Search Results (5)

Introduction/Objectives: Wall irregularity is a known risk factor in the evaluation of intracranial aneurysms, but the prognostic value of its subtypes remains unclear. Materials and methods: In this retrospective single-center cross-sectional study (2023–2025), we reviewed consecutive adult patients with intracranial aneurysms. Morphology was classified as daughter sac, multilobulated, or complex irregularity. We compared rupture status and calculated PHASES, ELAPSS, and UIATS scores. Principal Component Analysis (PCA), and logistic and linear regression were applied. Results: A total of 180 patients with 180 index aneurysms were included; mean age was 67.2 ± 12.1 years, and 72.2% were women. Overall, 43.3% of aneurysms were irregular, specifically: daughter sac (25.0%), multilobulated (36.1%), and complex irregularity (11.1%). SAH occurred in 40 patients (22.2%). Ruptured aneurysms had larger maximum diameter, size ratio, and aspect ratio (all p < 0.0001), plus higher 5-year PHASES (p = 0.0091) and ELAPSS growth scores (p < 0.0001). PCA identified three clusters with differing 5-year rupture risks; Cluster 3 had the highest risk (5.71 ± 5.25%) and was characterized by a higher proportion of daughter sac and multilobulated morphology (p = 1.65 × 10⁻⁷ and 8.80 × 10⁻¹⁶). Linear models showed each irregular subtype was associated with significantly larger aneurysm size. Conclusions: Irregular wall patterns were common and associated with larger aneurysm dimensions and higher risk scores. These findings support further investigation of refined morphological descriptors in rupture risk stratification. Full article

Background/Objectives: Risk-stratification tools, including the PHASES, UIATS, and ELAPSS, are commonly used to guide management of incidentally detected unruptured intracranial aneurysms (UIAs), but their predictive accuracy in real-world settings remains unclear. This study evaluated how these scores would have advised treatment in patients who subsequently presented with aneurysmal subarachnoid hemorrhage (aSAH). Methods: We retrospectively analyzed adults treated for aSAH at Copernicus Memorial Hospital (Łódź, Poland) between January 2022 and June 2024. For each ruptured aneurysm, we calculated PHASES (5-year rupture risk), UIATS recommendation, and ELAPSS (5-year growth risk) as if the lesion had been detected incidentally. Identical assessments were performed for UIAs that remained unruptured. Discrimination for rupture was evaluated using receiver-operating characteristic analysis (AUC). Results: Of 180 aneurysms (mean age 66.9 ± 11.3 years), 103 (57%) were ruptured. Patients with ruptured aneurysms were significantly older (69.9 vs. 64.0 years; p = 0.003), while sex, hypertension, smoking, and aneurysm morphology did not differ significantly. UIATS more frequently favored conservative management in ruptured aneurysms (56.3% vs. 39.0%; p = 0.046). PHASES (1.6% vs. 1.6%) and ELAPSS (3-year: 14.5% vs. 12.6%; 5-year: 22.6% vs. 20.0%) showed no significant differences between groups. Age was the only independent predictor of rupture (OR = 1.05/year; p < 0.001). The model’s cross-validated AUC was 0.731. Conclusions: Most ruptured aneurysms would not have been recommended for treatment based on UIATS. PHASES, ELAPSS, and UIATS did not reliably discriminate between ruptured and unruptured aneurysms, emphasizing the need for more precise and individualized risk assessment tools. Full article

Objectives: The increasing incidence of unruptured intracranial aneurysms (UIAs) has led to significant demands on neurovascular boards. Large language models (LLMs), such as ChatGPT-4, ChatGPT-3.5, Claude, and Atlas GPT, have emerged as tools to support clinical decision-making. This study compares treatment recommendations from these AI models with those of an interdisciplinary neurovascular board to evaluate their accuracy and alignment. Methods: We retrospectively included all 57 patients with UIAs discussed by the neurovascular board in 2023. The board’s consensus decision served as the reference standard. Key clinical and radiographic data, including PHASES, ELAPSS, and UIATS scores, were provided to the AI models. Each model was tasked with recommending either conservative or operative management and specifying the treatment modality (clipping, coiling, flow diverter, or WEB device/flow diverter) where appropriate. AI model recommendations were compared with the board’s decisions for management and the specific treatment modality of the UIA. Results: ChatGPT-4 achieved the highest accuracy in correctly predicting conservative or operative management (89%) and specific treatment types (73%), followed by Atlas GPT (74% accuracy in conservative/operative decisions and 55% accuracy in specific treatment types), Claude (70% accuracy in conservative/operative decisions and 50% accuracy in specific treatment types), and ChatGPT-3.5 (82% accuracy in conservative/operative decisions and 27% accuracy in specific treatment types). ChatGPT-3.5 displayed a strong preference for clipping (94.3%). ELAPSS scores significantly influenced AI recommendations and decision-making, particularly for ChatGPT-4 and ChatGPT-3.5. Follow-up recommendations for conservative management were shorter among AI models, with Claude suggesting the shortest interval (7.72 months) compared to the neurovascular board’s 13.36 months. Conclusions: AI models, particularly ChatGPT-4, align closely with expert neurovascular board decisions and offer promising support for initial clinical decision-making, particularly in resource-limited settings. However, interdisciplinary neurovascular boards remain unreplaceable for UIA management, and AI should be viewed as a complementary tool. The observed improvement from ChatGPT-3.5 to ChatGPT-4 underscores the rapid evolution of AI technology, and further advancements are expected to enhance both performance and accuracy in the future. Full article

Background: Treatment decisions for unruptured intracranial aneurysms (UIAs) pose a challenge for neurosurgeons, prompting the development of clinical scales assessing hemorrhage risk to provide management guidance. This study compares recommendations from the PHASES and UIA treatment scores (UIATS) applied to anterior communicating artery (AComA) UIAs against real-world management. Methods: While UIATS recommends management, for PHASES, an aneurysm with score of 10 or more was considered “high-risk”. Analysis involved assessing the concordance in each group alongside comparison to real-word management. Results: Among 129 patients, 46.5% were observed and 53.5% were treated. PHASES scores were significantly higher in the treatment group (p = 0.00002), and UIATS recommendations correlated with real-world decisions (p < 0.001). We observed no difference in the frequencies of UIATS recommendations between high- and low-risk groups. When comparing the UIATS and PHASES, 33% of high-risk aneurysms received a UIATS conservative management recommendation. In 39% of high-risk aneurysms, the UIATS recommendation was not definitive. Conversely, 27% of low-risk aneurysms obtained a UIATS UIA repair recommendation. Overall, concordance between PHASES and UIATS was 32%. Conclusions: Significant discordance in therapeutic suggestions underscores the predominant influence of center experience and individual assessments. Future studies should refine and validate decision-making strategies, potentially exploring alternative applications or developing tailored scales. Full article

The increasing number of incidental intracranial aneurysms creates a dilemma of which aneurysms to treat and which to observe. Clinical scoring systems consider risk factors for aneurysm rupture however objective parameters for assessment of aneurysms stability are needed. We retrospectively analysed contrast enhancing behaviour of un-ruptured aneurysms in the black blood magnetic resonance imaging (MRI) in N=71 patients with 90 aneurysms and assessed correlation between aneurysm wall contrast enhancement (AWCE) and aneurysm anatomy and clinical scoring systems. AWCE is associated with aneurysm height and height to width ratio in ICA aneurysms. AWCE is correlated to larger aneurysms in every anatomical location evaluated. However the mean size of the contrast enhancing aneurysms is significantly different between anatomical localizations indicating separate analyses for every artery. Clinical scoring systems like PHASES and UIATS correlate positively with AWCE in black blood MRI. MRI aneurysm wall contrast enhancement is a positive predictor for aneurysm instability and should be routinely assessed in follow up of incidental aneurysms. Aneurysms smaller than 7 mm with AWCE should be followed closely with focus on growth, as they may be prone to growth and rupture. Full article