Search Results (9)

COVID-19 vaccines have revolutionized prevention and clinical management by reducing disease severity and mortality. However, their long-term impact on hospitalization is unclear. This retrospective study assessed whether vaccination status, timing, and number of vaccine doses influence the risk of hospitalization and COVID-19 pneumonia in a large cohort in Italy, several years after initial vaccine rollout. From 1 October 2023, to 2 February 2024, at Humanitas Research Hospital (Milan) and two affiliates, we recorded age, sex, comorbidities, vaccination status (number of doses and time since last dose), admission type (urgent vs. elective), and pneumonia diagnosis. Baseline health was quantified by the Charlson Comorbidity Index. Among 16,034 admissions (14,874 patients), vaccination data were available for 5743 cases: 40.8% were in the emergency setting and 59.2% were elective. Patients presented with pneumonia in 6.8% of cases. Laboratory results confirmed COVID-19 pneumonia occurred in 43.7% of pneumonia cases, with a 16.9% mortality. Patients with no vaccine dose had a higher proportion of COVID-19 pneumonia, while COVID-19 pneumonia rates were lower in individuals who had received more vaccine doses. There were no significant differences in COVID-19 pneumonia risk by timing of last vaccination. Moreover, hospitalized unvaccinated patients had overall more frequent emergency admissions (57.3%), while patients with three or more doses had about a ~40% emergency admission rate. COVID-19 positivity during hospitalization was highest in unvaccinated patients (90.7%) and declined with vaccination status. Vaccinated patients, especially those with multiple doses, had significantly lower COVID-19 pneumonia rates and emergency admissions. These findings suggest a possible protective effect of vaccination in modifying the clinical presentation and severity of illness among those who are hospitalized and support continued vaccination efforts for high-risk groups to reduce severe adverse outcomes. Full article

With the increasing adoption of cooperative multi-UAV systems in applications such as cargo delivery and ground reconnaissance, the demand for scalable and efficient path planning methods has grown substantially. However, traditional heuristic algorithms are frequently trapped in local optima, require task-specific manual tuning, and exhibit limited generalization capabilities. Furthermore, their dependence on iterative optimization renders them unsuitable for large-scale real-time applications. To address these challenges, this paper introduces an end-to-end deep reinforcement learning framework that bypasses the reliance on handcrafted heuristic rules. The proposed method leverages an encoder–decoder architecture with multi-head attention (MHA), where the encoder generates embeddings for UAVs and task parameters, while the decoder dynamically selects actions based on contextual embeddings and enforces feasibility through a masking mechanism. The MHA module effectively models global spatial-task dependencies among nodes, enhancing solution quality. Additionally, we integrate a Multi-Start Greedy Rollout Baseline to evaluate diverse trajectories via parallelized greedy searches, thereby reducing policy gradient variance and improving training stability. Experiments demonstrated significant improvements in scalability, particularly in 100-node scenarios, where our method drastically reduced inference time compared to conventional methods, while maintaining a competitive path cost efficiency. A further validation on simulated mission environments and real-world geospatial data (sourced from Google Earth) underscored the robust generalization of the framework. This work advances large-scale UAV mission planning by offering a scalable, adaptive, and computationally efficient solution. Full article

The Vehicle Routing Problem (VRP) is a classic combinatorial optimization problem commonly encountered in the fields of transportation and logistics. This paper focuses on a variant of the VRP, namely the Vehicle Routing Problem with Stochastic Travel Cost (VRP-STC). In VRP-STC, the introduction of stochastic travel costs increases the complexity of the problem, rendering traditional algorithms unsuitable for solving it. In this paper, the GAT-AM model combining Graph Attention Networks (GAT) and multi-head Attention Mechanism (AM) is employed. The GAT-AM model uses an encoder–decoder architecture and employs a deep reinforcement learning algorithm. The GAT in the encoder learns feature representations of nodes in different subspaces, while the decoder uses multi-head AM to construct policies through both greedy and sampling decoding methods. This increases solution diversity, thereby finding high-quality solutions. The REINFORCE with Rollout Baseline algorithm is used to train the learnable parameters within the neural network. Test results show that the advantages of GAT-AM become greater as problem complexity increases, with the optimal solution generally unattainable through traditional algorithms within an acceptable timeframe. Full article

Training an effective deep learning model to learn ocean processes involves careful choices of various hyperparameters. We leverage DeepHyper’s advanced search algorithms for multiobjective optimization, streamlining the development of neural networks tailored for ocean modeling. The focus is on optimizing Fourier neural operators (FNOs), a data-driven model capable of simulating complex ocean behaviors. Selecting the correct model and tuning the hyperparameters are challenging tasks, requiring much effort to ensure model accuracy. DeepHyper allows efficient exploration of hyperparameters associated with data preprocessing, FNO architecture-related hyperparameters, and various model training strategies. We aim to obtain an optimal set of hyperparameters leading to the most performant model. Moreover, on top of the commonly used mean squared error for model training, we propose adopting the negative anomaly correlation coefficient as the additional loss term to improve model performance and investigate the potential trade-off between the two terms. The numerical experiments show that the optimal set of hyperparameters enhanced model performance in single timestepping forecasting and greatly exceeded the baseline configuration in the autoregressive rollout for long-horizon forecasting up to 30 days. Utilizing DeepHyper, we demonstrate an approach to enhance the use of FNO in ocean dynamics forecasting, offering a scalable solution with improved precision. Full article

Many studies identified factors associated with vaccination intention and hesitancy, but factors associated with vaccination promptness and the effect of vaccination intention on vaccination promptness are unknown. This study identified factors associated with COVID-19 vaccination promptness and evaluated the role of vaccination intention on vaccination promptness in 1223 participants in a community-based longitudinal cohort study (June 2020 to December 2021). Participants answered questions regarding COVID-19 vaccination intention, vaccination status, and reasons for not receiving a vaccine. The association of baseline vaccine hesitancy with vaccination was assessed by the Kaplan–Meier survival analysis. Follow-up analyses tested the importance of other variables predicting vaccination using the Cox proportional hazards model. Older age was associated with shorter time to vaccination (HR = 1.76 [1.37–2.25] 85-year-old versus 65-year-old). Lower education levels (HR = 0.80 [0.69–0.92]), household incomes (HR = 0.84 [0.72–0.98]), and baseline vaccination intention of ‘No’ (HR = 0.16 [0.11–0.23]) were associated with longer times to vaccination. The most common reasons for not being vaccinated (N = 58) were vaccine safety concerns (n = 33), side effects (n = 28), and vaccine effectiveness (n = 25). Vaccination campaigns that target populations prone to hesitancy and address vaccine safety and effectiveness could be helpful in future vaccination rollouts. Full article

Poland has implemented two major organizational changes in recent years to improve cancer care. In 2015, a dedicated ‘fast pathway’ to diagnostics and treatment was implemented for patients suspected of having cancer. In 2019, the National Oncology Network began pilots in four regions of care pathways for cancer at five sites. Neither has been evaluated—no baseline information was collected, and what assessments were undertaken were limited to process measures. While the 2019 initiative was at least piloted, a national rollout has been announced even while the pilot is still ongoing and when concerns about certain aspects of the model have been raised. Given that cancer is the second largest cause of death in Poland and that cancer outcomes are worse compared to Western European averages, there is a particular need to ensure that models of care are informed by the evidence and adapted to the realities of the Polish healthcare system. Full article

There is significant variability in neutralizing antibody responses (which correlate with immune protection) after COVID-19 vaccination, but only limited information is available about predictors of these responses. We investigated whether device-generated summaries of physiological metrics collected by a wearable device correlated with post-vaccination levels of antibodies to the SARS-CoV-2 receptor-binding domain (RBD), the target of neutralizing antibodies generated by existing COVID-19 vaccines. One thousand, one hundred and seventy-nine participants wore an off-the-shelf wearable device (Oura Ring), reported dates of COVID-19 vaccinations, and completed testing for antibodies to the SARS-CoV-2 RBD during the U.S. COVID-19 vaccination rollout. We found that on the night immediately following the second mRNA injection (Moderna-NIAID and Pfizer-BioNTech) increases in dermal temperature deviation and resting heart rate, and decreases in heart rate variability (a measure of sympathetic nervous system activation) and deep sleep were each statistically significantly correlated with greater RBD antibody responses. These associations were stronger in models using metrics adjusted for the pre-vaccination baseline period. Greater temperature deviation emerged as the strongest independent predictor of greater RBD antibody responses in multivariable models. In contrast to data on certain other vaccines, we did not find clear associations between increased sleep surrounding vaccination and antibody responses. Full article

5G is the new generation of 3GPP-based cellular communications that provides remarkable connectivity capabilities and extreme network performance to mobile network operators and cellular users worldwide. The rollout process of a new capacity layer (cell) on top of the existing previous cellular technologies is a complex process that requires time and manual effort from radio planning-engineering teams and parameter optimization teams. When it comes to optimum configuration of the 5G gNB cell parameters, the maximization of achieved coverage (RSRP) and quality (SINR) of the served mobile terminals are of high importance for achieving the very high data transmission rates expected in 5G. This process strongly relies on network measurements that can be even more insightful when mobile terminal localization information is present. This information can be generated by modern algorithmic techniques that act on the cellular network signaling measurements. Configuration algorithms can then use these measurements combined with location information to optimize various cell deployment parameters such as cell azimuth. Furthermore, data-driven approaches are shown in the literature to outperform traditional, model-based algorithms as they can automate the optimization of parameters while specializing in the characteristics of each individual geographical zone. In the context of the above, in this paper, we tested the automated network reconfiguration schemes based on unsupervised learning and applied statistics for cell azimuth steering. We compared network metric clustering and geospatial clustering to be used as our baseline algorithms that are based on K-means with the proposed scheme—hybrid network and spatial clustering based on hierarchical DBSCAN. Each of these algorithms used data generated by an initial scenario to produce cell re-configuration actions and their performance was then evaluated on a validated simulation platform to capture the impact of each set of gNB reconfiguration actions. Our performance evaluation methodology was based on statistical distribution analysis for RSRP and SINR metrics for the reference scenario as well as for each reconfiguration scheme. It is shown that while both baseline algorithms improved the overall performance of the network, the proposed hybrid network–spatial scheme greatly outperformed them in all statistical criteria that were evaluated, making it a better candidate for the optimization of 5G capacity layers in modern urban environments. Full article

Community pharmacist is one of the most prominent and accessible healthcare professions. The community pharmacists’ role in healthcare is evolving, with opportunities being taken to reduce pressure on primary care services. However, the question remains of how well community pharmacists are equipped for this changing role. This was a sequentially designed study using a mix of methods to explore nutrition education among community pharmacists in Northern Ireland. It consisted of two phases. Phase 1 was a cross-sectional exploration to map the attitudes and practice of Northern Ireland (NI) pharmacists towards diet-related health promotion and disease prevention. An online questionnaire with open and closed questions to gain both quantitative and qualitative responses was developed and distributed to community pharmacists practising in NI. A total of 91% considered nutrition important in reducing the global burden of disease. While the majority (89%) believed patients would value nutritional advice from a pharmacist, 74% were not confident in providing advice to a patient with diabetes. From the consensus gained in Phase 1 a nutrition education intervention (Phase 2) for pre-registration pharmacists was developed using the Hardens 10 question system. The training programme was advertised to pre-registration pharmacy students in NI. It was delivered by nutrition experts who have education qualifications. The intervention was evaluated using a before and after questionnaire that assessed knowledge, attitudes, and practice (KAP). Phase 2 did find sustained improvement from the baseline in KAP but there was a decline from immediately post-training to three months post-training. This suggests the need to further embed nutrition education. The education programme was found to be effective for the target population and sets the stage for the development of an implementation strategy for a wider roll-out with evaluation. Full article