Citations

Background: Estimating operative time with low accuracy and precision leads to suboptimal scheduling of available operating rooms (ORs) and waste of healthcare resources. We aimed to develop a predictive machine learning (ML) model for operative time using our institutional data to improve the scheduling of neurosurgical ORs, minimize waste, and maximize resource utilization. Methods: We developed a predictive model using our institution’s multicenter registry, which included diverse neurosurgical cases across three tertiary hospitals. We applied multiple ML techniques, including linear regression, support vector regression, deep neural networks, and extreme gradient boosting regression (XGBR). The best model was combined with the first fit decreasing bin-packing algorithm to create a practical OR scheduling system based on prior data. Results: The XGBR model exhibited the best performance, with lower mean absolute errors (MAEs) (root mean squared error: 52.24, MAE: 37.25) and higher R2 (0.76) values than other models. Implementing this model in a simulated OR scheduling scenario using institutional data, we successfully scheduled 30 random procedures with minimal residual time, such that the model ran out of procedures for the week with 86 and 171 min remaining in the cranial and spinal ORs, respectively, demonstrating potential efficiency gains. The cranial procedures were scheduled over 4 days and spinal procedures over 6 days, optimizing available OR time. Conclusion: Integrating ML models into operative time prediction can significantly improve the accuracy and efficiency of surgical schedules. This approach minimizes wasted OR time and enhances resource allocation, potentially improving patient outcomes and satisfaction by reducing waiting times.

BACKGROUND AND IMPORTANCE: Basilar artery fenestration aneurysms (BAFAs) present significant clinical challenges because of their high rupture risk and complex anatomy. Comprehensive management strategies are required, including thorough vascular assessment and post-treatment surveillance. Integration of complementary analyses such as computational fluid dynamics (CFD) holds promise in facilitating preoperative planning for these intricate lesions. CLINICAL PRESENTATION: A 60-year-old female was diagnosed with a BAFA during evaluation for headaches. Digital subtraction angiography revealed the aneurysm projecting posteriorly with a neck predominantly based on the right limb of the fenestration. After initial treatment with a pipeline embolization device, the aneurysm remained patent, requiring further treatment. A secondary approach with stent-assisted loose-packing coil embolization was then performed, resulting in complete occlusion of the aneurysm. Analysis of pretreatment 3-dimensional rotational angiogram images with CFD provided critical hemodynamic insights. It identified that 38.89% of the aneurysm area was exposed to low wall shear stress (WSS) and 11.5% was exposed to high WSS, indicating a high rupture risk profile with significant areas of both low and high WSS. In addition, low WSS was observed in regions corresponding to daughter sacs, suggesting a higher rupture risk. Streamline analysis indicated increased inflow through the right vertebral artery and the right limb of the fenestration, supporting the initial angiographic impression and guiding the choice of therapeutic strategy. CONCLUSION: This is the first study to analyze the morphology and pretreatment hemodynamics of a BAFA using CFD, illustrating the potential for future development of individualized therapeutic approach–based CFD in complex aneurysms.

Background The Woven EndoBridge (WEB) device is a prevalent treatment for intracranial aneurysms. While many studies have assessed the obliteration rate post-WEB embolization, few have focused on long-term outcomes in partially thrombosed aneurysms. Objective To assess whether partially thrombosed aneurysms are at higher risk of recurrence or retreatment following WEB embolization compared with non-thrombosed aneurysms. Methods We evaluated data from 22 academic institutions, focusing on previously untreated cerebral aneurysms treated with the WEB device. Logistic regression was utilized to analyze factors predicting long-term aneurysm obliteration and retreatment necessity. Results Among 1303 patients, 26 presented with a partially thrombosed aneurysm. In the partially thrombosed group, the mean aneurysm maximal diameter was 10.7±4 mm with a neck ratio of 1.99±1.19 mm, larger than in the control group where the mean aneurysm maximal diameter was 6.81±2.37 mm with a neck ratio of 1.64±0.51 mm (P<0.001 for both maximal diameter and neck ratio). At the final follow-up, partially thrombosed aneurysms treated by the WEB device had a 38.5% retreatment rate, compared with 7.0% for non-thrombosed aneurysms (P<0.001). Among partially thrombosed aneurysms, the Raymond-Roy type IIIa/b occlusion rate was higher (38.5% vs 9.9%, P<0.001). On multivariate analysis, partially thrombosed aneurysms compared with non-thrombosed aneurysms had an increased rate of retreatment (OR 3.64, 95% CI 1.28 to 10.1). Conclusion Partially thrombosed aneurysms are associated with a poorer occlusion rate and a higher rate of retreatment following WEB embolization. For partially thrombosed aneurysms, the WEB device appears suboptimal as a first-line treatment, and therefore alternative techniques should be prioritized.

Background We automated subarachnoid hemorrhage volume (SAHV) calculation with artificial intelligence (SAHVAI) and created 3‐dimensional volumetric images (SAHVAI‐3D) using noncontrast head computed tomography data for patients with aneurysmal SAH. We also defined 4‐dimensional SAHVAI (SAHVAI‐4D), representing SAHV over time. We aimed to compare automated SAHVAI values and computational times to manual SAHV measurement methods, explore the potential of imaging biomarkers to identify at‐risk brain regions for delayed cerebral ischemia and explore potential insights in future neurotherapeutic interventions for patient recovery after SAH. Methods A training set of 10 consecutive patients with aneurysmal SAH was used to manually compute SAHV, SAHVAI‐3D, and SAHVAI‐4D, including 92 noncontrast computed tomography scans (182 slices each). The SAHVAI deep learning algorithm generated automated SAHV values in cubic centimeters. A 3‐dimensional SAH brain map was created for each patient for the SAHVAI and manual evaluations. Blood volumetric outputs were analyzed and compared to neurologic outcomes at discharge, including delayed cerebral ischemia events, symptomatic vasospasm, and areas with the thickest SAH blood concentration. Results SAHVAI quantified SAHV in a mean of 6.7 seconds per scan, significantly faster than the manual method, which took >60 minutes per scan (Fisher exact test, P <0.001). SAHVAI demonstrated an accuracy of 99.8%, Dice score of 0.701, false‐positive rate of 0.0005, and negative predictive value of 0.999. The mean absolute error between SAHVAI and manual methods was 5.67 mL. SAHVAI‐3D brain map and total SAHV at admission were inversely associated with Glasgow Coma Scale (R 2 = 0.23, P = 0.017) and directly associated with length of hospital stay (R 2 = 0.175, P = 0.004), especially in regions with dense blood concentration. Conclusion SAHVAI‐3D and SAHVAI‐4D brain mapping techniques represent innovative imaging biomarkers for SAH. These advancements enable rapid evaluation and targeted interventions, potentially improving patient care in SAH management.

BACKGROUND AND OBJECTIVES: Rising US healthcare costs and the COVID-19 pandemic put increased pressure on hospitals to reduce patient length of stay (LOS) while maintaining high-quality care. We aimed to determine if implementing a pathway for same-day discharge after elective neuroendovascular procedures to a monitored hotel setting is safe, feasible, and cost-effective. METHODS: We evaluated patient outcomes after elective neuroendovascular procedures and same-day discharge to an on-campus Care Hotel. The study enrolled patients aged ≥18 years from October 1, 2020, to February 28, 2023. Exclusion criteria comprised major comorbidities, additional care necessitating hospitalization, absence of a caregiver, insurer-mandated hospitalization, or patient refusal of the Care Hotel model. Primary outcomes were readmission rate or prolonged LOS, new ischemic or hemorrhagic complications rate, and death rate from vascular causes within 6 months. Secondary outcomes included adverse events and deaths related to causes other than vascular complications within 6 months and changes in modified Rankin Scale score by 1 or more points at last follow-up. Healthcare cost savings associated with same-day discharge were analyzed using a control group. RESULTS: The study included 42 patients discharged to the Care Hotel and 84 controls. The average age was 61 years in the Care Hotel group and 64 years in the control group, and aneurysm treatment was the most frequent neuroendovascular procedure (83.3% and 79.8%, respectively). The readmission and extended LOS rates were 4.8% for the Care Hotel group. The rate of new ischemic or hemorrhagic complications was 4.8%. Cost analysis estimated savings of $7730.12 per procedure. CONCLUSION: This study suggests that the Care Hotel model is a safe, feasible, and cost-effective option for carefully selected patients undergoing elective neuroendovascular interventions. Adherence to discharge readiness criteria and meticulous patient selection are critical to minimizing complications and readmissions.

OBJECTIVE Spinal cord cavernous malformations (SCCMs) are rare vascular malformations with a capricious prognosis. Given the eloquent nature of the spinal cord, considerable surgical morbidity may be encountered. Therefore, conservative management has emerged as a valid alternative, especially for incidental lesions diagnosed on ubiquitous imaging. The aim of this systematic review and meta-analysis was to evaluate the safety and efficacy of surgical versus conservative management of SCCMs. METHODS Following PRISMA guidelines, this study included articles published in full-text form comparing the outcomes following conservative and surgical management of SCCMs. Collected variables included the total number of patients, spine level, resection, myelotomy, follow-up duration, bleeding, motor weakness, pain, bladder and/or bowel dysfunction, and neurological improvement or deterioration after discharge. The primary outcome of interest was long-term functional outcome. RESULTS Eleven articles comprising 515 patients were included, of whom 343 (66.6%) underwent resection and 172 (33.4%) were managed conservatively. Patients who underwent surgery were more likely to have preoperative motor deficits, hemorrhagic episodes, and bladder and/or bowel dysfunction, indicating increased disease severity. Resection was associated with significantly improved long-term functional outcomes (OR 3.27, 95% CI 1.72–6.24) compared with conservative management. There was no significant difference between the two groups regarding odds of long-term clinical deterioration (OR 1.03, 95% CI 0.35–3.03). However, the risk of hemorrhagic episodes during follow-up was higher in the conservative group (17.3%) compared with the surgical group (1.69%). The odds of hemorrhage during follow-up were lower in the surgical group, although not statistically significant (OR 0.24, 95% CI 0.05–1.05). CONCLUSIONS This study highlights that while surgical management of SCCMs is associated with better long-term functional outcomes and reduced risk of recurrent hemorrhage, treatment decisions must be carefully tailored to the individual patient, particularly given the potential risks associated with surgery. Conservative management, although less invasive, carries a nonnegligible risk of hemorrhage during follow-up, warranting close monitoring. These findings parallel management strategies used for brainstem cavernomas, for which surgery is reserved for cases with low surgical risk and worsening neurological symptoms. However, the limitations of current data, including selection bias and heterogeneity in reporting, emphasize the need for a multi-institutional registry to better define the natural history of SCCMs and inform future management strategies.

OBJECTIVE Tobacco smoking is among the factors known to significantly augment the risk of untreated intracranial aneurysm (IA) growth and rupture. Smoking appears to have a variable effect on different endovascular treatment modalities. The impact of smoking on the safety, efficacy, and outcomes of Woven EndoBridge (WEB) device use for wide-neck IAs has not been evaluated. This study aimed to investigate the outcomes of WEB devices by smoking status. METHODS A retrospective multicenter analysis was conducted on the data of patients from 36 sites worldwide treated with the WEB device for intracranial saccular aneurysms. Patients were stratified based on smoking status (current, former, and never smokers). The Student t-test and chi-square test were performed for continuous and categorical variables, respectively. Multivariable logistic regression was used to adjust for confounders. RESULTS Of 1376 patients with available smoking status, 504 were current smokers, 358 were former smokers, and 514 were never smokers. Upon adjusting for significant confounders, no association was found between smoking and recurrence outcomes (OR 1.39, 95% CI 0.69–2.80; p = 0.36), thromboembolic and hemorrhagic complications, and mortality among IAs treated with the WEB device. There was no statistically significant difference in outcomes between former and never smokers (OR 1.23, 95% CI 0.70–2.18; p = 0.46). The location of aneurysms differed between smoking groups, with former smokers having more anterior circulation aneurysms compared with current and never smokers (99.0% vs 96.9% vs 95.3%; p = 0.01). In terms of clinical symptoms, headache and dizziness were more common in the never smokers compared with current and former smokers (13.9% vs 8.9% vs 7.7%, p = 0.01). CONCLUSIONS This large-scale study suggests no significant correlation between smoking and the recurrence of IAs treated with the WEB device. Biological studies are warranted to better understand the biological impact of smoking on the growth and rupture of treated IAs.