Explore the vast range of titles available.

In this paper, a framework based on a sparse Mixture of Experts (MoE) architecture is proposed for the federated learning and application of a distributed classification model in domains (like cybersecurity and healthcare) where different parties of the federation store different subsets of features for a number of data instances. The framework is designed to limit the risk of information leakage and computation/communication costs in both model training (through data sampling) and application (leveraging the conditional-computation abilities of sparse MoEs). Experiments on real data have shown the proposed approach to ensure a better balance between efficiency and model accuracy, compared to other VFL-based solutions. Notably, in a real-life cybersecurity case study focused on malware classification (the KronoDroid dataset), the proposed method surpasses competitors even though it utilizes only 50% and 75% of the training set, which is fully utilized by the other approaches in the competition. This method achieves reductions in the rate of false positives by 16.9% and 18.2%, respectively, and also delivers satisfactory results on the other evaluation metrics. These results showcase our framework’s potential to significantly enhance cybersecurity threat detection and prevention in a collaborative yet secure manner.

Background Diagnosis of acute otitis media (AOM) in children can be challenging, given that symptoms are often non-specific or absent, and that the direct observation of the tympanic membrane in its entirety through otoscopy can sometimes be difficult. The aim of this study is to assess the diagnostic concordance in detection of AOM episodes between primary care paediatricians and physicians especially trained in paediatric otoscopy, and to characterize the most misleading elements in diagnostic failure. Methods Consecutive clinical charts of children regularly followed for recurrent AOM (RAOM, i.e.: >3 episodes in 6 months or > 4 episodes in 1 year) at our Otitis Media paediatric outpatient clinic were retrospectively screened, in order to collect any diagnosis of AOM episode (and the related clinical findings/middle ear complaints) performed by primary care paediatricians/emergency room paediatricians. Diagnosis of AOM episode was validated by the same experienced physician (FF) in case of otoscopic relief of a bulging eardrum with at least one of the following: hyperaemia or yellow-like colour. The diagnostic concordance in detection of AOM episodes between primary care/emergency room paediatricians and our internal validator was expressed as the percentage of matching diagnosis. Results One hundred and thirty-four single AOM episodes occurring in 87 children (mean age: 26.9 +/- 18.9 months) were included in the analysis. Diagnostic concordance in detection of AOM episodes between primary care/emergency room paediatricians and our internal validator was reported in 72.4% of cases. The most common pitfall found in our study was the misleading diagnosis of AOM in case of hyperaemic tympanic membrane without bulging (32/37 out of non-validated diagnoses). Conclusions AOM diagnosis still represents a relevant issue among paediatricians in our country, and the presence of tympanic membrane hyperaemia without concomitant bulging can be confusing.

Background Investigations on haematological alterations in paediatric COVID-19 have been focused mostly on lymphocytes and clotting profiles. Neutropenia has been occasionally reported and its course and impact on the disease have not been elucidated. The aim of this study was to describe the epidemiology, course, and impact of neutropenia in children with COVID-19 hospitalised in a tertiary care referral paediatric ward. Methods A single-centre retrospective study was conducted. Hospitalised children between 1 month and 18 years with confirmed COVID-19 and neutropenia were included and compared to non neutropenic patients. Complete blood picture with differential blood count, serum biochemistry, clotting profiles were performed; clinical data, length of hospitalisation, and prescription of drugs were collected. Results Twelve out of 95 patients (12.63%) with documented SARS-CoV-2 infection were neutropenic and met the inclusion criteria. The mean age was 161 days (range 38—490 days). The mean duration of symptoms in neutropenic children was 3.82 days, while the mean length of hospitalisation was 7.67 days. These findings were not significantly different in the two study groups. All patients had mild clinical manifestations and were discharged without sequelae. Conclusions We provided the first comprehensive study on neutropenia in mild paediatric COVID-19 infection. Our findings show that the main features of this haematological disorder in COVID-19 are analogous to the well-known transient benign neutropenia associated with other common viral infections. In our setting, neutropenia does not emerge as a potential negative prognostic factor in paediatric COVID-19.

Background/Objectives: Recurrent acute otitis media (rAOM) is a common disease in childhood, but its impact on the vestibular system remains poorly understood. The present study aimed to evaluate the long-term effects of rAOM on balance and vestibular function in pediatric patients. Methods: A total of 55 children, aged 8 years (25 males and 30 females), with a documented history of rAOM, no AOM episodes in the past year, and no previous ear surgery were assessed. Static posturography was used to assess postural instability, measuring sway area (SX, mm2) under four conditions: eyes open and eyes closed, with and without foam pads. Vestibular function was evaluated using the video head impulse test (v-HIT) to quantify vestibulo–ocular reflex (VOR) gain and corrective saccades across all six semicircular canals. Results: Children with a history of rAOM demonstrated significantly greater postural instability than healthy controls (p < 0.001 for all test conditions). The number of AOM episodes was the primary factor influencing balance dysfunction, with children who had more than eight episodes showing the most pronounced deficits in postural stability (p < 0.05). In some cases, the v-HIT revealed hypofunction in the right anterior (14.5%), left posterior (7.3%), left lateral (5.5%), left anterior (3.6%), and right posterior (3.6%) semicircular canals. Conclusions: The results of this study suggest that rAOM can lead to lasting balance and vestibular dysfunction, highlighting the importance of early monitoring and potential rehabilitation.

Background Cerebral venous sinus thrombosis in children is a rare but potentially fatal complication of acute mastoiditis, one of the most common pediatric infectious diseases. Due to its subtle clinical presentation, suspicion is essential for a prompt diagnosis and appropriate management. Unfortunately, no standard treatment options are available. To discuss the possible clinical presentation, microbiology, and management, we here report the case of a child with otogenic cerebral venous sinus thrombosis and perform a literature review starting from 2011. Case presentation The child, a 10-months-old male, presented clinical signs of right acute otitis media and mastoiditis. Brain computed tomography scan detected right sigmoid and transverse sinus thrombosis, as well as a subperiosteal abscess. Fusobacterium necrophorum and Haemophilus Influentiae were detected on cultural sampling. A multidisciplinary approach along with a combination of medical and surgical therapy allowed the patient’s full recovery. Conclusion Cerebral venous sinus thrombosis is a rare but severe complication of acute otitis media and mastoiditis. The management of this pathological condition is always challenging and an interdisciplinary approach is frequently required. Current therapeutic options include a combination of medical and surgical therapy. A patient-centered approach should guide timing and treatment management.

Clinical data provided by the patient are not always reliable or could be difficult to collect. In this case, a difficult history collection resulted in a diagnostic delay. Major complications were avoided performing an urgent surgical intervention. Clinical data provided by the patient are not always reliable or could be difficult to collect. In this case, a difficult history collection resulted in a diagnostic delay. Major complications were avoided performing an urgent surgical intervention.

Detecting deviant traces in business process logs is crucial for modern organizations, given the harmful impact of deviant behaviours (e.g., attacks or faults). However, training a Deviance Prediction Model (DPM) by solely using supervised learning methods is impractical in scenarios where only few examples are labelled. To address this challenge, we propose an Active-Learning-based approach that leverages multiple DPMs and a temporal ensembling method that can train and merge them in a few training epochs. Our method needs expert supervision only for a few unlabelled traces exhibiting high prediction uncertainty. Tests on real data (of either complete or ongoing process instances) confirm the effectiveness of the proposed approach.

Management of upper retropharyngeal abscesses in children is challenging. In surgical cases, ultrasound‐assisted intra‐operative procedures may be helpful to reach peculiar locations, thus reducing surgical morbidity and complications rate. Management of upper retropharyngeal abscesses in children is challenging. In surgical cases, ultrasound‐assisted intra‐operative procedures may be helpful to reach peculiar locations, thus reducing surgical morbidity and complications rate.

Predicting the final outcome of an ongoing process instance is a key problem in many real-life contexts. This problem has been addressed mainly by discovering a prediction model by using traditional machine learning methods and, more recently, deep learning methods, exploiting the supervision coming from outcome-class labels associated with historical log traces. However, a supervised learning strategy is unsuitable for important application scenarios where the outcome labels are known only for a small fraction of log traces. In order to address these challenging scenarios, a semi-supervised learning approach is proposed here, which leverages a multi-target DNN model supporting both outcome prediction and the additional auxiliary task of next-activity prediction. The latter task helps the DNN model avoid spurious trace embeddings and overfitting behaviors. In extensive experimentation, this approach is shown to outperform both fully-supervised and semi-supervised discovery methods using similar DNN architectures across different real-life datasets and label-scarce settings.

In today’s digital era, dominated by social media platforms such as Twitter , Facebook , and Instagram , the swift dissemination of misinformation represents a significant concern, impacting public sentiment and influencing pivotal global events. Promptly detecting such deceptive content with the help of Machine Learning models is crucial, yet it comes with the challenge of dealing with labelled examples for training these models. Impressive performance results were recently achieved by high-capacity pre-trained transformer-based models (e.g., BERT). Still, such models are too data- and compute-demanding for many critical application contexts where memory, time, and energy consumption must be limited. Here, we propose an innovative semi-supervised method for efficient and effective fake news detection using a content-oriented classifier based on a small-sized BERT embedder. After fine-tuning this model on the sole few labelled data available, an iterative Active Learning (AL) process is carried out, which benefits from limited experts’ feedback to acquire more labelled data for improving the model. The proposed method ensures good detection performances using a few training samples, reasonably small human intervention, and compute/memory costs.