Search

Artificial intelligence algorithms have become extensively utilized in survival analysis for high-dimensional, multi-source data. However, due to their complexity, these methods often yield poorly interpretable outcomes, posing challenges in the analysis of several conditions. One of these conditions is obstructive sleep apnea, a sleep disorder characterized by the simultaneous occurrence of comorbidities. Survival analysis provides a potential solution for assessing and categorizing the severity of obstructive sleep apnea, aiding personalized treatment strategies. Given the critical role of time in such scenarios and considering limitations in model interpretability, time-dependent explainable artificial intelligence algorithms have been developed in recent years for direct application to basic Machine Learning models, such as Cox regression and survival random forest. Our work aims to enhance model selection in OSA survival analysis using time-dependent XAI for Machine Learning and Deep Learning models. We developed an end-to-end pipeline, training several survival models and selecting the best performers. Our top models—Cox regression, Cox time, and logistic hazard—achieved good performance, with C-index scores of 0.81, 0.78, and 0.77, and Brier scores of 0.10, 0.12, and 0.11 on the test set. We applied SurvSHAP methods to Cox regression and logistic hazard to investigate their behavior. Although the models showed similar performance, our analysis established that the results of the log hazard model were more reliable and useful in clinical practice compared to those of Cox regression in OSA scenarios. [ABSTRACT FROM AUTHOR]

The genus Morbillivirus comprises several lympho-epithelio-neurotropic, highly pathogenic RNA viruses of domestic and wild vertebrates, including aquatic mammals. Among them, cetacean morbillivirus (CeMV) has been responsible since the 1980s for [...]

To the Editor: Anthrax is hypoendemic in Italy; a few outbreaks occurred yearly involving unvaccinated herbivores on pastures in central and southern regions and the major islands. Multiple-locus variable-number tandem-repeat [...]

As a result of the increase of game meat intended for human consumption through Europe, a plethora of food-borne diseases, including trichinellosis, may occur in consumers, posing a relevant public health threat. Thus, this study aims to a citizen science approach to monitor the occurrence of Trichinella spp. in wild boar meat intended for human consumption, evaluating the risk of infection for consumers. Following the European Regulation 2015/1375 ( laying down specific rules on official controls for Trichinella in meat ), from 2015 to 2021, hunters ( n  = 478) were involved to collect diaphragm pillar samples of wild boars from mainland southern Italy, which were tested for Trichinella spp. L 1 larvae via HCl-pepsin digestion and Multiplex PCR. Overall, 139,160 animals were collected (average of 19,880 per year), being 14 (i.e., 0.01%) tested positive to Trichinella britovi by the combined biochemical and molecular approach. An average larval burden of 28.4 L 1 per gram of meat was found (minimum 3.2 - maximum 132.6). A statistically significant difference was found in the prevalence according to hunting seasons ( p  < 0.01, with higher values in 2016 and 2021) and regions of the study area ( p  < 0.01). No statistically significant decrease in the prevalence of T. britovi throughout the study period was found ( p  = 0.51), except in Apulia region ( p  < 0.01). These findings revealed a stable prevalence of T. britovi in wild boar meat intended for human consumption, suggesting a risk of infection for consumers, especially hunters and local markets users. Citizen science surveillance models could be promoted to improve trichinellosis control and prevention in a One Health perspective., Competing Interests: None., (© 2023 The Authors. Published by Elsevier B.V.)

Anthrax is a disease of humans and animals caused by the encapsulated, spore-forming Bacillus anthracis. In Italy, anthrax is normally a sporadic disease. During the summer 2004, anthrax broke out in the Basilicata, in southern Italy, a region with a low prevalence of anthrax in which vaccination had been suspended since 1998. The disease involved several animals in few weeks and in a large area. Over 41 days, 81 cattle died, as well as 15 sheep, 9 goats, 11 horses and 8 deer. The Multiple-locus Variable-Number Tandem Repeats Analysis (MLVA) showed that all the 53 isolates belonged to the Cluster Ala, genotype 1. The results of the Single Nucleotide Repeats (SNRs) Analysis showed that 48/53 B. anthacis strains belonged to a single clonal lineage, the sub-genotype sgt - eB. Two sporadic mutants, sgt - eB,m1 and sgt - eB,m2, were isolated, only one managing to infect other herds. Factors that could have contributed to the spread of infection, such as the transmission of spores by insect vectors and the favourable weather conditions were evaluated.