomatic hydrocephalus. Conclusions Ultrasound-guided ventricular puncture is safe, feasible, and efficacious for use during cranioplasty to help facilitate bone flap replacement in patients with “full” brains, with an overall low rate of associated periprocedural complications. Although further studies are needed in a larger patient cohort, this technique should be considered to help reduce the morbidity associated with cranioplasty.

Follow-up MRI/MRA is historically obtained as outpatient when patients with a spontaneous intracerebral hemorrhage (ICH) have an initial MRI/MRA that is negative for an underlying structural lesion. However, the utility of repeating MR imaging in a delayed fashion remains uncertain. We retrospectively reviewed 396 patients with spontaneous ICH admitted at our institution between 2015 and 2017 and selected those whose initial MRI/MRA was negative for an underlying structural lesion and those who underwent follow-up MR imaging in a delayed fashion. A total of 113 patients met the study criteria. The average age of those with negative follow-up MRI/MRA was 65.0 ± 12.6 (IQR: 55.0–74.0) years old. None of the 113 patients with a negative inpatient MRI/MRA had an underlying structural lesion on follow-up MRI/MRA (0%, 95% CI 0.0–0.032, p < 0.001). The mean time of the follow-up imaging from the initial study was 105.7 days (median: 62 days; IQR: 42.5–100.5). Of the 113, 83 (73.5%) underwent follow-up MRI with and without gadolinium, while 30 (26.5%) patients did not receive gadolinium. Delayed follow-up MRI in patients with a negative initial MRI/MRA for workup of spontaneous ICH was not diagnostic in any of the patients included in the study. Our study suggests that a routine follow-up MRI for this patient population is not necessary.

OBJECTIVEThe advent of mechanical thrombectomy (MT) has become an effective option for the treatment of acute ischemic stroke in addition to tissue plasminogen activator (tPA). With recent advances in device technology, MT has significantly altered the hospital course and functional outcomes of stroke patients. The authors’ goal was to establish the most up-to-date reperfusion and functional outcomes with the evolution of MT technology.METHODSThe authors conducted a retrospective study of 403 patients who underwent MT for ischemic stroke at their institution from 2010 to 2017. They collected data on patient comorbidities, National Institutes of Health Stroke Scale (NIHSS) score on arrival, tPA administration, revascularization outcomes, and functional outcomes on discharge.RESULTSIn 403 patients, the mean NIHSS score on presentation was 15.8 ± 6.6, with 195 (48.0%) of patients receiving tPA prior to MT. Successful reperfusion (thrombolysis in cerebral infarction score 2B or 3) was achieved in 84.4%. Hemorrhagic conversion with significant mass effect was noted in 9.9% of patients. The median lengths of ICU and hospital stay were 3.0 and 7.0 days, respectively. Functional independence (modified Rankin Scale score 0–2) was noted in 125 (31.0%) patients, while inpatient mortality occurred in 43 (10.7%) patients.CONCLUSIONSAs MT has established acute ischemic stroke as a neurosurgical disease, there is a pressing need to understand the hospital course, hospital- and procedure-related complications, and outcomes for this new patient population. The authors provide a detailed account of key metrics for MT with the latest device technology and identify the predictors of unfavorable outcomes and inpatient mortality.

Background Carotid-cavernous fistulas (CCFs) are acquired pathological shunting lesions between the carotid artery and the cavernous sinus leading to elevated intraocular pressure (IOP). CCFs are commonly treated via endovascular embolization, which theoretically restores physiological pressure differentials. Objective To present our institutional data with CCF treated with embolization and discuss endovascular routes, recurrence rates, and dynamic IOP changes. Methods Retrospective analysis of 42 CCF patients who underwent Onyx (Covidien, Irvine, California) embolization and pre- and postoperative IOP measurement at a single institution. Results CCFs were 19.0% direct (type A) and 81.0% indirect (types B, C, or D). Onyx-18 liquid embolisate was used during all embolizations. Overall rate of total occlusion was 83.3% and was statistically similar between direct and indirect fistulas. Preoperative IOP was elevated in 37.5%, 100.0%, 75.0%, and 50% in type A, B, C, and D fistulas, respectively. Average ΔIOP was -7.3 ± 8.5 mmHg (range: -33 to +8). Follow-up time was 4.64 ± 7.62 mo. Full angiographic occlusion was a predictor of symptom resolution at 1 mo (P = .026) and 6 mo (P = .021). Partial occlusion was associated with persistent symptoms postoperatively at 1 mo (P = .038) and 6 mo follow-up (P = .012). Beyond 6 mo, negative ΔIOP was associated with continued symptom improvement. Recurrence occurred in 9.5% of patients, all of which were indirect CCFs. Conclusion Onyx embolization of CCF is an effective treatment for CCF and often results in the reversal of IOP elevation. Full occlusion predicts favorable clinical outcomes up to 6 mo. Postoperative IOP reduction may indicate favorable long-term clinical outcomes.

Herein, the authors present the case of a 54-year-old male diagnosed with coronavirus disease 2019 (COVID-19) during a screening test. The patient was asked to self-isolate at home and report with any exacerbations of symptoms. He presented later with pneumonia complicated by encephalopathy at days 14 and 15 from initial diagnosis, respectively. MRI of the brain showed bithalamic and gangliocapsular FLAIR signal abnormality with mild right-sided thalamic and periventricular diffusion restriction. A CT venogram was obtained given the distribution of edema and demonstrated deep venous thrombosis involving the bilateral internal cerebral veins and the vein of Galen. CSF workup was negative for encephalitis, as the COVID-19 polymerase chain reaction (PCR) test and bacterial cultures were negative. A complete hypercoagulable workup was negative, and the venous thrombosis was attributed to a hypercoagulable state induced by COVID-19. The mental decline was attributed to bithalamic and gangliocapsular venous infarction secondary to deep venous thrombosis. Unfortunately, the patient’s condition continued to decline, and care was withdrawn.

OBJECTIVEMechanical thrombectomy (MT) is now the standard of care for acute ischemic stroke (AIS) secondary to large-vessel occlusion, but there remains a question of whether elderly patients benefit from this procedure to the same degree as the younger populations enrolled in the seminal trials on MT. The authors compared outcomes after MT of patients 80–89 and ≥ 90 years old with AIS to those of younger patients.METHODSThe authors retrospectively analyzed records of patients undergoing MT at their institution to examine stroke severity, comorbid conditions, medical management, recanalization results, and clinical outcomes. Univariate and multivariate logistic regression analysis were used to compare patients < 80 years, 80–89 years, and ≥ 90 years old.RESULTSAll groups had similar rates of comorbid disease and tissue plasminogen activator (tPA) administration, and stroke severity did not differ significantly between groups. Elderly patients had equivalent recanalization outcomes, with similar rates of readmission, 30-day mortality, and hospital-associated complications. These patients were more likely to have poor clinical outcome on discharge, as defined by a modified Rankin Scale (mRS) score of 3–6, but this difference was not significant when controlled for stroke severity, tPA administration, and recanalization results.CONCLUSIONSOctogenarians, nonagenarians, and centenarians with AIS have similar rates of mortality, hospital readmission, and hospital-associated complications as younger patients after MT. Elderly patients also have the capacity to achieve good functional outcome after MT, but this potential is moderated by stroke severity and success of treatment.

Background and importance Carotid-cavernous fistulas (CCF) are pathological connections between carotid artery branches and the cavernous sinus. They can lead to a variety of symptoms, such as chemosis and double vision, or more insidious events, such as vision loss and intracranial hemorrhage. Although these patients are often treated by endovascular means, we describe a case in which the patient's CCF was not able to be accessed by usual methods and required an open surgical approach. Clinical presentation The patient had progressive chemosis, double vision, and periorbital pain. Angiogram showed an indirect type D CCF with cortical venous drainage with a large sylvian vein that was directly draining the fistula. The patient did not have a dilated superior ophthalmic vein, and the petrosal sinuses could not be catheterized. Therefore, because of the patient's increased risk for intracranial hemorrhage, she was taken to the operating room for an image guided burr hole for direct catheterization of the sylvian vein. From this point, the fistulous point could be catheterized, and the CCF was embolized using onyx. Follow-up angiogram showed complete occlusion. Conclusion This is the first report in literature of an indirect CCF being treated through a transsylvian approach with onyx. This combined open-surgical-and-endovascular approach was necessary to get full resolution of the lesion, and patient had rapid improvement of symptoms.

Mobile stroke units (MSUs) have been implemented worldwide for stroke care, but outcome data are lacking to show their efficacy specifically in patients undergoing mechanical thrombectomy (MT). Here, we include patients from our stroke network MSU and compare them to patients who arrived conventionally.A retrospective review of a stroke database was performed to identify patients who underwent MT after arrival via an MSU from August 2019 to December 2020. Demographic factors, past medical history, stroke characteristics, treatment variables, complications, and functional outcomes were recorded. These were compared to date-matched patients who underwent MT after arrival via conventional means.Seven patients were treated with MT after arriving by an MSU. These patients were compared to 50 date-matched patients who underwent thrombectomy after arrival through conventional means. No statistically significant difference between cohorts was observed in terms of demographic variables, comorbidities, stroke characteristics, or tissue plasminogen activator administration. Patients from the MSU cohort had significantly shorter time from symptom onset to groin puncture time (191.33 minutes ±77.53 vs. 483.51 minutes ±322.66, P = 0.034). Importantly, MSU-transferred patients had significantly better discharge functional status measured by using the modified Rankin Scale (1.86 ± 1.35 vs. 3.57 ± 1.88, P = 0.024). No significant difference in final thrombolysis in cerebral infarction score, complications, length of stay, or mortality was observed.Our pilot study demonstrates the efficacy of the MSU in decreasing door-to-puncture time and a concordant improvement in the discharge modified Rankin Scale score. Further prospective studies are needed to assess cost-efficacy and optimal protocol for MSUs in stroke care.

Mechanical thrombectomy is established as standard of care in the management of acute ischemic stroke due to large vessel occlusion and evidence-based guidelines for mechanical thrombectomy have been defined. As research continues to further expand the eligibility criteria for thrombectomy and the number of thrombectomy procedures increase worldwide, there is also growing focus on innovation of thrombectomy devices, procedural techniques, and related outcomes. Thrombectomy primarily involves use of stent retrievers and distal aspiration techniques, but variations and different combinations of techniques have been reported. As this is a rapidly evolving area in stroke management, there is debate as to which, if any, of these techniques leads to improved clinical outcomes over another and there is a lack of data comparing them. In this review, currently published and distinct techniques of mechanical thrombectomy are described methodically along with illustrations to aid in understanding the subtle differences between the techniques. The perceived benefits of each variation are discussed.

Study Design Retrospective Cohort Study. Objectives To determine the ability of early vital sign abnormalities to predict functional independence in patients with SCI that required surgery. Methods A retrospective analysis of data extracted from the Pennsylvania Trauma Outcome Study database. Inclusion criteria were patients >18 years with a diagnosis of SCI who required urgent spine surgery in Pennsylvania from 1/1/2010-12/31/2020 and had complete records available. Results A total of 644 patients met the inclusion criteria. The mean age was 47.1 ± 14.9 years old and the mean injury severity score (ISS) was 22.3 ± 12.7 with the SCI occurring in the cervical, thoracic, and lumbar spine in 61.8%, 19.6% and 18.0%, respectively. Multivariable logistic regression analyses for predictors of functional independence at discharge showed that higher HR at the scene (OR 1.016, 95% CI 1.006-1.027, P = .002) and lower ISS score (OR .894, 95% CI .870-.920, P < .001) were significant predictors of functional independence. Similarly, higher admission HR (OR 1.015, 95% CI 1.004-1.027, P = .008) and lower ISS score (OR .880, 95% CI 0.864-.914, P < .001) were significant predictors of functional independence. Peak Youden indices showed that patients with HR at scene >70 and admission HR ≥83 were more likely to achieve functional independence. Conclusions Early heart rate is a strong predictor of functional independence in patients with SCI. HR at scene >70 and admission HR ≥83 is associated with improved outcomes, suggesting lack of neurogenic shock.

Machine learning algorithms have received increased attention in neurosurgical literature for improved accuracy over traditional predictive methods. In this review, the authors sought to assess current applications of machine learning for outcome prediction of neurosurgical treatment of intracranial aneurysms and identify areas for future research.A PRISMA-compliant systematic review of the PubMed, MEDLINE, and EMBASE databases was conducted for all studies utilizing machine learning for outcome prediction of intracranial aneurysm treatment. Patient characteristics, machine learning methods, outcomes of interest, and accuracy metrics were recorded from included studies.16 studies were ultimately included in qualitative synthesis. Studies primarily analyzed angiographic outcomes, functional outcomes, or complication prediction using clinical, radiological, or composite variables. The majority of included studies utilized supervised learning algorithms for analysis of dichotomized outcomes.Commonly included variables were demographics, presentation variables (including ruptured or unruptured status), and treatment used. Areas for future research include increased generalizability across institutions and for smaller datasets, as well as development of front-end tools for clinical applicability of published algorithms.

This meeting abstract was removed due to the OA licensing requirements of this journal. The full abstract is listed here : https://www.svin.org/files/SVIN_2021_Abstracts_for_Web.pdf

Rescue stenting is used as a bailout technique during mechanical thrombectomy for stroke. We performed a retrospective study analyzing outcomes of patients that received a stent as a bailout measure and compared results to a control group.We identified all patients who underwent a mechanical thrombectomy for a large vessel occlusion between January 2010 and October 2019. Subjects with mTICI 0-2 A after at least three passes were defined as failed MT and constituted the control group (NSG-controls). Patients that received a rescue stent (RSG) formed the study group.Comparative analysis of patient demographics between NSG-controls and SRG was performed. Baseline characteristics and comorbidities were not significantly different between both groups. NIHSS at admission and IV t-PA were not significantly different among both groups (16.5 vs. 14.2, p = 0.19) and (39.4% vs. 29.4%, p = 0.30), respectively. There was no significant difference in procedural and post-procedural complications between both the groups. In the RSG, 24 patients (82.4%) achieved favorable revascularization outcomes. NIHSS at discharge (p = 0.01) was higher in the NSG-controls, while favorable functional outcome at three months (12% vs. 39.2%, p = 0.01) was observed at a higher proportion in the RSG. There was also a significant mortality difference, with 15.2% mortality in the RSG compared to 35.1% mortality in the NSG-controls (p = 0.03). In multivariate analysis, stenting was an independent predictor of favorable outcome (OR: 10.0, p = 0.009).Herein, we demonstrated that rescue stenting is a feasible, safe, and effective procedure to improve stroke outcomes and should be seriously considered if the primary mechanical thrombectomy is not successful.

The flow redirection endoluminal device (FRED) is a novel self-expanding double-layer nitinol braided flow diverter that recently received FDA approval. However, early postmarket studies from the United States are lacking.To report our short-term multicenter experience.Series of consecutive patients undergoing FRED treatment for intracranial aneurysms were queried from prospectively maintained registries at 4 North-American Centers in Pennsylvania (February 2020-June 2021). The pertinent baseline demographics, aneurysmal characteristics, and procedural outcomes were collected and analyzed, with primary outcome of aneurysmal occlusion and secondary outcome of safety and complications.Sixty-one patients (median age 58 years, 82% female) underwent 65 FRED treatment procedures for 72 aneurysms. Most (86.1%) of the aneurysms were unruptured; 80.5% were saccular in morphology, and 87.5% were located along the internal carotid artery, with a median size of 7.1 mm (IQR 5.2-11.9 mm). Radiographic follow-up was available in 86.1% of the aneurysms, showing complete occlusion in 74.2% (80% in catheter angiography-only group), and near-complete occlusion in 11.3% of the cases (median 6.3 months), with 2.8% re-treated. Permanent ischemic complications were encountered in 2.8% of the cases, with no procedural mortality. A modified Rankin Scale of 0 to 2 was documented in 98.1% of the patients at the last clinical follow-up (median 6.1 months).The results of the early postmarket experience with the FRED device show reasonable safety and adequate aneurysmal occlusion rates comparable with other flow diverters. However, more extensive multicenter studies with more extended follow-up data are needed to assess the long-term safety and durability of the device.

Background Despite the recent increase of transradial access among neurointerventionalists, there is still a paucity of evidence in the neurosurgical literature. There are 3 newly Food and Drug Administration–approved devices—Woven EndoBridge (WEB), Surpass, and PulseRider—that significantly expand the options available for endovascular treatment of cerebral aneurysms. Our work reports the safety and feasibility of radial artery catheterization for the deployment of these new devices. Methods We performed a review of the first 10 patients with an unruptured cerebral aneurysm treated via a transradial cerebral angiogram. Seven patients underwent embolization with the WEB device, 1 patient underwent embolization with the PulseRider, and 2 patients underwent embolization with the Surpass device. We describe in detail our workflow and the devices used for transradial access. Results The aneurysms treated include internal carotid artery bifurcation, middle cerebral artery, anterior communicating artery, basilar tip, and posterior communicating artery. All patients underwent radial artery catheterization, and none of them had to be converted to femoral artery access. Of the 10 patients, 9 required a single attempt for accurate device deployment. One patient had unsuccessful placement of the WEB device and required coiling of the aneurysm because of device herniation into the parent vessel. None of the patients had any postoperative complications and were discharged the following day with the same modified Rankin scale score as preoperatively. Conclusions Our experience with 10 patients revealed no limitations during catheterization and deployment of these devices. One patient had to be converted to coil embolization, which was feasible through the same vascular access. None of the patients had vascular complications postoperatively with minimal wrist discomfort.

Intracranial pressure (ICP)-guided therapy has been the mainstay of treatment of patients with severe traumatic brain injury (TBI), but recent data have questioned its efficacy. The aim of this study was to demonstrate trends in compliance to TBI guidelines and use of ICP-guided care in a mature trauma system.A retrospective analysis was conducted of 36,915 patients with severe TBI collected by the Pennsylvania Trauma Systems Foundation. The registry includes all patients18 years old with a diagnosis of TBI with a Glasgow Coma Scale score ≤8 who were admitted from January 2000 to December 2017.Of 36,915 patients, 73.6% were men with a median age of 43.0 ± 21.3 years. An ICP monitor was placed in 16.3% of all patients. The rate of ICP monitoring ranged from 17.8% of patients in 2000-2004 to 16.7% in 2005-2009, 16.4% in 2010-2014, and 12.8% in 2015-2017 (P 0.001). The most statistically significant decrease was noted from 2014 (16.4%) to 2015 (14.1%, P = 0.042). The percent decrease in ICP monitoring from 2000-2014 to 2015-2017 was equivalent for patients with Glasgow Coma Scale scores of 3-5 (-4.0%) and 6-8 (-4.5%).As studies emerged that demonstrated unclear benefit of ICP monitoring in improving care in patients with severe TBI, there was a significant statewide decline in the use of ICP monitoring after 2014 among all TBI subpopulations despite noteworthy limitations in the aforementioned studies and clear recommendations from the Brain Trauma Foundation guidelines.

The Woven EndoBridge (WEB) device is becoming increasingly popular for treatment of wide-neck aneurysms. As experience with this device grows, it is important to identify factors associated with occlusion following WEB treatment to guide decision making and screen patients at high risk for recurrence. The aim of this study was to identify factors associated with adequate aneurysm occlusion following WEB device treatment in the neurosurgical literature and in our case series. A systematic review of the present literature was conducted to identify studies related to the prediction of WEB device occlusion. In addition, a retrospective review of our institutional data for patients treated with the WEB device was performed. Demographics, aneurysm characteristics, procedural variables, and 6-month follow-up angiographic outcomes were recorded. Seven articles totaling 450 patients with 456 aneurysms fit our criteria. Factors in the literature associated with inadequate occlusion included larger size, increased neck width, partial intrasaccular thrombosis, irregular shape, and tobacco use. Our retrospective review identified 43 patients with 45 aneurysms. A total of 91.1% of our patients achieved adequate occlusion at a mean follow-up time of 7.32 months. Increasing degree of contrast stasis after WEB placement on the post-deployment angiogram was significantly associated with adequate occlusion on follow-up angiogram (p = 0.005) and with Raymond-Roy classification (p = 0.048), but not with retreatment (p = 0.617). In our systematic review and case series totaling 450 patients with 456 aneurysms, contrast stasis on post-deployment angiogram was identified as a predictor of adequate aneurysm occlusion, while morphological characteristics such as larger size and wide neck negatively impact occlusion.

BACKGROUND There is a paucity of information regarding treatment strategies and variables affecting outcomes of revision lumbar fusions. OBJECTIVE To evaluate the influence of primary vs different surgeon on functional outcomes of revisions. METHODS All elective lumbar fusion revisions, March 2018 to August 2019, were retrospectively categorized as performed by the same or different surgeon who performed the primary surgery. Oswestry Disability Index (ODI) and clinical variables were collected. Multiple logistic regression identified multivariable-adjusted odds ratio (OR) of independent variables analyzed. RESULTS Of the 130 cases, 117 (90%) had complete data. There was a slight difference in age in the same (median: 59; interquartile range [IQR], 54-66) and different surgeon (median: 67; IQR, 56-72) groups (P = .02); all other demographic variables were not significantly different (P > .05). Revision surgery with a different surgeon had an ODI improvement (median: 8; IQR, 2-14) greater than revisions performed by the same surgeon (median: 1.5; IQR, -3 to 10) (P

Instrumented fusion procedures are essential in the treatment of degenerative lumbar spine disease to alleviate pain and improve neurological function, but they are being performed with increasing incidence and variability. We implemented a training module for neurosurgery residents that is based on evidence-based criteria for lumbar fusion surgery and measured its effectiveness in residents' decision making regarding whether patients should or should not undergo instrumented fusion.The study design was a pretest versus posttest experiment conducted from September 2019 until July 2020 to measure improvement after formalized instruction on evidence-based guidelines. Neurosurgery residents of all training levels at our institution participated. A test was administered at the beginning of each academic year. The highest possible score was 18 points in each pretest and posttest.There was a general trend of test score improvement across all levels of training with a greater degree of change for participants with lower compared with higher pretest scores, indicating a possible ceiling effect. Paired t test demonstrated an overall mean score increase of 2 points (P0.0001), equivalent to an 11.11% increase (P 0.0001). Stratified by training group, mean absolute change in test score was 2 (P = 0.0217), 1.67 (P = 0.0108), and 2.25 (P = 0.0173) points for junior, midlevel, and senior training groups, respectively.Incorporating a targeted evidence-based learning module for lumbar spine fusion surgery can improve neurosurgery residents' clinical decision making toward a more uniform practice supported by published data.

Neuroendovascular surgery has become an indispensable domain in the treatment of cerebrovascular disease with a slew of treatment options for numerous pathologies. The field experienced a movement toward a transradial approach for diagnostic and interventional procedures. Advantages of the transradial approach include lower risk for complications, which can be fatal using the transfemoral route, higher patient satisfaction, and shorter hospital stays. Those advantages are not unique to the adult population but are, in fact, even more pronounced in pediatrics. They include early mobilization of patients since flat bed rest is not required as it is with transfemoral puncture for hemostasis at the groin. This also obviates the need for continuous intravenous sedatives, which is fraught with its own risks. Early reports have demonstrated the feasibility of transradial cerebral angiography in children. Others have also shown that the transradial approach can be safely used to administer intra-arterial chemotherapy in children with retinoblastoma. A standardized protocol is imperative to maximize the success rate of the transradial approach in pediatrics and includes the routine use of ultrasound as well as a “radial cocktail” to avoid vasospasm. While transfemoral may be the conventional route, transradial offers a plethora of advantages, particularly in children. As more experience in transradial is gained in adults, it is likely that this will translate into more transradial procedures in children as well.

IntroductionTrigeminal neuralgia remains a challenging disease with significant debilitating symptoms and variable efficacy in terms of treatment options, namely microvascular decompression (MVD), stereotactic radiosurgery (SRS), and percutaneous rhizotomy. Internal neurolysis (IN) is an alternative treatment that may be provide patient benefit but has limited understanding. We performed a systematic review of IN treatment of trigeminal neuralgia.MethodsStudies from 2000 to 2021 that assessed IN in trigeminal neuralgia were aggregated and independently reviewed. Weighted averages for demographics, outcomes and complications were generated.ResultsA total of 520 patients in 12 studies were identified with 384 who underwent IN (mean age 53.8 years, range 46-61.4 years). A mean follow-up time of 36.5 months (range 12-90 months) was seen. Preoperative symptoms were present for about 55.0 months before treatment and pain was predominantly in V2/3 (26.8%) followed by other distributions. An excellent to good outcome (Barrow Neurological Institute Pain Score [BNI-PS] I-III) was seen in 83.7% of patients (range 72-93.8%). Pain outcomes at 1 year were excellent in 58-78.4%, good or better in 77-93.75% and fair or better in 80-93.75% of patients. On average facial numbness following IN was seen in 96% of patients however at follow-up remained in only 1.75-10%. The vast majority of remaining numbness was not significantly distressing to patients. Subgroup comparisons of IN vs. recurrent MVD, IN vs. radiofrequency ablation, the impact of IN during the absence of vascular compression as well as IN with and without MVD were also evaluated.ConclusionsIN represents a promising approach for surgical treatment of trigeminal neuralgia in the absence of vascular compression or in potential cases of recurrence. Complications were limited in general. Further study is required to evaluate the impact of IN via higher quality prospective studies.

Glioblastoma (GBM) with deep-supratentorial extension (DSE) involving the thalamus, basal ganglia and corpus collosum, poses significant challenges for clinical management. In this study, we present our outcomes in patients who underwent resection of supratentorial GBM with associated involvement of deep brain structures. We conducted a retrospective review of patients who underwent resection of GBM at our institution between 2012 and 2018. A total of 419 patients were included whose pre-operative MRI scans were reviewed. Of these, 143 (34.1%) had GBM with DSE. There were similar rates of IDH-1 mutation (9% versus 7.6%, p = 0.940) and MGMT methylation status (35.7% versus 45.2%, p = 0.397) between the two cohorts. GBM patients without evidence of DSE had higher rates of radiographic gross total resection (GTR) compared to those with DSE: 70.6% versus 53.1%, respectively (p = 0.002). The presence of DSE was not associated with decreased progression-free survival (PFS) compared to patients without DSE (mean 7.24 ± 0.97 versus 8.89 ± 0.76 months, respectively; p = 0.276), but did portend a worse overall survival (OS) (mean 10.55 ± 1.04 versus 15.02 ± 1.05 months, respectively; p = 0.003). There was no difference in PFS or OS amongst DSE and non-DSE patients who underwent GTR, but patients who harbored DSE and underwent subtotal resection had worse OS (mean 8.26 ± 1.93 versus 12.96 ± 1.59 months, p = 0.03). Our study shows that GBM patients with DSE have lower OS compared to those without DSE. This survival difference appears to be primarily related to the limited surgical extent of resection owing to the neurological deficits that may be incurred with involvement of eloquent deep brain structures.

Objective The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic is a pressing public health issue. Although most cases do not result in severe illness requiring hospitalization, there is increasing evidence that SARS-CoV-2–induced inflammation can exacerbate pre-existing diseases. We sought to describe the characteristics of patients with aneurysmal subarachnoid hemorrhage who were actively or very recently infected with SARS-CoV-2. Methods We reviewed subarachnoid hemorrhage cases of patients who also were positive for SARS-CoV-2 at 5 high-volume cerebrovascular centers in the United States from March 2020 to January 2021. Cases of aneurysmal subarachnoid hemorrhage were analyzed. Results A total of 10 patients were identified, consisting of 5 women (50%) and 5 men (50%). Median age was 38.5 years. Four of the 10 patients (40%) were asymptomatic with respect to SARS-CoV-2–related symptoms, 3 patients (30%) had mild-to-moderate symptoms, and 3 patients (30%) had severe coronavirus disease 2019 (COVID-19), with pneumonia and sepsis. Of the 10 cases, 4 had dissecting pseudoaneurysms (40%), 3 in the posterior circulation and 1 in the anterior circulation. Among 6 saccular/blister aneurysms, 4 (67%) were ≤4 mm in largest diameter. Conclusions Our experience with aneurysmal subarachnoid hemorrhage in patients positive for COVID-19 reveals a possibly distinct pattern compared with traditional aneurysmal subarachnoid hemorrhage, namely a high frequency of small aneurysms, dissecting pseudoaneurysms, and young patients.

Background Machine learning algorithms depend on accurate and representative datasets for training in order to become valuable clinical tools that are widely generalizable to a varied population. We aim to conduct a review of machine learning uses in stroke literature to assess the geographic distribution of datasets and patient cohorts used to train these models and compare them to stroke distribution to evaluate for disparities. Aims 582 studies were identified on initial searching of the PubMed database. Of these studies, 106 full texts were assessed after title and abstract screening which resulted in 489 papers excluded. Of these 106 studies, 79 were excluded due to using cohorts from outside the United States or being review articles or editorials. 27 studies were thus included in this analysis. Summary of review Of the 27 studies included, 7 (25.9%) used patient data from California, 6 (22.2%) were multicenter, 3 (11.1%) were in Massachusetts, 2 (7.4%) each in Illinois, Missouri, and New York, and 1 (3.7%) each from South Carolina, Washington, West Virginia, and Wisconsin. 1 (3.7%) study used data from Utah and Texas. These were qualitatively compared to a CDC study showing the highest distribution of stroke in Mississippi (4.3%) followed by Oklahoma (3.4%), Washington D.C. (3.4%), Louisiana (3.3%), and Alabama (3.2%) while the prevalence in California was 2.6%. Conclusions It is clear that a strong disconnect exists between the datasets and patient cohorts used in training machine learning algorithms in clinical research and the stroke distribution in which clinical tools using these algorithms will be implemented. In order to ensure a lack of bias and increase generalizability and accuracy in future machine learning studies, datasets using a varied patient population that reflects the unequal distribution of stroke risk factors would greatly benefit the usability of these tools and ensure accuracy on a nationwide scale.

Introduction Novel machine learning (ML) methods are being investigated across medicine for their predictive capabilities while boasting increased adaptability and generalizability. In our study, we compare logistic regression with machine learning for feature importance analysis and prediction in first-pass reperfusion. Methods We retrospectively identified cases of ischemic stroke treated with mechanical thrombectomy (MT) at our institution from 2012–2018. Significant variables used in predictive modeling were demographic characteristics, medical history, admission NIHSS, and stroke characteristics. Outcome was binarized TICI on first pass (0-2a vs 2b-3). Shapley feature importance plots were used to identify variables that strongly affected outcomes. Results Accuracy for the Random Forest and SVM models were 67.1% compared to 65.8% for the logistic regression model. Brier score was lower for the Random Forest model (0.329 vs 0.342) indicating better predictive capability. Other supervised learning models performed worse than the logistic regression model, with accuracy of 56.2% for Naive Bayes and 61.6% for XGBoost. Shapley plots for the Random Forest model showed use of aspiration, hyperlipidemia, hypertension, use of stent retriever, and time between symptom onset and catheterization as the top five predictors of first pass reperfusion. Conclusion Use of machine learning models, such as Random Forest, for the study of MT outcomes, is more accurate than logistic regression for our dataset, and identifies new factors that contribute to achieving first pass reperfusion. The benefits of machine learning, such as improved predictive capabilities, integration of new data, and generalizability, establish ML as the preferred model for studying outcomes in stroke.