Search

Abstract This paper presents an open-access repository collecting information on measles virus infections and flight passenger movements in European countries from 2011 to 2023. It provides a comprehensive overview of reported measles cases and measles-mumps-rubella (MMR) vaccination coverage from authoritative organizations such as the World Health Organization (WHO) and the European Centre for Disease Prevention and Control (ECDC). In addition, the dataset includes detailed data on passenger movements between countries, facilitating analysis of cross-border disease transmission. This resource enables more precise spatial analyses for monitoring and forecasting measles outbreaks, underscoring the importance of adequate vaccination coverage and sustained international surveillance to prevent the spread of the disease.

Abstract Background Acute kidney injury (AKI) is among the most common complications following cardiac surgery in adult and pediatric patients, significantly affecting morbidity and mortality. Artificial Intelligence (AI) with Machine Learning (ML) can be used to predict outcomes. AKI diagnosis anticipation may be an ideal target of these methods. The scope of the study is building a Machine Learning (ML) train model with Random Forest (RF) algorithm, based on electronic health record (EHR) data, able to forecast AKI continuously after 48 h in post-cardiac surgery children, and to test its performance. Four hundred nineteen consecutive patients out of 1115 hospital admissions were enrolled in a single-center retrospective study. Patients were younger than 18 years and admitted from August 2018 to February 2020 in a pediatric cardiac intensive care unit (PCICU) undergoing cardiac surgery, invasive procedure (hemodynamic studies), and medical conditions with complete EHR records and discharged after 48 h or more. Results Thirty-six variables were selected to build the algorithm according to commonly described cardiac surgery-associated AKI clinical predictors. We evaluated different models for different outcomes: binary AKI (no AKI vs. AKI), severe AKI (no-mild vs severe AKI), and multiclass classification (maximum AKI and the most frequent level of AKI, mode AKI). The algorithm performance was assessed with the area under the curve receiver operating characteristics (AUC ROC) for binary classification, with accuracy and K for multiclass classification. AUC ROC for binary AKI was 0.93 (95% CI 0.92–0.94), and for severe AKI was 0.99 (95% CI 0.98–1). Mode AKI accuracy was 0.95, and K was 0.80 (95% CI 0.94–0.96); maximum AKI accuracy was 0.92, and K was 0.71 (95% CI 0.91–0.93). The importance matrix plot demonstrated creatinine, basal creatinine, platelets count, adrenaline support, and lactate dehydrogenase for binary AKI with the addition of cardiopulmonary bypass duration for severe AKI as the most relevant variables of the model. Conclusions We validated a ML model to detect AKI occurring after 48 h in a retrospective observational study that could help clinicians in individuating patients at risk of AKI, in which a preventive strategy can be determinant to improve the occurrence of renal dysfunction.

Over the last century, P. oceanica meadows have undergone significant regression along Mediterranean coasts due to anthropogenic disturbances. Using an integrated approach based on historical aerial photography interpretation in GIS environment and Bayesian modelling, we mapped the upper limits of a P. oceanica meadow and identified the most influential disturbance factors acting along the coast of Giglio Island, where several local human-mediated impacts have historically co-occurred from 1968 to 2013. Model selection based on the DIC criterion suggested that the presence of the impacts is suitable for describing the seagrass coverage variation. Similarities in P. oceanica cover within 13 investigated zones were highlighted when considering the most relevant impacts, such as harbour expansion, mining, and anchoring. The detected adverse effects indicate the need for implementing management actions focusing on the present and past sources of impact to reduce their effect on P. oceanica beds actively.

Developing predictive methods to identify patients with high risk of severe COVID-19 disease is of crucial importance. Authors show here that by measuring anti-SARS-CoV-2 antibody and cytokine levels at the time of hospital admission and integrating the data by unsupervised hierarchical clustering/machine learning, it is possible to predict unfavourable outcome.

Background: Short-term forecasts of infectious disease burden can contribute to situational awareness and aid capacity planning. Based on best practice in other fields and recent insights in infectious disease epidemiology, one can maximise the predictive performance of such forecasts if multiple models are combined into an ensemble. Here, we report on the performance of ensembles in predicting COVID-19 cases and deaths across Europe between 08 March 2021 and 07 March 2022. Methods: We used open-source tools to develop a public European COVID-19 Forecast Hub. We invited groups globally to contribute weekly forecasts for COVID-19 cases and deaths reported by a standardised source for 32 countries over the next 1–4 weeks. Teams submitted forecasts from March 2021 using standardised quantiles of the predictive distribution. Each week we created an ensemble forecast, where each predictive quantile was calculated as the equally-weighted average (initially the mean and then from 26th July the median) of all individual models’ predictive quantiles. We measured the performance of each model using the relative Weighted Interval Score (WIS), comparing models’ forecast accuracy relative to all other models. We retrospectively explored alternative methods for ensemble forecasts, including weighted averages based on models’ past predictive performance. Results: Over 52 weeks, we collected forecasts from 48 unique models. We evaluated 29 models’ forecast scores in comparison to the ensemble model. We found a weekly ensemble had a consistently strong performance across countries over time. Across all horizons and locations, the ensemble performed better on relative WIS than 83% of participating models’ forecasts of incident cases (with a total N=886 predictions from 23 unique models), and 91% of participating models’ forecasts of deaths (N=763 predictions from 20 models). Across a 1–4 week time horizon, ensemble performance declined with longer forecast periods when forecasting cases, but remained stable over 4 weeks for incident death forecasts. In every forecast across 32 countries, the ensemble outperformed most contributing models when forecasting either cases or deaths, frequently outperforming all of its individual component models. Among several choices of ensemble methods we found that the most influential and best choice was to use a median average of models instead of using the mean, regardless of methods of weighting component forecast models. Conclusions: Our results support the use of combining forecasts from individual models into an ensemble in order to improve predictive performance across epidemiological targets and populations during infectious disease epidemics. Our findings further suggest that median ensemble methods yield better predictive performance more than ones based on means. Our findings also highlight that forecast consumers should place more weight on incident death forecasts than incident case forecasts at forecast horizons greater than 2 weeks. Funding: AA, BH, BL, LWa, MMa, PP, SV funded by National Institutes of Health (NIH) Grant 1R01GM109718, NSF BIG DATA Grant IIS-1633028, NSF Grant No.: OAC-1916805, NSF Expeditions in Computing Grant CCF-1918656, CCF-1917819, NSF RAPID CNS-2028004, NSF RAPID OAC-2027541, US Centers for Disease Control and Prevention 75D30119C05935, a grant from Google, University of Virginia Strategic Investment Fund award number SIF160, Defense Threat Reduction Agency (DTRA) under Contract No. HDTRA1-19-D-0007, and respectively Virginia Dept of Health Grant VDH-21-501-0141, VDH-21-501-0143, VDH-21-501-0147, VDH-21-501-0145, VDH-21-501-0146, VDH-21-501-0142, VDH-21-501-0148. AF, AMa, GL funded by SMIGE - Modelli statistici inferenziali per governare l'epidemia, FISR 2020-Covid-19 I Fase, FISR2020IP-00156, Codice Progetto: PRJ-0695. AM, BK, FD, FR, JK, JN, JZ, KN, MG, MR, MS, RB funded by Ministry of Science and Higher Education of Poland with grant 28/WFSN/2021 to the University of Warsaw. BRe, CPe, JLAz funded by Ministerio de Sanidad/ISCIII. BT, PG funded by PERISCOPE European H2020 project, contract number 101016233. CP, DL, EA, MC, SA funded by European Commission - Directorate-General for Communications Networks, Content and Technology through the contract LC-01485746, and Ministerio de Ciencia, Innovacion y Universidades and FEDER, with the project PGC2018-095456-B-I00. DE., MGu funded by Spanish Ministry of Health / REACT-UE (FEDER). DO, GF, IMi, LC funded by Laboratory Directed Research and Development program of Los Alamos National Laboratory (LANL) under project number 20200700ER. DS, ELR, GG, NGR, NW, YW funded by National Institutes of General Medical Sciences (R35GM119582; the content is solely the responsibility of the authors and does not necessarily represent the official views of NIGMS or the National Institutes of Health). FB, FP funded by InPresa, Lombardy Region, Italy. HG, KS funded by European Centre for Disease Prevention and Control. IV funded by Agencia de Qualitat i Avaluacio Sanitaries de Catalunya (AQuAS) through contract 2021-021OE. JDe, SMo, VP funded by Netzwerk Universitatsmedizin (NUM) project egePan (01KX2021). JPB, SH, TH funded by Federal Ministry of Education and Research (BMBF; grant 05M18SIA). KH, MSc, YKh funded by Project SaxoCOV, funded by the German Free State of Saxony. Presentation of data, model results and simulations also funded by the NFDI4Health Task Force COVID-19 (https://www.nfdi4health.de/task-force-covid-19-2) within the framework of a DFG-project (LO-342/17-1). LP, VE funded by Mathematical and Statistical modelling project (MUNI/A/1615/2020), Online platform for real-time monitoring, analysis and management of epidemic situations (MUNI/11/02202001/2020); VE also supported by RECETOX research infrastructure (Ministry of Education, Youth and Sports of the Czech Republic: LM2018121), the CETOCOEN EXCELLENCE (CZ.02.1.01/0.0/0.0/17-043/0009632), RECETOX RI project (CZ.02.1.01/0.0/0.0/16-013/0001761). NIB funded by Health Protection Research Unit (grant code NIHR200908). SAb, SF funded by Wellcome Trust (210758/Z/18/Z).

Abstract Characterizing and monitoring changes in biogenic 3‐dimensional (3D) structures at multiple scales over time is challenging within the practical constraints of conventional ecological tools. Therefore, we developed a structure‐from‐motion (SfM)‐based photogrammetry method, coupled with inspection and mesh processing software, to estimate important ecological parameters of underwater worm colonies (hummocks) constructed by the sabellariid polychaete Sabellaria alveolata, using non‐destructive, 3D modeling and mesh analysis. High resolution digital images of bioconstructions (hummocks) were taken in situ under natural conditions to generate digital 3D models over different sampling periods to analyse the morphological evolution of four targeted hummocks. 3D models were analysed in GOM Inspect software, a powerful and freely available mesh processing software to follow growth as well as morphology changes over time of each hummock. Linear regressions showed 3D models only slightly overestimated the real dimensions of the reference objects with an average error

Periodic assessments of population status and trends to detect natural influences and human effects on coastal dolphin are often limited by lack of baseline information. Here, we investigated for the first time the site-fidelity patterns and estimated the population size of bottlenose dolphins (Tursiops truncatus) at the Tiber River estuary (central Mediterranean, Tyrrhenian Sea, Rome, Italy) between 2017 and 2020. We used photo-identification data and site-fidelity metrics to study the tendency of dolphins to remain in, or return to, the study area, and capture–recapture models to estimate the population abundance. In all, 347 unique individuals were identified. The hierarchical cluster analysis highlighted 3 clusters, labeled resident (individuals encountered at least five times, in three different months, over three distinct years; n = 42), part-time (individuals encountered at least on two occasions in a month, in at least two different years; n = 73), and transient (individuals encountered on more than one occasion, in more than 1 month, none of them in more than 1 year; n = 232), each characterized by site-fidelity metrics. Open POPAN modeling estimated a population size of 529 individuals (95% CI: 456–614), showing that the Capitoline (Roman) coastal area and nearby regions surrounding the Tiber River estuary represent an important, suitable habitat for bottlenose dolphins, despite their proximity to one of the major urban centers in the world (the city of Rome). Given the high number of individuals in the area and the presence of resident individuals with strong site fidelity, we suggest that conservation plans should not be focused only close to the Tiber River mouths but extended to cover a broader scale of area.

In practical applications of pattern recognition, there are often different features extracted from raw data used for identification. Methods of combining multiple classifiers with different features are viewed as a general problem in various application areas. In this paper some statistical methods based on mixtures of experts models able to combine classifiers and different feature sets are illustrated and applied to the text-independent speaker recognition problem. The comparison takes place on the basis of a dataset composed of more then 50 vocal signals (Italian speakers, phone calls recording).

Assessing the distribution of marine apex–predators is pivotal to understanding community interactions and defining management goals. However, several challenges arise in both estimates and predictions considering the distinctive and mutable biological/ecological requirements of these species and the influence of human activities. Thus, efforts to study apex–predators’ spatial distribution patterns must deal with inherent uncertainty. Relying on different data sources (research programs and social media reports), physiographic and environmental covariates (depth, slope, surface temperature and chlorophyll–a), and specific source–related detection functions, this study selected a Spatial Log–Gaussian Cox Process to model the distribution patterns of an opportunistic apex–predator, the common bottlenose dolphin (Tursiops truncatus), over 14 years (2008−2021) in the Mediterranean Sea (Italy) using a total of 955 encounters. Both depth and slope showed a significant (95% significance) reduction effect in the encounters when deeper and steeper, respectively. Temperature (parabolic) shows a positive effect (90% significance), while chlorophyll–a values did not seem to have a significant effect on encounter intensities within each season. The estimated posterior mean and the coefficient of variation surfaces for the intensity by season showed higher intensity in summer near the Tiber River estuary than other regions. Almost homogeneous predictions were observed in winter, with marginal greater intensities where lower temperatures and higher chlorophyll–a concentration were observed. The relatively low variance was predicted in the more coastal parts of the study area within each season, while higher uncertainty was instead revealed in the southernmost offshore area. This study highlighted the persistent presence of the common bottlenose dolphin in the investigated area both winter and summer, with a coherent distribution within each season, and rare transient occurrences in deeper waters (where uncertainty increases). Thanks to its versatile characteristics, the species seems to well adapt to different seasonal conditions and maintain its distributional range.

The intensification of agricultural land use and urbanisation has increased nutrient loads in aquatic ecosystems. Nitrogen loads can alter ecosystem structure and functioning, resulting in increased algal productivity, algal blooms and eutrophication. The principal aim of the present paper is to extend the use of epilithic δ 15 N signatures to a lake ecosystem in order to evaluate the potential impact of anthropogenic nitrogen discharges (organic and inorganic) that can also reach coastal waters. Epilithic associations were collected from volcanic rocks in different seasons in shallow water along the entire perimeter of Lake Bracciano and analysed for their nitrogen stable isotope signatures. Furthermore, some stones were moved from an unpolluted site to a polluted one in order to verify the effect on the nitrogen signature of the epilithic association. The epilithon’s δ 15 N signatures provided strong evidence of the space-time variability of N inputs. The differing quality of nitrogen loads was reflected in high isotopic variation within the lake, especially at the beginning of summer (1.7‰ ≤ δ 15 N ≤ 13.3‰), while in winter, when anthropogenic pressure was lowest, the δ 15 N signature variation was less accentuated (3.1‰ ≤ δ 15 N ≤ 7.6‰). At all sampling times, spatial variability was found to be related to the various human activities along the lake shore (especially tourism and agriculture), while seasonal variation at all sampling sites was related to the intensity of anthropogenic pressures (higher in summer and lower in winter). Our results showed that epilithic algal associations and the physicochemical properties of the water did not influence the δ 15 N signature, which in contrast was strongly related to the site-specific effect of human activities around the lake. Thus, the distribution of δ 15 N across space and time can be used to direct nutrient reduction strategies in the region and can assist in monitoring the effectiveness of environmental protection measures. [ABSTRACT FROM AUTHOR]