Archivio della ricerca della Scuola Superiore Sant'Anna
Not a member yet
26957 research outputs found
Sort by
Towards Trustworthy AI
No full textThe rapid advancements in AI, particularly in deep neural networks (DNNs), have prompted the research community to face complex
safety and security challenges, which must be carefully addressed to ensure the correct integration of AI algorithms into
human-centric systems. AI threats can range from intentionally crafted samples, such as adversarial perturbations or real-world
adversarial objects, to unexpected out-of-distribution samples. The presence of these threats raises numerous questions and
considerations about the security vulnerabilities and safety requirements of the models and applications under analysis. Accordingly,
it is crucial to thoroughly understand and design testing methodologies and mitigation strategies, taking into account specific
aspects and requirements of each application scenario
A Novel SCN5A Missense Variant Associated With Familial Non-Dilated Left Ventricular Cardiomyopathy
No full textCompounds for inhibiting the interaction of sars-cov2 with human protein ace2
No full textNovel compounds capable of blocking viral infections sustained by the SARS-Cov2 virus are provided. A method for preventing and/or treating infectious diseases caused by a virus involving administering the novel compounds is also provided
Hypergravity and ERK Inhibition Combined Synergistically Reduce Pathological Tau Phosphorylation in a Neurodegenerative Cell Model
No full textThis study evaluates the effects of hypergravity (HG) on a neurodegenerative model in vitro, looking at how HG influences Tau protein aggregation in Mouse Hippocampal Neuronal Cells (HT22) induced by neurofibrillary tangle seeds. Overall, 50× g significantly, synergistically, reduced the Tau aggregate Area when combined with ERK-inhibitor PD-0325901, correlating with decreased phosphorylation at critical residues pS262 and pS396. These findings suggest HG treatments may help mitigate cytoskeletal damage linked to Tau aggregation
Understanding the Importance of Feature Groups for Clinical Outcome Predictions with Machine Learning in Post-Stroke Robotic-Assisted Rehabilitation
No full textOutcome predictions in post-stroke rehabilitation are a key element to personalize the treatment to the needs of the patient, finally enhancing effectiveness of the therapy. They can form the basis of Decision Support Systems, helping clinicians to progressively tune the therapy depending on patients' clinical status and progress. Diverse data sources, such as clinical, demographic, kinematic and time-related data in robotic-assisted rehabilitation, can provide different prediction results. Understanding which data source, or combination thereof, contains useful information for outcome predictions can improve the development of machine learning tools, Decision Support Systems, and even clinical setups designed to record these useful data. The presented work investigates different feature groups and machine learning methods, using data recorded within a robotic-assisted rehabilitation treatment including 44 stroke patients. Results highlight the effectiveness of using multi-dimensional feature groups to predict poststroke rehabilitation. While clinical data alone can already achieve a solid basis for predictive modeling, the integration of kinematic and time-related data can significantly improve prediction accuracy of the patient outcome
BIOELECTRONIC MODULATION OF NERVE-CANCER COMMUNICATION TO INFLUENCE THE TUMOR MICROENVIRONMENT
No full textThe invention relates to a method for the treatment of cancer or adjuvating the treatment of cancer by exploiting the bidirectional tumor-nerve communication as novel pathway to induce an anticancer activity towards epithelial cancer cells using bioelectronic neuromodulation aimed at influencing the TME status
