RISC Software (Austria)

In recent years, the integration of ethical values into higher education has gained substantial recognition. This study investigated the relationship between ethical values and academic achievement among university students, focusing on six core dimensions: trustworthiness, respect, responsibility, fairness, caring, and citizenship. Data were collected using self-assessment and peer-assessment instruments and analyzed through a quantitative survey design. Descriptive statistics revealed a moderate to high prevalence of ethical values from both self-perceived and peer-reported perspectives. Independent samples t-test results indicated significant differences between self and peer assessments for trustworthiness, respect, and responsibility, while no significant differences emerged for fairness, caring, and citizenship. Regression analysis further identified responsibility and caring as significant predictors of academic achievement. These findings underscore the pivotal role of students’ ethical self-concept—particularly in terms of responsibility and empathy—in fostering academic success. The study recommends embedding character education into higher education curricula and adopting pedagogical frameworks that promote both cognitive excellence and ethical development.

IntroductionThe Anterior Communicating Artery complex (AComA) is one of the most common intracranial aneurysms locations. Accurate rupture risk assessment in patients with cerebral aneurysms is essential for optimizing treatment decisions. Computational fluid dynamics has significantly advanced insight into aneurysmal hemodynamics. Many studies concentrate predominantly on blood flow patterns, frequently neglecting the biomechanical properties of the aneurysm wall. Fluid-structure interaction analysis combines hemodynamic behavior with wall mechanics, potentially facilitating a more thorough evaluation of rupture risk assessment.MethodsIn this study, we employed advanced techniques to investigate several single and composite parameters to predict the rupture risk of AComA aneurysms in a cohort of 150 patients treated at the Kepler University Hospital in Linz, Austria. For this reason, clinical, morphological, hemodynamic, and structural mechanical parameters were assessed.ResultsA subsequent workflow analysis, consisting of comparative analysis, collinearity analysis, predictive modeling, composite parameter, performance evaluation, and internal threshold validation, revealed the Gaussian curvature GLN (AUC = 0.91) with a sensitivity of 0.93 and specificity of 0.83 as a best-performing single parameter for aneurysm rupture prediction. Composite parameters like WGD (combination of wall shear stress, Gaussian curvature, and wall displacement) achieved an AUC of 0.89, and WG (combination of wall shear stress and Gaussian curvature) an AUC of 0.88. An internal validation with 25 independent ruptured aneurysms was performed, and the previous results were confirmed with very high sensitivity values of 0.92 for GLN.ConclusionOur findings indicate that the investigated morphological, hemodynamic, and structural, mechanical parameters could provide a potential tool for evaluating rupture risk for AComA aneurysms. The single morphological parameter GLN offers, followed by composite parameters WGD and WG, excellent prediction power for the aneurysm rupture state, as confirmed by internal validation. Further studies are warranted to evaluate the prospective clinical application of these parameters.

Applying Quantum Machine Learning (QML) to high-resolution image classification is a significant challenge, typically requiring extensive classical pre-processing. This work proposes a QML model that uses a novel quanvolution-pooling to directly extract features from high-resolution images, eliminating the need for classical pre-processing with fixed or learnable operations. By utilizing a compact configuration of only hardware-native gates, our approach achieves a high degree of inherent noise resilience. We also present the first LIME-based explainability study of QML models for high-resolution image classification tasks. Our approach was evaluated on three datasets under both noise-free and noisy simulations, exhibiting minimal performance degradation in the presence of noise. Explainability analysis revealed that the model consistently focused on clinically relevant regions, even under noisy conditions. These findings demonstrate the feasibility and robustness of QML models for high-resolution image classification.

Nowadays, surgical treatment of cerebral aneurysms remains one of the most demanding disciplines in neurosurgery. The increasing shift toward endovascular interventions leads to a decline in open surgical cases. This fact leaves residents and young neurosurgeons with fewer training opportunities and limited to complex and high-risk aneurysms. There is a growing need for realistic simulation tools to enhance neurosurgical training and preoperative planning. We developed and externally validated a patient-specific mixed-reality simulator for cerebral aneurysm clipping, during the research project "Medical EDUcation in Surgical Aneurysm Clipping (MEDUSA)". Our approach combines physical phantoms of the skull and brain tissue with virtual intracranial blood vessels, including a virtual intracranial aneurysm. Real surgical instruments provide an immersive training environment featuring integrated blood flow simulation for evaluating clipping strategies. A life-sized skull with silicone brain lobes is mounted in a standard neurosurgical head clamp. Optical tracking synchronizes the position of a real clip applier and an emulated surgical microscope with the corresponding virtual environment, allowing true mixed-reality interaction. After aneurysm clipping, blood flow is automatically simulated to assess residual aneurysms or stenoses of the parental vessels. We conducted an external validation with 40 neurosurgeons at two international events. Participants completed a 32-item questionnaire evaluating face and content validity on a 5-point Likert scale. Participants' surgical experience ranged from novice to expert (> 15 years). Average ratings for simulator realism and educational value were high, with mean scores between 3.13 and 4.25. The highest ratings were for the blood flow simulation (4.25) and the simulator's potential for preoperative planning (4.20). Most participants agreed that the physical and virtual components were valuable and that the simulator should be integrated into neurosurgical training and standard surgical workflows. Our mixed-reality simulator achieved robust face and content validity among a diverse group of neurosurgeons. Combining real surgical instruments with a deformable virtual aneurysm model, including blood flow simulation, offers a high level of realism and immediate objective feedback.Supplementary InformationThe online version contains supplementary material available at 10.1007/s10143-025-03846-x.

BackgroundChronic posthemorrhagic hydrocephalus often arises following spontaneous subarachnoid hemorrhage (SAH). Timely identification of patients predisposed to develop chronic shunt-dependent hydrocephalus may significantly enhance clinical outcomes. MethodsWe performed an analysis of 510 SAH-patients treated at our institution between 2013 and 2018. Clinical and radiological variables, including age, sex, Hunt & Hess grade, Fisher-Score, external ventricular drainage placement, central nervous system infection, aneurysm characteristics, and treatment modalities, were evaluated. Supervised machine learning models, trained and compared using Python and scikit-learn, were employed to predict chronic shunt-dependent hydrocephalus. Model performance was rigorously assessed through repeated cross-validation. To facilitate transparency and collaboration, we publicly released the dataset and code on GitHub (https://github.com/RISCSoftware/shuntclf) and developed an interactive web application (https://huggingface.co/spaces/risc42/shuntclf). ResultsAmong the evaluated machine learning models, logistic regression exhibited superior performance, with an AUC-ROC of 0.819 and an AUC-PR of 0.482, along with the highest F1 score of 0.473. Although the balanced accuracy scores of the models were generally proximate, ranging from 0.735 to 0.764, logistic regression consistently outperform others in key metrics such as AUC-ROC and AUC-PR. Conversely, female gender and absence of aneurysm within the anterior communicating artery were associated with reduced shunt requirement likelihood. ConclusionMachine learning models, including logistic regression, demonstrate strong predictive capability for early chronic shunt-dependent hydrocephalus following spontaneous SAH, which may potentially contribute to more timely shunt placement interventions. This predictive capability is supported by our web interface, which simplifies the application of these models, aiding clinicians in efficiently determining the need for shunt placement.