Advancing aneurysm management: the potential of AI and machine learning in enhancing safety and predictive accuracy.

Cerebral aneurysm rupture, the predominant cause of non-traumatic subarachnoid hemorrhage, underscores the need for effective treatment and early detection methods. A study in Neurosurgical Review compared microsurgical clipping to endovascular therapy in 130 patients with middle cerebral artery (MCA) aneurysms, finding significantly fewer serious adverse events (SAEs) and neurological complications in the endovascular group. This suggests endovascular therapy's superiority in safety and reducing complications for MCA aneurysm patients. Furthermore, a systematic review and meta-analysis assessed the diagnostic accuracy of AI algorithms in detecting cerebral aneurysms, revealing a high sensitivity but notable false-positive rates, indicating AI's potential while highlighting the need for further validation. Machine learning algorithms also showed promise in predicting cerebral aneurysm rupture risk, demonstrating reasonable sensitivity and specificity. Additionally, AI-based radiomics models are advancing rapidly, offering enhanced predictive accuracy and personalized treatment planning by analyzing imaging data to identify features indicative of aneurysm conditions. Collectively, these findings emphasize the advantages of endovascular therapy for MCA aneurysms and the emerging role of AI and machine learning in improving early detection and personalized management of cerebral aneurysms.

Application of 3D printing to create an in vitro aneurysm rupture model.

Currently available benchtop (in vitro) aneurysm models are inadequate for testing the efficacy of endovascular device treatments. Specifically, current models do not represent the mechanical instability of giant aneurysms (defined as aneurysms with 25 mm in height or width) and do not predictably rupture under simulated physiological conditions. Hence, in vitro aneurysm models with biomechanically relevant material properties and a predictable rupture timeframe are needed to accurately assess the efficacy of new medical device treatment options. Understanding the material properties of an aneurysm (e.g., shear and compression modulus) as it approaches rupture is a crucial step toward creating a pathologically relevant and sophisticated in vitro aneurysm rupture model. We investigated the change in material properties of a blood vessel, via enzymatic treatment, to simulate the degradation of an aneurysm wall and used this information to create a sophisticated aneurysm rupture model using the latest in additive manufacturing technologies (3D printing) with tissue-like materials. Mechanical properties (shear and compression modulus) of swine carotid vessels were evaluated before and after incubation with collagenase D enzyme (30 min at 37°C) to simulate the effect of biochemical activity on aneurysm wall approaching rupture compared to control vessels (untreated). Mechanical strength of a soft and flexible 3D-printed material (VCA-A30: 30 shore A hardness) was tested for comparison to these arterial vessels. This material was then used to create spherical shaped, giant-sized (25-mm diameter) aneurysm phantoms and were run under neurovascular pressures (120/80 ± 5 mmHg), beats per minute (BPM = 70) and flows representing the middle cerebral artery [MCA: 142.67 (±20.13) mL/min] using a blood analog [3.6 (±0.4) cP viscosity] with non-Newtonian shear-thinning properties. The shear modulus of swine carotid vessel before treatment was 12.2 (±2.7) KPa and compression modulus was 663.5 (±111.6) KPa. After enzymatic treatment by collagenase D, shear modulus of animal tissues reduced by 33% (p-value = .039) while compression modulus remained statistically unchanged (p-value = .615). Control group (untreated vessels) showed minimal reduction (13%, p-value = .226) in shear modulus and 78% increase (p-value = .034) in compression modulus. The shear modulus of the 3D-printed material was 228.59 (±24.82) KPa while its compression modulus was 668.90 (±13.16) KPa. This material was used to prototype a sophisticated in vitro giant aneurysm rupture model. When subjected to physiological pressures and flow rates, the untreated models consistently ruptured at ~12 min. These results indicate that aneurysm rupture can be recreated consistently in a benchtop in vitro model, utilizing the latest 3D-printed materials, connected to a physiologically relevant programmable pump. Further studies will investigate the optimization of various aneurysm dome thickness regions within the aneurysm, with tunable rupture times for comparison of aneurysm device deployment and benchtop controls based on the measurable effects of pressure and flow changes within the aneurysm models. These optimized in vitro rupture models could ultimately be used to test the efficacy of device treatment options and rupture risk by quantifying specific device rupture times and aneurysm rupture position.

Ruptured giant splenic artery aneurysm with an exceptional concurrent gastric and transverse colonic fistula: A rare case report.

INTRODUCTION: Splenic artery aneurysm (SAA) is a focal dilation of the splenic artery with varying etiologies including atherosclerosis, arteritis, or trauma. Giant SAAs with a diameter of 10 cm is rare and can lead to severe complications like rupture and fistulas. Therefore, an accurate and timely diagnosis and treatment are important. PATIENT CONCERNS: A 50-year-old male presented with acute epigastric pain and hemorrhagic shock. Considering his symptoms and examination, ultrasound, multi-slice computed tomography and digital subtraction angiography results, a ruptured giant splenic artery aneurysm complicated with an exceptional gastric and transverse colonic fistula was suspected. DIAGNOSIS: Ruptured giant splenic artery aneurysm. INTERVENTIONS: Left anterolateral thoracotomy to control the severe aortic bleeding just above the diaphragm, aneurysmectomy, splenectomy, and closing the gastric and transverse colon perforations. OUTCOMES: Multi-slice computed tomography demonstrated the presence of splenic artery aneurysm in the distal third measuring (10 × 12 cm) in diameter with a true lumen measuring (7 × 3.5 cm) and a large hematoma extending to the greater and lesser gastric curvature. Intraoperatively, a large pulsating mass was detected occupying the epigastrium and the left hypochondrium with severe adhesions with the stomach and transverse colon. CONCLUSION: Giant SAA with a diameter of 10 cm is rare and is associated with severe complications. Therefore, successful treatment of splenic artery aneurysms involves prompt diagnosis, immediate surgical intervention to control bleeding, and tailored approaches like thoracotomy to control the thoracic aorta for better hemodynamic stabilization, aiming to eliminate the aneurysm and reduce complications effectively.

Hemodynamic differences determining rupture and non-rupture in middle cerebral aneurysms after growth.

BACKGROUND AND PURPOSE: Intracranial aneurysm growth is a significant risk factor for rupture; however, a few aneurysms remain unruptured for long periods, even after growth. Here, we identified hemodynamic features associated with aneurysmal rupture after growth. MATERIALS AND METHODS: We analyzed nine middle cerebral artery aneurysms that grew during the follow-up period using computational fluid dynamics analysis. Growth patterns of the middle cerebral artery aneurysms were divided into homothetic growth (Type 1), de novo bleb formation (Type 2), and bleb enlargement (Type 3). Hemodynamic parameters of the four ruptured aneurysms after growth were compared with those of the five unruptured aneurysms. RESULTS: Among nine aneurysms (78%), seven were Type 1, one was Type 2, and one was Type 3. Three (43%) Type 1 aneurysms ruptured after growth. Maximum oscillatory shear index after aneurysmal growth was significantly higher in ruptured Type 1 cases than in unruptured Type 1 cases (ruptured vs. unruptured: 0.455 ± 0.007 vs. 0.319 ± 0.042, p = 0.003). In Type 1 cases, a newly emerged high-oscillatory shear index area was frequently associated with rupture, indicating a rupture point. Aneurysm growth was observed in the direction of the high-pressure difference area before enlargement. In Types 2 and 3 aneurysms, the maximum oscillatory shear index decreased slightly, however, the pressure difference values remain unchanged. In Type 3 aneruysm, the maximum OSI and PD values remained unchanged. CONCLUSIONS: This study suggests that hemodynamic variations and growth pattern changes are crucial in rupture risk determination using computational fluid dynamics analysis. High-pressure difference areas may predict aneurysm enlargement direction. Additionally, high maximum oscillatory shear index values after enlargement in cases with homothetic growth patterns were potential rupture risk factors.

Prevalence of ruptured small and very small aneurysms: a retrospective single-centre study.

AIM OF STUDY: To retrospectively assess the occurrence and consequences of subarachnoid haemorrhages (SAH) caused by ruptured intracranial aneurysms (RIA), particularly focusing on the treatment outcomes of small aneurysms treated with either endovascular embolisation or surgical intervention. MATERIAL AND METHODS: We retrospectively analysed data from 408 patients (144 males and 264 females) who were hospitalised between 2013 and 2022 at the Department of Neurosurgery and Neurology in University Hospital Nr 2 in Bydgoszcz, Poland. Clinical conditions at admission, assessed using the Glasgow Coma Scale, Hunt-Hess scale (H-H), modified Rankin scale (mRS), as well as age and sex, were recorded. Additionally, aneurysm data including size, localisation, and the method and outcome of endovascular or surgical treatment were examined. RESULTS: Among the 408 patients hospitalised due to SAH, the most common localisation of the 375 RIAs was the anterior communicating artery (AcomA) complex (111 cases, 29.6%), followed by the medial cerebral artery (MCA) (95 cases, 25.3%), internal carotid artery (ICA) (94 cases, 25%), and the vertebrobasilar complex (consisting of the basilar artery (BA) - 25 cases, vertebral artery (VA) - 13 cases, anterior inferior cerebellar artery (AICA) - one case, and posterior inferior cerebellar artery (PICA) - four cases), which accounted for 43 SAH cases (11.46%). In 33 cases, neither RIA nor a haemorrhage source was identified, or arteriography showed no cerebral arteries contrast flow. Among the examined group of 375 RIAs, 45 (12%) were microaneurysms (≤ 3 mm), 35 (9%) were small aneurysms (3 ≤ 5 mm), 89 (24%) were medium-sized (5 ≤ 7 mm), and 151 (40%) were large aneurysms (> 7 mm), serving as the source of SAH. A better outcome was significantly associated with lower initial H-H grade (p < 0.001), higher GCS (p < 0.001), lower mRS at admission (p < 0.001), younger age (p < 0.001), smaller size (≤ 3 mm) (p < 0.001), and endovascular treatment (p < 0.001). CONCLUSIONS: In this series, over 21% of patients suffered from SAH resulting from ruptured small aneurysms (≤ 5 mm), with 12% specifically attributed to ruptured very small aneurysms (≤ 3 mm), despite large aneurysms (> 7 mm) being the most prevalent source of bleeding in 40% of cases. A worse prognosis was primarily associated with the severity of SAH, reflected in poorer clinical status at admission and older age. Endovascular embolisation was found to be effective and associated with better outcomes compared to surgical treatment.

Clinical relevance of critical plasma homocysteine levels in predicting rupture risk for small and medium-sized intracranial aneurysms.

Plasma homocysteine (Hcy) has been globally recognized as an independent risk factor for various neurovascular diseases. In this study, the authors investigated the relationship between critical Hcy concentration and the risk of rupture in intracranial aneurysms (IAs). This study collected data from 423 patients with both ruptured and unruptured IAs. We compared demographic data, vascular rupture risk factors, and laboratory test results between the two groups. Multivariable logistic regression analysis was employed to determine the correlation between critical plasma Hcy levels and the risk of rupture in small to medium-sized IAs. A total of 330 cases of ruptured intracranial aneurysms (RIA) and 93 cases of unruptured intracranial aneurysms (UIA) were included. Univariate analysis revealed statistically significant differences between the ruptured and unruptured groups in terms of hypertension, hyperlipidemia, plasma Hcy levels, and IA morphology (all P < 0.05). Multivariable logistic regression analysis indicated that hypertension (odds ratio [OR] 0.504; 95% confidence interval [CI] 0.279-0.911; P = 0.023), hyperlipidemia (OR 1.924; 95% CI 1.079-3.429; P = 0.027), and plasma Hcy levels (OR 1.420; 95% CI 1.277-1.578; P < 0.001) were independently associated with the rupture of small to medium-sized IAs, all with statistical significance (P < 0.05). Our study suggests that critical plasma Hcy levels are an independent risk factor for increased rupture risk in small to medium-sized intracranial aneurysms. Therefore, reducing plasma Hcy levels may be considered a valuable strategy to mitigate the risk of intracranial vascular abnormalities rupture and improve patient prognosis.

A case report: Treatment of a patient with ruptured middle cerebral aneurysm in the second trimester of pregnancy.

BACKGROUND: To summarize the clinical experience of intracranial aneurysm clipping in the treatment of ruptured intracranial aneurysms in the second trimester of pregnancy. METHODS: A case of ruptured middle cerebral aneurysm in the second trimester of pregnancy was reported. Craniotomy and aneurysm clipping were performed at 24 weeks of pregnancy, and fetal preservation was continued after the operation. RESULTS: The prognosis of the parturient was good and the skull was missing on the operative side. A healthy baby boy was delivered by cesarean section 2 months after the operation, and skull repair was performed 4 months after the operation. During the follow-up for 1 year, the mother and son were healthy and no obvious sequelae were found. CONCLUSION: Ruptured intracranial aneurysm hemorrhage in mid-pregnancy is a rare and critical case. Summarizing the corresponding clinical experience will help to have a reference plan for the next time when facing a similar situation, and it will help to treat critically ill patients. The treatment of ruptured intracranial aneurysm in mid-pregnancy requires multidisciplinary collaboration, and cranial aneurysm clamping + fertility preservation can reduce the impact of radiation on the fetus and improve the prognosis for both the mother and the fetus.

Outcomes following surgical clipping of re-ruptured previously untreated intracranial aneurysms.

Re-rupture of untreated intracranial aneurysm is a potentially life-threatening condition. Despite tremendous advances in the diagnosis and treatment of intracranial aneurysms, such events are not rare and continue to pose a management dilemma. In this study, we examined the clinical, radiological and treatment details of patients who underwent microsurgical clipping for re-rupture of previously untreated intracranial aneurysms. Re ruptures were categorized as early and late re ruptures (< or > 7 days of inter ictus interval respectively). Modified Rankin Score (mRS) was used for functional outcome assessment and logistic regression analysis was used to test the predictors of long-term outcome. Re-ruptured intracranial aneurysms comprised 5% (n = 32/637) of the aneurysm clippings done at our center in this time span. The mean mRS score at discharge and at last follow-up were 3 and 3.04 respectively. Twenty-four (75%) patients were alive at a mean follow-up of 36 months. Early re-ruptures were associated with worse mean mRS scores at discharge (3.9 vs 2.5, p = 0.03) including the perioperative deaths (n = 4, 12.5%). The functional status at discharge and a poor preoperative clinical grade predicted a poor long-term outcome. Therefore, the long-term outcomes are primarily dependent on the short-term outcomes and to a lesser extent, the clinical grade at presentation. Those presenting with poor preoperative clinical grade, especially in the setting of an early re rupture, have a very poor prognosis and do not benefit from surgery.

On flow fluctuations in ruptured and unruptured intracranial aneurysms: resolved numerical study.

Flow fluctuations have emerged as a promising hemodynamic metric for understanding of hemodynamics in intracranial aneurysms. Several investigations have reported flow instabilities using numerical tools. In this study, the occurrence of flow fluctuations is investigated using either Newtonian or non-Newtonian fluid models in five patient-specific intracranial aneurysms using high-resolution lattice Boltzmann simulation methods. Flow instabilities are quantified by computing power spectral density, proper orthogonal decomposition, and fluctuating kinetic energy of velocity fluctuations. Our simulations reveal substantial flow instabilities in two of the ruptured aneurysms, where the pulsatile inflow through the neck leads to hydrodynamic instability, particularly around the rupture position, throughout the entire cardiac cycle. In other monitoring points, the flow instability is primarily observed during the deceleration phase; typically, the fluctuations begin just after peak systole, gradually decay, and the flow returns to its original, laminar pulsatile state during diastole. Additionally, we assess the rheological impact on flow dynamics. The disparity between Newtonian and non-Newtonian outcomes remains minimal in unruptured aneurysms, with less than a 5% difference in key metrics. However, in ruptured cases, adopting a non-Newtonian model yields a substantial increase in the fluctuations within the aneurysm sac, with up to a 30% higher fluctuating kinetic energy compared to the Newtonian model. The study highlights the importance of using appropriate high-resolution simulations and non-Newtonian models to capture flow fluctuation characteristics that may be critical for assessing aneurysm rupture risk.

Revolutionizing Aneurysm detection: The role of artificial intelligence in reducing rupture rates.

Cerebral aneurysms, affecting 2-5% of the global population, are often asymptomatic and commonly located within the Circle of Willis. A recent study in Neurosurgical Review highlights a significant reduction in the annual rupture rates of unruptured cerebral aneurysms (UCAs) in Japan from 2003 to 2018. By analyzing age-adjusted mortality rates of subarachnoid hemorrhage (SAH) and the number of treated ruptured cerebral aneurysms (RCAs), researchers found a substantial decrease in rupture rates-from 1.44 to 0.87% and from 0.92 to 0.76%, respectively (p < 0.001). This 88% reduction was largely attributed to improved hypertension management. Recent advancements in artificial intelligence (AI) and machine learning (ML) further support these findings. The RAPID Aneurysm software demonstrated high accuracy in detecting cerebral aneurysms on CT Angiography (CTA), while ML algorithms showed promise in predicting aneurysm rupture risk. A meta-analysis indicated that ML models could achieve 83% sensitivity and specificity in rupture prediction. Additionally, deep learning techniques, such as the PointNet + + architecture, achieved an AUC of 0.85 in rupture risk prediction. These technological advancements in AI and ML are poised to enhance early detection and risk management, potentially contributing to the observed reduction in UCA rupture rates and improving patient outcomes.

Primary decompressive craniectomy in patients with large intracerebral hematomas due to aneurysmal subarachnoid hemorrhage.

BACKGROUND: Decompressive craniectomy (DC) can alleviate increased intracranial pressure in aneurysmal subarachnoid hemorrhage patients with concomitant space-occupying intracerebral hemorrhage, but also carries a high risk for complications. We studied outcomes and complications of DC at time of ruptured aneurysm repair. METHODS: Of 47 patients treated between 2010 and 2020, 30 underwent DC during aneurysm repair and hematoma evacuation and 17 did not. We calculated odds ratios (OR) for delayed cerebral ischemia (DCI), angiographic vasospasm, DCI-related infarction, and unfavorable functional outcome (extended Glasgow Outcome Scale 1-5) at three months. Complication rates after DC and cranioplasty in the aneurysmal subarachnoid hemorrhage patients were compared to those of all 107 patients undergoing DC for malignant cerebral infarction during the same period. RESULTS: In DC versus no DC patients, proportions were for clinical DCI 37% versus 53% (OR = 0.5;95%CI:0.2-1.8), angiographic vasospasm 37% versus 47% (OR = 0.7;95%CI:0.2-2.2), DCI-related infarctions 17% versus 47% (OR = 0.2;95%CI:0.1-0.7) and unfavorable outcome 80% versus 88% (OR = 0.5;95%CI:0.1-3.0). ORs were similar after adjustment for baseline predictors for outcome. Complications related to DC and cranioplasty occurred in 18 (51%) of subarachnoid hemorrhage patients and 41 (38%) of cerebral infarction patients (OR = 1.7;95%CI:0.8-3.7). CONCLUSIONS: In patients with aneurysmal subarachnoid hemorrhage and concomitant space-occupying intracerebral hemorrhage, early DC was not associated with improved functional outcomes, but with a reduced rate of DCI-related infarctions. This potential benefit has to be weighed against high complication rates of DC in subarachnoid hemorrhage patients.

Strategies and outcomes of endovascular treatment of posterior inferior cerebellar artery aneurysms: a single center experience.

To explore safe and reliable strategies and outcomes of endovascular procedures in the treatment of posterior inferior cerebellar artery (PICA) aneurysms. Retrospectively reviewed and analyzed the cases of PICA aneurysms that undergone endovascular therapy from July 2017 through January 2022 in our neurosurgical center, as well as outcomes of long-term follow-up. Total 24 cases were enrolled. Majority of the PICA aneurysms (87.5%, 21/24) presented initially with subarachnoid hemorrhage (SAH) and only 3 cases were not ruptured when they were clinically diagnosed as PICA aneurysms. The patients were endovascularly given either aneurysm occlusion with selective coils (12 cases), embolization of aneurysms and parent arteries (7 cases: 3 cases with coils and 4 cases with Onyx liquid embolic agent), or stent-assisted coiling of the aneurysms (5 cases). One patient, who had comorbidity of intracranial hemorrhage and severe cerebral vasospasm, declined further post-surgery therapy, and discharged from the hospital with anticipation of poor outcome. The rest 23 patients were followed up for 3-24 months with a recurrence rate of 17.4% (4/23). Endovascular procedure of embolizing PICA aneurysms with selective coils or stent-assisted coils is feasible, safe, and reliable. Simplified embolization of the aneurysms or occlusion of the parent artery is recommended as the first choice for the ruptured and bleeding PICA aneurysms.

Bifurcation dissecting aneurysm: tips and tricks to differentiate from saccular aneurysm.

Bifurcations are a common site for saccular aneurysms, but rarely can be a site for dissecting aneurysms. Identification of these aneurysms is extremely important because the management plan depends on it. We describe a rare case of a ruptured dissecting aneurysm at the right ICA bifurcation in a pre-teen child which posed a diagnostic dilemma but ultimately was successfully managed with flow diversion.

Massive bleeding from an infected pseudoaneurysm in an arteriovenous graft that resulted in death: A case report.

We report an autopsy of a death due to a ruptured infected pseudoaneurysm; a man in his 70s was found dead with massive bleeding from the shunt of his right arm. Autopsy and pathological examination revealed that the cause of death was hemorrhagic shock due to rupture of an infected pseudoaneurysm. Ruptured aneurysms and pseudoaneurysm are a complication of dialysis, and death is rare because they are treated immediately on discovery. However, these ruptures often occur in non-medical facilities and could result in death if the patient does not have knowledge of first aid. Thus, patient education is important. Approximately only half of the deaths due to massive bleeding from a shunt are autopsied. In Japan, autopsies or partial autopsies are considered necessary to determine whether a bleeding was traumatic and to prevent medical errors from being overlooked.

Tailoring fenestrated aneurysm clips intraoperatively: Instant solution for a difficult problem.

The anterior communicating artery (AcoA) aneurysms represent the most complex aneurysms of the anterior circulation. For years, surgical challenges including the intricate anatomy and narrow surgical corridor have been overcome using supplementary techniques including extended craniotomies, wide opening of the cisterns, gyrus rectus resection and special clips like fenestrated clips. However, imaginative solutions such as intraoperative clip modification may be inevitable in particular cases for safe clipping. We retrospectively analyzed clinical records of two patients who required clip modification intraoperatively. Case #1 underwent microsurgical clipping of a ruptured, 4-mm AcoA aneurysm. Unfortunately, given the short distance between the two A2s, it was not possible to clip the aneurysm without a compromise to the contralateral A2 with the available shortest 3mm-fenestrated clip. We then used the clip modification technique intraoperatively by shortening the clip tips with mesh-plaque cutter and smoothening the remaining sharp ends using cautery sanding. Eventually, the aneurysm was clipped successfully with the modified-fenestrated clip. Post-clipping imagings confirmed complete occlusion of the aneurysm and patency of parent arteries. Case 2# underwent microsurgical clipping for a ruptured, 1-mm AcoA aneurysm. Like Case 1#, the initial clipping attempt with the available shortest 4mm-fenestrated clip failed given the excessive length of the tips. The patient, thus, required clip modification as described above. The aneurysm was then clipped successfully using the modified-fenestrated clip, protecting bilateral A2s. Post-clipping imagings demonstrated patency of parent arteries with no residual aneurysm filling. Clip modification seems to be an effective option in clipping the AcoA aneurysms when available clips are too long to secure them safely.

Coil embolization of the middle cerebral artery bifurcation aneurysms: Feasibility and durability.

OBJECTIVE: To evaluate the feasibility and durability of coil embolization for MCAB aneurysms by analyzing clinical and radiological results. METHODS: From January of 2008 to June of 2018, we treated a total of 1785 aneurysms using coil embolization. The aneurysms were treated by both coiling and stent-assisted coiling. Among these cases, 223 MCAB aneurysms were analyzed retrospectively. Clinical and radiological assessments were conducted at admission, after treatment, at discharge, and at last clinical follow-up. RESULTS: Coil embolization was performed on 223 MCAB aneurysms in 217 patients. Peri-procedural ischemic, hemorrhagic, and other complications within 30 days after coil embolization occurred at rates of 8.0 %, 8.0 %, and 2.0 %, respectively, in the ruptured group and at 2.9 %, 1.2 %, and 0 %, respectively, in the unruptured group. The overall morbidity and mortality rates associated with complications were 2.3 % and 2.0 %. The cumulative major recurrence rates were 5.1 % at 12 months, 7.1 % at 18 months, and 11.9 % at three years after coil embolization. The mean follow-up period was 33.27 ± 25.48 months. Independent risk factors for major recurrence after coil embolization for MCAB aneurysms were a ruptured aneurysm, initial incomplete occlusion, the aneurysm size, and the neck size. CONCLUSION: Coil embolization is a good alternative treatment option for MCAB aneurysms compared to surgical clipping. Considering the risk factors for major recurrence, the follow-up angiography should continue up to three years after coil embolization.

Predictors of Intrahospital Mortality in Aneurysmal Subarachnoid Hemorrhage after Endovascular Embolization.

Background and Objectives: Aneurysmal subarachnoid hemorrhage (ASAH) is defined as bleeding in the subarachnoid space caused by the rupture of a cerebral aneurysm. About 11% of people who develop ASAH die before receiving medical treatment, and 40% of patients die within four weeks of being admitted to hospital. There are limited data on single-center experiences analyzing intrahospital mortality in ASAH patients treated with an endovascular approach. Given that, we wanted to share our experience and explore the risk factors that influence intrahospital mortality in patients with ruptured intracranial aneurysms treated with endovascular coil embolization. Materials and Methods: Our study was designed as a clinical, observational, retrospective cross-sectional study. It was performed at the Department for Radiology, University Clinical Center Kragujevac in Kragujevac, Serbia. The study inclusion criteria were ≥18 years, admitted within 24 h of symptoms onset, acute SAH diagnosed on CT, aneurysm on DSA, and treated by endovascular coil embolization from January 2014 to December 2018 at our institution. Results: A total of 66 patients were included in the study-48 (72.7%) women and 18 (27.3%) men, and 19.7% of the patients died during hospitalization. After adjustment, the following factors were associated with in-hospital mortality: a delayed ischemic neurological deficit, the presence of blood in the fourth cerebral ventricle, and an elevated urea value after endovascular intervention, increasing the chances of mortality by 16.3, 12, and 12.6 times. Conclusions: Delayed cerebral ischemia and intraventricular hemorrhage on initial head CT scan are strong predictors of intrahospital mortality in ASAH patients. Also, it is important to monitor kidney function and urea levels in ASAH patients, considering that elevated urea values after endovascular aneurysm embolization have been shown to be a significant risk factor for intrahospital mortality.

A comprehensive investigation of morphological features responsible for cerebral aneurysm rupture using machine learning.

Cerebral aneurysms are a silent yet prevalent condition that affects a significant global population. Their development can be attributed to various factors, presentations, and treatment approaches. The importance of selecting the appropriate treatment becomes evident upon diagnosis, as the severity of the disease guides the course of action. Cerebral aneurysms are particularly vulnerable in the circle of Willis and pose a significant concern due to the potential for rupture, which can lead to irreversible consequences, including fatality. The primary objective of this study is to predict the rupture status of cerebral aneurysms. To achieve this, we leverage a comprehensive dataset that incorporates clinical and morphological data extracted from 3D real geometries of previous patients. The aim of this research is to provide valuable insights that can help make informed decisions during the treatment process and potentially save the lives of future patients. Diagnosing and predicting aneurysm rupture based solely on brain scans is a significant challenge with limited reliability, even for experienced physicians. However, by employing statistical methods and machine learning techniques, we can assist physicians in making more confident predictions regarding rupture likelihood and selecting appropriate treatment strategies. To achieve this, we used 5 classification machine learning algorithms and trained them on a substantial database comprising 708 cerebral aneurysms. The dataset comprised 3 clinical features and 35 morphological parameters, including 8 novel morphological features introduced for the first time in this study. Our models demonstrated exceptional performance in predicting cerebral aneurysm rupture, with accuracy ranging from 0.76 to 0.82 and precision score from 0.79 to 0.83 for the test dataset. As the data are sensitive and the condition is critical, recall is prioritized as the more crucial parameter over accuracy and precision, and our models achieved outstanding recall score ranging from 0.85 to 0.92. Overall, the best model was Support Vector Machin with an accuracy and precision of 0.82, recall of 0.92 for the testing dataset and the area under curve of 0.84. The ellipticity index, size ratio, and shape irregularity are pivotal features in predicting aneurysm rupture, respectively, contributing significantly to our understanding of this complex condition. Among the multitude of parameters under investigation, these are particularly important. In this study, the ideal roundness parameter was introduced as a novel consideration and ranked fifth among all 38 parameters. Neck circumference and outlet numbers from the new parameters were also deemed significant contributors.

Rupture risk of intracranial aneurysms: Comparison between small ruptured intracranial aneurysms and large unruptured intracranial aneurysms.

To compare the differences in clinical and morphological features between small ruptured intracranial aneurysms and large unruptured intracranial aneurysms to evaluate the risk factors for the rupture of IAs. The clinical data of 189 consecutive patients with 193 IAs were reviewed. The patients and IAs were divided into ruptured (<5 mm) and unruptured groups (>10 mm). The characteristics of the patients and the intracranial aneurysms (IAs) were compared between the 2 groups, and the risk factors for rupture of IAs were assessed using multiple logistic regression. Patient age (odds ratio [OR], 0.955), IA located at the internal carotid artery (ICA, OR, 0.202), irregular shape (OR, 0.083) and parent vessel diameter (OR, 0.426) were negatively correlated with the risk of IA rupture. IAs located at bifurcations (OR, 6.766) were positively correlated with the risk of IA rupture. In addition to the size of the IAs, regardless of IAs shape, other factors, such as younger age (<63.5 years), location at a bifurcation, IAs located at the ICA and a small parent vessel diameter (<3.25 mm), can influence the risk of IA rupture.