Explore the vast range of titles available.

In recent years, the widespread availability of wearable devices and smartphones has enabled the large-scale collection of human activity data, fostering new opportunities for automatic workout recognition and personalized fitness monitoring. However, the centralized storage of video recordings raises critical privacy concerns, particularly when raw data contain identifiable individuals. Federated Machine Learning provides a paradigm designed with the aim of reducing privacy risks; here, models are collaboratively trained across distributed clients without sharing their sensitive data. In this paper, we propose an approach for workout video classification with Federated Machine Learning, enhanced by explainability through Gradient-weighted Class-Activation Mapping. The proposed method is evaluated on a real-world multi-class exercise video dataset, organized into eight biomechanically coherent macro-classes. In the experimental analysis, we consider several federated configurations in terms of the number of clients, the chosen aggregation strategy, and global communication rounds. The obtained results demonstrate that different aggregation strategies achieve comparable overall accuracy, while explainability effectively highlights the discriminative regions associated with exercise execution, revealing meaningful differences in model behavior between aggregation strategies and uncovering misclassifications driven by contextual biases, demonstrating the trustworthiness of the proposed approach for explainable workout video classification.

The safety of workers in industrial settings is ensured through the correct use of Personal Protective Equipment (PPE). The use of such equipment can be monitored using Deep Learning (DL). Federated Machine Learning (FML) is a technique that can be used in this context to preserve the privacy of sensitive information and provide explainability for the models adopted. Explainability techniques are an essential resource for interpreting the classification performed by the model. In this regard, this study aims to evaluate, through the adoption of specific similarity indices, the robustness and consistency of the explainability algorithms adopted to identify the areas of the images that are decisive for PPE classification. The dataset consists of 1600 real images representing work environments, in which staff are portrayed both with and without Personal Protective Equipment; specifically, there are workers wearing helmets, workers wearing reflective vests, workers wearing both devices and, finally, workers without any PPE. SSIM, VIF and SCC are the most relevant indices involved in the study. In the experimental phase, their mean values stand at 0.99, 0.96 and 0.96 for the intra-client study, and 0.96, 0.91 and 0.71 in the inter-client analysis.

Human pose estimation is a crucial task in computer vision with widespread applications in healthcare, rehabilitation, sports, and remote monitoring. In this paper, we propose a deep learning-based method for automatic human pose estimation and joint angle computation, tailored specifically for physiotherapy and telemedicine scenarios. Beyond pose estimation, the proposed method is able to compute angles between joints, enabling analysis of body alignment and posture. The proposed approach is built upon a customized skeleton with 25 anatomical keypoints and a dataset composed of over 150,000 annotated and augmented images derived from multiple open-source datasets. Experimental results demonstrate the effectiveness of the proposed method, achieving a mAP@50 of 0.58 for keypoint localization and 0.98 for object detection. Moreover, we demonstrate several real-world practical use cases in evaluating exercise correctness and identifying postural deviations by exploiting the proposed method, confirming that the proposed method can represent a promising approach for automated motion analysis, with potential impact on digital health, rehabilitation support, and remote patient care.

Microsatellite instability represents a key biomarker in gastrointestinal cancers with significant diagnostic and therapeutic implications. Traditional molecular assays for microsatellite instability detection, while effective, are costly, time-consuming, and require specialized infrastructure. In this paper we propose an explainable deep learning-based method for microsatellite instability detection starting from the analysis of histopathological images. We consider a set of convolutional neural network architectures i.e., MobileNet, Inception, VGG16, VGG19, and a Vision Transformer model, and we propose a way to provide a kind of clinical explainability behind the model prediction through (three) Class Activation Mapping techniques. With the aim to further strengthen trustworthiness in predictions, we introduce a set of robustness metrics aimed to quantify the consistency of highlighted discriminative regions across different Class Activation Mapping methods. Experimental results on a real-world dataset demonstrate that VGG16 and VGG19 models achieve the best performance in terms of accuracy; in particular, the VGG16 model obtains an accuracy of 0.926, while the VGG19 one reaches an accuracy equal to 0.917. Furthermore, Class Activation Mapping techniques confirmed that the developed models consistently focus on similar tissue regions, while robustness analysis highlighted high agreement between different Class Activation Mapping techniques. These results indicate that the proposed method not only achieves interesting predictive accuracy but also provides explainable predictions, with the aim to boost the integration of deep learning into real-world clinical practice.

Background: Formaldehyde, classified as a carcinogen in 2004, as of today is widely used in many work activities. From its classification, further studies were performed to evaluate its carcinogenicity. The aim of the systematic review is to update the evidence on occupational exposure to formaldehyde and cancer onset. Methods: The review, in accordance with the PRISMA statement, includes articles in English reporting original results of studies conducted on workers exposed to formaldehyde, considering all types of cancer, published from 1 January 2000 to 30 July 2021 and selected from the Pubmed and Scopus databases. The studies’ quality was assessed by the Newcastle–Ottawa Scale. Results: A total of 21 articles were included, conducted in different European, American, and Asian countries. The most investigated occupational areas are those characterized by a deliberate use of formaldehyde. Some studies evaluated all types of cancer, whereas others focused on specific sites such as thyroid and respiratory, lymphohematopoietic, or central nervous systems. The results showed weak associations with lung cancer, nasopharyngeal cancer, leukemia, and non-Hodgkin’s lymphoma. Conclusions: The results demonstrate the need for further original studies carried out on representative samples of workers exposed to measured levels of FA. These studies should be designed to reduce the bias due to co-exposure to other carcinogens.

Formaldehyde is a toxic and carcinogenic compound, still used in several occupational settings due to its properties. Thus, in these working scenarios, it is necessary to provide effective measures to reduce workers’ exposure to formaldehyde. The aim of this systematic review is to provide a picture of the worldwide mitigation strategies implemented in occupational environments for minimizing the exposure to formaldehyde and which ones are the most effective for this purpose.The systematic review was performed according to PRISMA statement; the protocol was registered in PROSPERO (CRD42022302207). The search was performed on three electronic databases (PubMed, Scopus, and Web of Science). Studies were considered eligible if they describe strategies for mitigating formaldehyde occupational exposure and their efficacy. We included articles reporting observational studies, semi-experimental, and experimental studies and published in the English language, from the inception to March 26th, 2023. The quality assessment was performed using the Newcastle–Ottawa Quality Assessment Scale.In total, 28 articles were included in the review. The employment scenarios/activities studied were human and veterinary anatomy, autopsy, histopathology or pathology laboratories, embalming procedures, hospital, operating theaters, aquaculture, textile or foundry industries, industry using 3-D printers, offices, and firefighters’ activities. Different methods have proven useful in mitigating formaldehyde exposure, such as the use of personal protective equipment, engineering control methods, organization methods, and technical strategies, with a reduction of airborne formaldehyde until to 99.6%. The highest reduction was obtained in an anatomy laboratory through locally exhausted dissection tables equipped with activated carbon filters.The specific suitable procedures should be standardized and applied in all work settings for an appropriate risk management, in order to protect the health of exposed workers.

Healthcare workers (HCWs) played an essential role in managing the COVID-19 pandemic. The Italian Workers’ Compensation Authority (INAIL) and the Italian National Institute of Health (ISS) developed a retrospective study to analyze and understand trends and characteristics of infections among HCWs during the first wave of the pandemic. Between May and September 2020, Italian Regions retrospectively collected anonymous data regarding HCWs infected from the beginning of the pandemic until 30 April 2020 from their administrative sources through a questionnaire asking for socio-demographic and occupational information about the characteristics of contagion and disease outcome. Almost 16,000 valid questionnaires were received. Logistic regression was performed to ascertain the effect of age, gender, geographical macro area, profession, and pre-existing health conditions on the likelihood of HCWs developing more severe forms of COVID-19 (at least hospitalization with mild symptoms). All predictor variables were statistically significant. HCWs at higher risk of developing a more severe disease were males (OR: 1.90; 95% CI: 1.44–2.51), older than 60 years of age (OR: 6.00; 95% CI: 3.30–10.91), doctors (OR: 4.22; 95% CI: 2.22–9.02), working in Lombardy (OR: 55.24; 95% CI: 34.96–87.29) and with pre-existing health conditions (OR: 1.90; 95% CI: 1.43–2.51). This study analyses the main reasons for the overload put on the National Health Service by the first wave of the pandemic and the risk of infection for HCWs by age, gender, occupational profile and pre-existing health conditions. Improved knowledge, availability of personal protective equipment (PPE) and a tight vaccination campaign for HCWs strongly changed the trend of infections among HCWs, with substantial elimination of serious and fatal cases.

Background In light of recent developments in nanotechnologies, interest is growing to better comprehend the interaction of nanoparticles with body tissues, in particular within the cardiovascular system. Attention has recently focused on the link between environmental pollution and cardiovascular diseases. Nanoparticles <50 nm in size are known to pass the alveolar–pulmonary barrier, enter into bloodstream and induce inflammation, but the direct pathogenic mechanisms still need to be evaluated. We thus focused our attention on titanium dioxide (TiO 2 ) nanoparticles, the most diffuse nanomaterial in polluted environments and one generally considered inert for the human body. Methods We conducted functional studies on isolated adult rat cardiomyocytes exposed acutely in vitro to TiO 2 and on healthy rats administered a single dose of 2 mg/Kg TiO 2 NPs via the trachea. Transmission electron microscopy was used to verify the actual presence of TiO 2 nanoparticles within cardiac tissue, toxicological assays were used to assess lipid peroxidation and DNA tissue damage, and an in silico method was used to model the effect on action potential. Results Ventricular myocytes exposed in vitro to TiO 2 had significantly reduced action potential duration, impairment of sarcomere shortening and decreased stability of resting membrane potential. In vivo , a single intra-tracheal administration of saline solution containing TiO 2 nanoparticles increased cardiac conduction velocity and tissue excitability, resulting in an enhanced propensity for inducible arrhythmias. Computational modeling of ventricular action potential indicated that a membrane leakage could account for the nanoparticle-induced effects measured on real cardiomyocytes. Conclusions Acute exposure to TiO 2 nanoparticles acutely alters cardiac excitability and increases the likelihood of arrhythmic events.

Background: In recent decades, there has been an increase in male infertility, and in many cases, the etiology remains unclear. Several studies relate male hypo-fertility to xenobiotic exposure, even if no data exist about multiple exposure at the environmental level. Methods: The study involved 86 males with diagnosis of idiopathic male infertility (IMI), and 46 controls with no alteration in sperm characteristics. Seminal plasma (SP) and urine samples were analyzed by liquid chromatography tandem mass spectrometry (LC-MS/MS) to quantify biomarkers of exposure (the main metabolites of benzene, toluene, 1,3-butadiene, 3-monochloropropanediol, styrene, and naphthol) and effect (oxidized products of nucleic acids).Results: Biomarker concentrations were similar in subjects with IMI and controls even if a stronger correlation between biomarkers of exposure and effects were observed in SP. Data show that, both in SP and urine, most metabolites were inter-correlated, indicating a simultaneous co-exposure to the selected substances at the environmental level. Principal component analysis showed in SP the clustering of mercapturic acids indicating a preferential metabolic pathway with Glutathione (GSH) depletion and, consequently, an increase of oxidative stress. This result was also confirmed by multivariable analysis through the development of explanatory models for oxidized products of nucleic acids. Conclusions: This study highlights how oxidative stress on the male reproductive tract can be associated with a different representation of metabolic pathways making the reproductive tract itself a target organ for different environmental pollutants. Our results demonstrate that SP is a suitable matrix to assess the exposure and evaluate the effects of reproductive toxicants in environmental/occupational medicine. The statistical approach proposed in this work represents a model appropriate to study the relationship between multiple exposure and effect, applicable even to a wider variety of chemicals.