Automated Preoperative and Postoperative Volume Estimates Risk of Retreatment in Chronic Subdural Hematoma: A Retrospective, Multicenter Study.

BACKGROUND AND OBJECTIVES: Several neurosurgical pathologies, ranging from glioblastoma to hemorrhagic stroke, use volume thresholds to guide treatment decisions. For chronic subdural hematoma (cSDH), with a risk of retreatment of 10%-30%, the relationship between preoperative and postoperative cSDH volume and retreatment is not well understood. We investigated the potential link between preoperative and postoperative cSDH volumes and retreatment. METHODS: We performed a retrospective chart review of patients operated for unilateral cSDH from 4 level 1 trauma centers, February 2009-August 2021. We used a 3-dimensional deep learning, automated segmentation pipeline to calculate preoperative and postoperative cSDH volumes. To identify volume thresholds, we constructed a receiver operating curve with preoperative and postoperative volumes to predict cSDH retreatment rates and selected the threshold with the highest Youden index. Then, we developed a light gradient boosting machine to predict the risk of cSDH recurrence. RESULTS: We identified 538 patients with unilateral cSDH, of whom 62 (12%) underwent surgical retreatment within 6 months of the index surgery. cSDH retreatment was associated with higher preoperative (122 vs 103 mL; P < .001) and postoperative (62 vs 35 mL; P < .001) volumes. Patients with >140 mL preoperative volume had nearly triple the risk of cSDH recurrence compared with those below 140 mL, while a postoperative volume >46 mL led to an increased risk for retreatment (22% vs 6%; P < .001). On multivariate modeling, our model had an area under the receiver operating curve of 0.76 (95% CI: 0.60-0.93) for predicting retreatment. The most important features were preoperative and postoperative volume, platelet count, and age. CONCLUSION: Larger preoperative and postoperative cSDH volumes increase the risk of retreatment. Volume thresholds may allow identification of patients at high risk of cSDH retreatment who would benefit from adjunct treatments. Machine learning algorithm can quickly provide accurate estimates of preoperative and postoperative volumes.

Interaction of admission platelet count with current medications and the risk for chronic subdural recurrence.

OBJECTIVE: Chronic subdural hematoma (cSDH) has a reported 10%-24% rate of recurrence after surgery, and prognostic models for recurrence have produced equivocal results. The objective of this study was to leverage a data mining algorithm, chi-square automatic interaction detection (CHAID), which can incorporate continuous, nominal, and binary data into a decision tree, to identify the most robust predictors of repeat surgery for cSDH patients. METHODS: This was a retrospective cohort study of all patients with SDH from two level 1 trauma centers at a single institution. All patients underwent cSDH evacuation performed by 15 neurosurgeons between 2011 and 2020. The primary outcome was the rate of repeat surgery for recurrent cSDH following the initial evacuation. The authors used CHAID to identify relevant predictors of repeat surgery, including age, sex, comorbidities, postsurgical complications, platelet count prior to the first procedure, midline shift prior to the first procedure, hematoma volume, and preoperative use of anticoagulants, antiplatelets, or statins. RESULTS: Sixty (13.8%) of 435 study-eligible patients (average age 74.0 years) had a cSDH recurrence. These patients had 2.0 times greater odds of having used anticoagulants. The final CHAID model had an overall accuracy of 87.4% and an area under the curve of 0.76. According to the model, the predictor with the strongest association with cSDH recurrence was admission platelet count. Approximately 26% of patients (n = 23/87) with an admission platelet count < 157 × 109/L had a cSDH recurrence, whereas none of the 44 patients with admission platelets > 313 × 109/L had a recurrence. Approximately 17% of patients in the 157-313 × 109/L platelet group who had used preoperative statins required a second procedure, which was associated with a 2.3 times increased risk for repeat surgery compared to those who had not used statins preoperatively. Among those who had not used preoperative statins, a platelet count ≤ 179 × 109/L on admission for the first procedure was the strongest differentiator for a second surgery (n = 5/22 [23%]), which increased the risk of recurrence by 4.5 times. Among the patients using preoperative statins, the use of anticoagulants was the strongest differentiator for requiring repeat surgery (n = 11/33 [33%]). CONCLUSIONS: The described model identified platelet count on admission as the most important predictor of repeat cSDH surgery, followed by preoperative statin use and anticoagulant use. Critical cutoffs for platelet count were identified, which future studies should evaluate to determine if they are modifiable or reflective of underlying disease states.

Safety and efficacy of eptifibatide in acute ischemic stroke requiring extracranial carotid artery stenting.

BACKGROUND: The antiplatelet management in acute ischemic stroke requiring carotid artery stenting is heterogenous, with no clear guidelines to direct management. OBJECTIVE: To evaluate the safety and efficacy of an intravenous eptifibatide protocol in the management of acute ischemic stroke requiring emergent carotid artery stenting. METHODS: We performed a retrospective analysis of consecutive patients who underwent carotid artery stenting for acute ischemic stroke at a high-volume tertiary neuroscience center, who were managed with an intravenous eptifibatide protocol. The protocol consists of an intravenous loading eptifibatide bolus (180 mcg/kg) at the time of stenting, followed by a maintenance infusion of 1 mcg/kg/min, then oral or nasogastric loading of dual antiplatelet agents. RESULTS: 80 patients were included for analysis. Median presenting NIHSS was 17. Sixty-six patients (83%) had a tandem intracranial occlusion. Six (7.5%) patients developed symptomatic intracranial hemorrhage (sICH). Those who received intravenous thrombolysis were not more likely to develop sICH (10% vs 5%, p = 0.40). Those patients with a presenting ASPECTS <8 were significantly more likely to develop sICH than those with ASPECTS 8-10 (25% vs 3%, p = 0.004). CONCLUSIONS: Eptifibatide may have a role in the management of acute stroke requiring carotid stenting. Caution may be required in those with established infarct on presentation imaging.

The perils and promises of generative artificial intelligence in neurointerventional surgery.

Generative artificial intelligence (AI) holds great promise in neurointerventional surgery by providing clinicians with powerful tools for improving surgical precision, accuracy of diagnoses, and treatment planning. However, potential perils include biases or inaccuracies in the data used to train the algorithms, over-reliance on generative AI without human oversight, patient privacy concerns, and ethical implications of using AI in medical decision-making. Careful regulation and oversight are needed to ensure that the promises of generative AI in neurointerventional surgery are realized while minimizing its potential perils.[ChatGPT authored summary using the prompt "In one paragraph summarize the promises and perils of generative AI in neurointerventional surgery".].

Establishment of Age- and Sex-Specific Reference Cerebral Ventricle Volumes.

BACKGROUND: The diagnosis of hydrocephalus is dependent on clinical symptoms and radiographic findings including ventriculomegaly. Our goal was to generate a data set of ventricular volume utilizing non-pathologic computed tomography (CT) scans for adults to help define reference ventricle size. METHODS: We performed a retrospective analysis of non-contrast head CTs for adults at a single institution to identify patients who had undergone imaging and did not have a diagnosis of hydrocephalus, history of ventriculoperitoneal shunting, or treatments for hydrocephalus. A convolutional neural network was trained on hand-segmented scans from a variety of age ranges and then utilized to automate the segmentation of the entire data set. RESULTS: Ventricles on 866 CT scans were segmented to generate a reference range of volumes for both male and female individuals ranging in age from 18-99 years. The generated data were binned by age ranges. CONCLUSIONS: We have developed a convolutional neural network that can segment the ventricles on CT scans of adult patients over a range of ages. This network was used to measure the ventricular volume of non-pathologic head CTs to produce reference ranges for several age bins. This data set could be utilized to aid in the diagnosis of hydrocephalus by comparing potentially pathologic scans to reference ventricular volumes.

Safety and feasibility of the Wahoo Hybrid Access System, a dual-mode guide catheter, in a range of neuroendovascular procedures.

BACKGROUND: There is a clinical need for a guide catheter with combined stability and navigability, which can be used in a biaxial system for neuroendovascular procedures in place of triaxial systems. OBJECTIVE: To assess the safety and feasibility of the Q'Apel Medical Wahoo Hybrid Access System, a dual-mode 0.072″ internal diameter guide catheter, in a range of neuroendovascular procedures. METHODS: We performed a retrospective analysis of consecutive cases from a high-volume tertiary center in which the Wahoo Hybrid Access System was used as the guide catheter. Characteristics of the patients, vascular lesions, procedure, and procedural complications were assessed. RESULTS: A total of 102 patients were included for analysis. Vascular lesions were in the anterior circulation in 90 of 102 (88%), and posterior circulation in 12 of 102 (12%). Eighty-four cases were ruptured or unruptured aneurysm embolization procedures, the majority being balloon-assisted coiling (42%) and flow diversion (42%). All cases, including flow diversion, were performed as a biaxial system. There were no instances of prolapse of the catheter beyond the arterial segment in which it was initially placed. The procedure was able to be performed to completion in 101 of 102 (99%) cases. Thromboembolic complications occurred in 5 of 102 (5%); causality in two cases was unrelated to the guide catheter, and three were indeterminate. CONCLUSIONS: The Wahoo guide catheter is safe and feasible when used in a variety of neuroendovascular procedures. It can accommodate a range of devices, can be safely navigated into distal vasculature, and provides support for a range of procedures, including those which traditionally require triaxial support.

Comparative study of intracranial access in thrombectomy using next generation 0.088 inch guide catheter technology.

BACKGROUND: Most conventional 0.088 inch guide catheters cannot safely navigate intracranial vasculature. The objective of this study is to evaluate the safety of stroke thrombectomy using a novel 0.088 inch guide catheter designed for intracranial navigation. METHODS: This is a multicenter retrospective study, which included patients over 18 years old who underwent thrombectomy for anterior circulation large vessel occlusions. Technical outcomes for patients treated using the TracStar Large Distal Platform (TracStar LDP) or earlier generation TRX LDP were compared with a matched cohort of patients treated with other commonly used guide catheters. The primary outcome measure was device-related complications. Secondary outcome measures included guide catheter failure and time between groin puncture and clot engagement. RESULTS: Each study arm included 45 patients. The TracStar group was non-inferior to the control group with regard to device-related complications (6.8% vs 8.9%), and the average time to clot engagement was 8.89 min shorter (14.29 vs 23.18 min; p=0.0017). There were no statistically significant differences with regard to other technical outcomes, including time to recanalization (modified Thrombolysis In Cerebral Infarction (mTICI) ≥2B). The TracStar was successfully advanced into the intracranial internal carotid artery in 33 cases (73.33%); in three cases (6.67%), it was swapped for an alternate catheter. Successful reperfusion (mTICI 2B-3) was achieved in 95.56% of cases. Ninety-day follow-up data were available for 86.67% of patients, among whom 46.15% had an modified Rankin Score of 0-2%, and 10.26% were deceased. CONCLUSIONS: Tracstar LDP is safe for use during stroke thrombectomy and was associated with decreased time to clot engagement. Intracranial access was regularly achieved.

Walrus large bore guide catheter impact on recanalization first pass effect and outcomes: the WICkED study.

BACKGROUND: The use of a balloon-guide catheter (BGC) in acute stroke treatment has been widely adopted after demonstrating optimized procedure metrics and outcomes. Initial technical constraints of previous devices included catheter stiffness and smaller inner diameters. We aim to evaluate the performance and safety of the Walrus BGC, a variable stiffness catheter with a large bore 0.087 inch inner diameter (ID), via the the WICkED study (Walrus Large Bore guide Catheter Impact on reCanalization first pass Effect anD outcomes). METHODS: This is a retrospective, site adjudicated, multicenter study on consecutive patients with large vessel occlusion treated with the Walrus BGC. Baseline characteristics, procedural outcomes and functional outcomes were analyzed. RESULTS: A total of 338 patients met the inclusion criteria. The Walrus was successfully tracked into distal vasculature and allowed therapeutic device delivery in all but 3 cases (0.9%). Large aspiration catheters ≥0.070 inch ID were used in 71.9% of cases. Stent retriever thrombectomy was used as the first-line modality in 59.2% and thromboaspiration in 40.8% of cases. The successful recanalization rate (modified treatment in cerebral ischemia (mTICI) 2b/3) was 94.4%, with 64.8% of the patients achieving mTICI 2b/3 after the first pass. The Walrus-related adverse event rate was 0.6%, corresponding to two vessel dissections. Functional independence was 50% (126/252) and mortality 25% (63/252). Unfavorable outcomes were more likely in older patients, who had unsuccessful reperfusion, longer procedure times, and a higher mean number of passes. CONCLUSION: In acute ischemic stroke patients presenting with large vessel occlusion, the Walrus BGC demonstrated excellent navigability and safety profile, allowed the accommodation of leading large bore aspiration catheters, and demonstrated high vessel recanalization rates.

Aspiration Thrombectomy: 2-Dimensional Operative Video.

Acute ischemic stroke is one of the leading causes of disability and mortality worldwide. There have been significant improvements to the treatment of acute ischemic stroke over the past 5 yr, specifically related to strokes caused by large vessel occlusions. Stent retrievers with and without local aspiration and direct aspiration alone have all been demonstrated as viable treatment options for this patient population. This case represents the surgical technique for direct aspiration for the treatment of large vessel occlusion. A 76-yr-old man presented with right-sided weakness and aphasia. His last known normal was 5 h ago. His NIHSS (National Institutes of Health Stroke Scale) was 18. The noncontrast computed tomography (CT) did not show a significant infarct burden and ASPECTS (Alberta Stroke Program Early CT Score) of 9. CT angiogram demonstrated a left M1 occlusion. The patient was not a candidate for tissue plasminogen activator (tPA) because of time to presentation; however, the patient was deemed to be a candidate for emergent thrombectomy. Consent was obtained per institutional guidelines for the emergent procedure and the video recording. The video demonstrates a direct aspiration thrombectomy technique for the treatment of stroke. The patient successfully underwent direct aspiration thrombectomy with a TICI 3 (thrombolysis in cerebral infarction) recanalization.

Segmentation of Chronic Subdural Hematomas Using 3D Convolutional Neural Networks.

OBJECTIVE: Chronic subdural hematomas (cSDHs) are an increasingly prevalent neurologic disease that often requires surgical intervention to alleviate compression of the brain. Management of cSDHs relies heavily on computed tomography (CT) imaging, and serial imaging is frequently obtained to help direct management. The volume of hematoma provides critical information in guiding therapy and evaluating new methods of management. We set out to develop an automated program to compute the volume of hematoma on CT scans for both pre- and postoperative images. METHODS: A total of 21,710 images (128 CT scans) were manually segmented and used to train a convolutional neural network to automatically segment cSDHs. We included both pre- and postoperative coronal head CTs from patients undergoing surgical management of cSDHs. RESULTS: Our best model achieved a DICE score of 0.8351 on the testing dataset, and an average DICE score of 0.806 ± 0.06 on the validation set. This model was trained on the full dataset with reduced volumes, a network depth of 4, and postactivation residual blocks within the context modules of the encoder pathway. Patch trained models did not perform as well and decreasing the network depth from 5 to 4 did not appear to significantly improve performance. CONCLUSIONS: We successfully trained a convolutional neural network on a dataset of pre- and postoperative head CTs containing cSDH. This tool could assist with automated, accurate measurements for evaluating treatment efficacy.

Efficacy of beveled tip aspiration catheter in mechanical thrombectomy for acute ischemic stroke.

BACKGROUND: Direct aspiration thrombectomy techniques use large bore aspiration catheters for mechanical thrombectomy. Several aspiration catheters are now available. We report a bench top exploration of a novel beveled tip catheter and our experience in treating large vessel occlusions (LVOs) using next-generation aspiration catheters. METHODS: A retrospective analysis from a prospectively maintained database comparing the bevel shaped tip aspiration catheter versus non-beveled tip catheters was performed. Patient demographics, periprocedural metrics, and discharge and 90-day modified Rankin Scale (mRS) scores were collected. Patients were divided into two groups based on which aspiration catheter was used. RESULTS: Our data showed no significant difference in age, gender, IV tissue plasminogen activator administration, admission NIH Stroke Scale score, baseline mRS, or LVO location between the beveled tip and flat tip groups. With the beveled tip, Thrombolysis in Cerebral Infarction (TICI) 2C or better recanalization was more frequent overall (93.2% vs 74.2%, p=0.017), stent retriever usage was lower (9.1% vs 29%, p=0.024), and patients had lower mRS on discharge (median 3 vs 4, p<0.001) and at 90 days (median 2 vs 4, p=0.008). CONCLUSION: Patients who underwent mechanical thrombectomy with the beveled tip catheter had a higher proportion of TICI 2C or better and had a significantly lower mRS score on discharge and at 90 days.

Lessons Learned Over More than 500 Stroke Thrombectomies Using ADAPT With Increasing Aspiration Catheter Size.

BACKGROUND: Endovascular thrombectomy is currently the standard of care for acute ischemic stroke (AIS). Although earlier trials on endovascular thrombectomy were performed using stent retrievers, recently completed the contact aspiration vs stent retriever for successful revascularization (ASTER) and a comparison of direct aspiration versus stent retriever as a first approach (COMPASS) trials have shown the noninferiority of direct aspiration. OBJECTIVE: To report the largest experience with ADAPT thrombectomy and compare the impact of advancement in reperfusion catheter technologies on outcomes. METHODS: We reviewed a retrospective database of AIS patients who underwent ADAPT thrombectomy between January 2013 and November 2017 at the Medical University of South Carolina. Demographics and baseline characteristics, technical variables, and radiological and clinical outcomes were reviewed. RESULTS: Among 510 patients (mean age: 67.7, 50.6% females), successful recanalization at first pass was achieved in 61.8%, and with aspiration only in 77.5%. Mean procedure time was 27.4 min, and the rate of good outcomes (mRS 0-2) at 90 d was 42.9%. The rate of recanalization with aspiration only was significantly higher, and procedure time was significantly lower in patients treated with larger catheters (ACE 064 and ACE 068) compared to smaller catheters (5 MAX and ACE, P < .05). There were no differences in complication rates or postoperative parenchymal hemorrhage across groups (P > .05); however, use of ACE 068 was an independent predictor of good outcomes at 90 d on multivariate regression analysis (odds ratio = 1.6, P < .05). CONCLUSION: Refinement of ADAPT thrombectomy by incorporating reperfusion catheters with higher inner diameters and thus higher aspiration forces is associated with better outcomes, shorter procedure times, and lower likelihood of using additional devices without impacting complication rates.

Impact of Procedure Time on Outcomes of Thrombectomy for Stroke.

BACKGROUND: Endovascular thrombectomy (ET) for acute ischemic stroke is the current standard of care. Although successful ET has high efficacy in improving functional outcomes, the decision to abort a long procedure remains a challenge. Longer procedure time (PT) has been associated with lower rates of functional independence. OBJECTIVES: The objective of this study was to evaluate the impact of PT on outcomes and complications after ET using different techniques at a multicenter level and to define the risk of procedure extension in different patient cohorts. METHODS: Patients undergoing ET with a stent retriever (SR) or a direct aspiration at first pass technique at 7 U.S. centers between June 2013 and February 2018 were reviewed from prospectively maintained databases that include baseline variables and technical and clinical outcomes. Multivariate analyses were used to assess impact of PT on 90-day modified Rankin scores, successful recanalization, post-procedural symptomatic hemorrhage (sICH), and complications. RESULTS: The study included 1,359 patients and demonstrated a decreased likelihood of good functional outcomes (modified Rankin score 0 to 2) when PT extended beyond 30 min (p < 0.01). Rates of sICH and complications increased exponentially with PT (doubling rates of 26 and 50 min, respectively). The cumulative rate of successful recanalization and good outcomes plateaued after 60 min of PT. In patients with PT >30 min, fewer attempts predicted the success of ET and good outcomes (p < 0.01). Successful recanalization was achieved faster with the direct aspiration at first pass technique than in SR. The direct aspiration technique was more sensitive to PT than SR, and posterior stroke was more sensitive to PT than anterior stroke. CONCLUSIONS: Longer ET procedures lead to lower rates of functional independence and higher rates of sICH and complications. Exceeding 60 min or 3 attempts should trigger careful assessment of futility and risks of continuing the procedure.

Intra-Arterial Tissue Plasminogen Activator Is a Safe Rescue Therapy with Mechanical Thrombectomy.

INTRODUCTION: Intra-arterial tissue plasminogen activator (IA-tPA) has been widely used in conjunction with mechanical thrombectomy (MT) or as rescue therapy. Data on the safety of IA-tPA as a rescue therapy are scarce. OBJECTIVE: To report the safety outcome of IA-tPA during MT with respect to hemorrhage and functional outcome. METHODS: We reviewed our prospectively maintained data and identified patients who received mechanical thrombectomy between November 1, 2014, and January 30, 2018. Collected variables included demographics, comorbidities, baseline National Institutes of Health Stroke Scale, procedural variables, and outcome variables, which were subjected to a matched and unmatched analysis. Hemorrhagic transformation was classified based on European Cooperative Acute Stroke Study criteria. Functional outcome was assessed based on modified Rankin Scale. RESULTS: A total of 486 patients were treated with MT during the study period, of whom 67 patients received IA tPA as a rescue therapy. IA tPA was used at the discretion of neuroendovascular surgeon if complete recanalization (modified Treatment in Cerebral Ischemia ≥2c) was not achieved with ADAPT (A Direct Aspiration First Pass Technique) or for distal occlusion that could not be reached with thrombectomy catheters. Both groups did not differ in baseline characteristics, comorbidities, or admission National Institutes of Health Stroke Scale. There was no significant difference in good outcome (modified Rankin Scale ≤2), death, any hemorrhage, or parenchymal hemorrhage type 2 between groups in matched and unmatched analyses. CONCLUSIONS: IA-tPA administration during MT was not associated with increased risk of hemorrhage in selected patients with incomplete recanalization after thrombectomy.

First attempt recanalization with ADAPT: rate, predictors, and outcome.

INTRODUCTION: The rate of first-attempt recanalization (FAR) with the newer-generation thrombectomy devices, and more specifically with aspiration devices, is not well known. Moreover, the effect of FAR on outcomes after mechanical thrombectomy is not properly understood. OBJECTIVE: To report the rate of FAR using a direct aspiration first pass technique (ADAPT), investigate the association between FAR and outcomes, and identify the predictors of FAR. METHODS: The ADAPT database was used to identify a subgroup of patients in whom FAR was achieved. Baseline characteristics, procedural, and postprocedural variables were collected. Outcome measures included 90-day modified Rankin scale (mRS) score, mortality, and hemorrhagic complications. Multivariate logistic regression was used to identify FAR predictors. RESULTS: A total of 524 patients was included of whom 178 (34.0%) achieved FAR. More patients in the FAR group than in the non-FAR group received IV tPA (46.6% vs 37.6%; p<0.05). For the functional outcome, higher proportions of patients in the FAR group achieved functional independence (mRS score 0-2; 53% vs 37%; p<0.05). Additionally, we observed lower mortality and hemorrhagic transformation rates in the FAR group than the non-FAR group. Independent predictors of FAR in the anterior circulation were pretreatment IV tPA, non-tandem occlusion, and use of larger reperfusion catheters (Penumbra, ACE 64-68). Independent predictors of FAR in the posterior circulation were diabetes, onset-to-groin time, and cardioembolic etiology. CONCLUSION: FAR was associated with better functional outcome and lower mortality rate. When ADAPT is used, a larger aspiration catheter and pretreatment IV tPA should be employed when indicated.

Incidence, predictors, and outcome of early seizures after mechanical thrombectomy.

OBJECTIVE: Despite the wide utilization of mechanical thrombectomy (MT) for acute ischemic stroke treatment, little is known about the incidence of early post-thrombectomy seizures, its predictors, and association with long-term outcome. METHODS: Using a prospective registry of mechanical thrombectomy in ischemic stroke between January 2013 and July 2017, we identified patients who developed a seizure within 7 days (early seizure) of qualifying event. Backward stepwise regression analysis was used to assess independent predictors of seizure occurrence and the association between seizure and functional outcome (modified Rankin scale of 0-2 vs. ≥3). RESULTS: A total of 459 patients were included in the final analysis. Mean age was 67.5 (SD 15.1), and 49.9% of patients were female. Successful recanalization (TICI≥2B) was achieved in 92.8% of patients. Eleven (2.4%) patients developed at least one seizure. Only an Alberta Stroke Program Early CT (ASPECT) score of <6 was independently associated with the occurrence of early seizures [Odds ratio, 95% confidence interval: 8.188, (2.219-30.214); P = .002]. On multivariate analysis, early seizures were associated with 90-day mortality rate [OR,6.487; 95% confidence interval, (1.481-28.405); P = .013] and poor functional outcome (OR, 4.7; 95% confidence interval (1.08-20.83); p = .039). CONCLUSION: In the studied cohort, 2.4% of ischemic stroke patients treated with MT developed at least one seizure within 7 days of stroke onset. A low ASPECT score was associated with the occurrence of early seizures. The occurrence of seizures was associated with 90-day mortality and poor functional outcome.

Initial Experiences with Artificial Neural Networks in the Detection of Computed Tomography Perfusion Deficits.

BACKGROUND: Head computed tomography (CT) with perfusion imaging has become crucial in the selection of patients for mechanical thrombectomy. In recent years, machine learning has rapidly evolved and found applications in a wide variety of health care tasks. We report our initial experiences with training a neural network to predict the presence and laterality of a perfusion deficit in patients with acute ischemic stroke. METHODS: CT perfusion images of patients with suspicion for acute ischemic stroke were obtained. The data were split into training and validation sets. A long-term, recurrent convolutional network was constructed, which consisted of a convolutional neural network stacked on top of a long short-term memory layer. RESULTS: Of the 396 patients, 139 (35.1%) had a right-sided perfusion deficit, 199 (50.3%) had a left-sided deficit, and 58 (14.6%) had no evidence of a deficit. The best model was able to achieve an accuracy of 85.8% on validation data. Receiver operating characteristic curves were generated for each class, and an area under the curve (AUC) was calculated for each class. For right-sided deficits, the AUC was 0.90, for left-sided deficits, the AUC was 0.96, and for no deficit, the AUC was 0.93. CONCLUSIONS: The field of machine learning, powered by convolutional neural networks for the task of image recognition and processing, has quickly developed in recent years. We constructed an artificial neural network that can identify and classify the presence and laterality of a perfusion deficit on CT perfusion imaging.

Thrombectomy for acute ischemic stroke in the elderly: a 'real world' experience.

INTRODUCTION: Completed randomized trials on endovascular thrombectomy (ET) did not independently assess the efficacy of ET in the elderly (≥80 years old) who were often excluded or under-represented in trials. There were also inconsistent criteria for patient selection in this population across the different trials. This work evaluates outcomes after ET for acute ischemic stroke (AIS) in the elderly at a high volume stroke center. METHODS: We reviewed all cases of AIS that underwent a direct aspiration first pass technique (ADAPT) thrombectomy for large vessel occlusions between March 2013 and October 2017 while comparing outcomes in the elderly with younger counterparts. We also reviewed AIS cases in elderly patients undergoing medical management who were matched to the ET counterparts by demographics, comorbidities, baseline deficits, and stroke severity. RESULTS: Of 560 patients undergoing ET for AIS, 108 patients were in the elderly group (≥80 years of age), and had a significantly lower likelihood of functional independence (defined as a modified Rankin Scale score of 0-2) at 90 days compared with younger patients (20.5% vs 44.4%, P<0.001), and higher mortality rates (34.3% vs 20%, P<0.001). When compared with patients undergoing medical management, elderly patients did not have a significant improvement in rates of good outcomes (20.5% vs 19.5%, P>0.05), and had significantly higher rates of hemorrhage (40.7% vs 9.3%, P<0.001). We also identified baseline stroke severity and the incidence of hemorrhage as two independent predictors of outcome in the elderly patients. CONCLUSIONS: ET in the elderly did not show a similar benefit to younger patients when compared with medical management. These findings emphasize the need for more optimal selection criteria for the elderly population to improve the risk to benefit ratio of ET.

Evaluation of previously embolized intracranial aneurysms: inter-and intra-rater reliability among neurosurgeons and interventional neuroradiologists.

BACKGROUND: The angiographic evaluation of previously coiled aneurysms can be difficult yet remains critical for determining re-treatment. OBJECTIVE: The main objective of this study was to determine the inter-rater reliability for both the Raymond Scale and per cent embolization among a group of neurointerventionalists evaluating previously embolized aneurysms. METHODS: A panel of 15 neurointerventionalists examined 92 distinct cases of immediate post-coil embolization and 1 year post-embolization angiographs. Each case was presented four times throughout the study, along with alterations in demographics in order to evaluate intra-rater reliability. All respondents were asked to provide the per cent embolization (0-100%) and Raymond Scale grade (1-3) for each aneurysm. Inter-rater reliability was evaluated by computing weighted kappa values (for the Raymond Scale) and intraclass correlation coefficients (ICC) for per cent embolization. RESULTS: 10 neurosurgeons and 5 interventional neuroradiologists evaluated 368 simulated cases. The agreement among all readers employing the Raymond Scale was fair (κ=0.35) while concordance in per cent embolization was good (ICC=0.64). Clinicians with fewer than 10 years of experience demonstrated a significantly greater level of agreement than the group with greater than 10 years (κ=0.39 and ICC=0.70 vs κ=0.28 and ICC=0.58). When the same aneurysm was presented multiple times, clinicians demonstrated excellent consistency when assessing per cent embolization (ICC=0.82), but moderate agreement when employing the Raymond classification (κ=0.58). CONCLUSIONS: Identifying the per cent embolization in previously coiled aneurysms resulted in good inter- and intra-rater agreement, regardless of years of experience. The strong agreement among providers employing per cent embolization may make it a valuable tool for embolization assessment in this patient population.

The golden 35†min of stroke intervention with ADAPT: effect of thrombectomy procedural time in acute ischemic stroke on outcome.

INTRODUCTION: In acute ischemic stroke (AIS), extending mechanical thrombectomy procedural times beyond 60 min has previously been associated with an increased complication rate and poorer outcomes. OBJECTIVE: After improvements in thrombectomy methods, to reassess whether this relationship holds true with a more contemporary thrombectomy approach: a direct aspiration first pass technique (ADAPT). METHODS: We retrospectively studied a database of patients with AIS who underwent ADAPT thrombectomy for large vessel occlusions. Patients were dichotomized into two groups: 'early recan', in which recanalization (recan) was achieved in ≤35 min, and 'late recan', in which procedures extended beyond 35 min. RESULTS: 197 patients (47.7% women, mean age 66.3 years) were identified. We determined that after 35 min, a poor outcome was more likely than a good (modified Rankin Scale (mRS) score 0-2) outcome. The baseline National Institutes of Health Stroke Scale (NIHSS) score was similar between 'early recan' (n=122) (14.7±6.9) and 'late recan' patients (n=75) (15.9±7.2). Among 'early recan' patients, recanalization was achieved in 17.8±8.8 min compared with 70±39.8 min in 'late recan' patients. The likelihood of achieving a good outcome was higher in the 'early recan' group (65.2%) than in the 'late recan' group (38.2%; p<0.001). Patients in the 'late recan' group had a higher likelihood of postprocedural hemorrhage, specifically parenchymal hematoma type 2, than those in the 'early recan' group. Logistic regression analysis showed that baseline NIHSS, recanalization time, and atrial fibrillation had a significant impact on 90-day outcomes. CONCLUSIONS: Our findings suggest that extending ADAPT thrombectomy procedure times beyond 35 min increases the likelihood of complications such as intracerebral hemorrhage while reducing the likelihood of a good outcome.