The humoral response after vaccination was evaluated in 1248 individuals who received different COVID-19 vaccine schedules. The study compared subjects primed with adenoviral ChAdOx1-S (ChAd) and boosted with BNT162b2 (BNT) mRNA vaccines (ChAd/BNT) to homologous dosing with BNT/BNT or ChAd/ChAd vaccines. Serum samples were collected at two, four and six months after vaccination, and anti-Spike IgG responses were determined. The heterologous vaccination induced a more robust immune response than the two homologous vaccinations. ChAd/BNT induced a stronger immune response than ChAd/ChAd at all time points, whereas the differences between ChAd/BNT and BNT/BNT decreased over time and were not significant at six months. Furthermore, the kinetic parameters associated with IgG decay were estimated by applying a first-order kinetics equation. ChAd/BNT vaccination was associated with the longest time of anti-S IgG negativization and with a slow decay of the titer over time. Finally, analyzing factors influencing the immune response by ANCOVA analysis, it was found that the vaccine schedule had a significant impact on both the IgG titer and kinetic parameters, and having a Body Mass Index (BMI) above the overweight threshold was associated with an impaired immune response. Overall, the heterologous ChAd/BNT vaccination may offer longer-lasting protection against SARS-CoV-2 than homologous vaccination strategies.

Artificial intelligence (AI) models are promising tools for predicting antimicrobial susceptibility in gram-negative bloodstream infections (GN-BSI). Single-center study on hospitalized patients with GN-BSI, over 7-year period, aimed to predict resistance to fluoroquinolones (FQ-R), third generation cephalosporins (3GC-R), beta-lactam/beta-lactamase inhibitors (BL/BLI-R) and carbapenems (C-R) was performed. Analyses were carried out within a machine learning framework, developed using the scikit-learn Python package. Overall, 2552 patients were included. Enterobacterales accounted for 85.5% of isolates, with E. coli, Klebsiella spp, and Proteus spp being most common. Distribution of resistance was FQ-R 48.6%, 3GC-R 40.1%, BL/BLI-R 29.9%, and C-R 16.9%. Models’ validation showed good performance predicting antibiotic resistance for all four resistance classes, with the best performance for C-R (AUC-ROC 0.921 ± 0.013). The developed pipeline has been made available (https://github.com/EttoreRocchi/ResPredAI), along with documentation for running the same workflow on a different dataset, to account for local epidemiology and clinical features.

Since the beginning of the COVID-19 pandemic, a large number of epidemiological models have been developed. The principal objective of the present study is to provide a new six-compartment model for the COVID-19 pandemic, which takes into account both the possibility of re-infection and the differentiation between asymptomatic and symptomatic infected subjects. The model, denoted as θ-SI(R)D, is a six-compartment model, described by as many ordinary differential equations. The six compartments are denoted as Susceptible ($S$), Symptomatic Infected ($I_s$), Asymptomatic Infected ($I_a$), Recovered from Asymptomatic fraction ($R_a$), Recovered from Symptomatic fraction ($R_s$), and Deceased ($D$). Such a model has no analytical solutions, so we performed both a simulation and a model validation ($R^2=0.829)$. Based on the results of our simulations (and, on the other hand, on the results of most of the models in the scientific literature), it is possible to draw the reasonable conclusion that the epidemic tends, even without vaccination, to a steady state.

Many attempts to build epidemic models of the current Covid-19 epidemic have been made in the recent past. However, only models postulating permanent immunity have been proposed. In this paper, we propose a SI(R) model in order to forecast the evolution of the epidemic under the hypothesis of not permanent immunity. This model offers an analytical solution to the problem of finding possible steady states, providing the following equilibrium values: Susceptible about 17%, Recovered (including deceased and healed) ranging from 79 to 81%, and Infected ranging from 2 to 4%. However, it is crucial to consider that the results concerning the recovered, which at first glance are particularly impressive, include the huge proportion of asymptomatic subjects. On the basis of these considerations, we analyse the situation in the province of Pesaro-Urbino, one of the main outbreaks of the epidemic in Italy.

This study investigates the use of Neural Ordinary Differential Equations (NODEs) as an alternative to traditional compartmental models and Nonlinear Mixed-Effects (NLME) models for drug concentration prediction in pharmacokinetics. Unlike standard models that rely on strong assumptions and often struggle with high-dimensional covariate relationships, NODEs offer a data-driven approach, learning differential equations directly from data while integrating covariates. To evaluate their performance, NODEs were applied to a real-world Dalbavancin pharmacokinetic dataset comprising 218 patients and compared against a two-compartment model and an NLME within a cross-validation framework, which ensures an evaluation of robustness. Given the challenge of limited data availability, a data augmentation strategy was employed to pre-train NODEs. Their predictive performance was assessed both with and without covariates, while model explainability was analyzed using Shapley additive explanations (SHAP) values. Results show that, in the absence of covariates, NODEs performed comparably to state-of-the-art NLME models. However, when covariates were incorporated, NODEs demonstrated superior predictive accuracy. SHAP analyses further revealed how NODEs leverage covariates in their predictions. These results establish NODEs as a promising alternative for pharmacokinetic modeling, particularly in capturing complex covariate interactions, even when dealing with sparse and small datasets, thus paving the way for improved drug concentration predictions and personalized treatment strategies in precision medicine.

Background: Multidrug-resistant Klebsiella pneumoniae represents a significant challenge in healthcare settings, prompting numerous studies on the rapid detection of antimicrobial resistance. Mass spectrometry has been recently integrated into routine laboratory diagnostics, providing highly sensitive results for pathogen identification. Furthermore, previously published studies have demonstrated its potential application in predicting antimicrobial resistance. Materials and methods: The study collected 686 clinical isolates of K. pneumoniae from three Italian hospitals and used their MALDI-TOF mass spectra as input to machine learning models for predicting susceptibility profiles to amikacin and meropenem, which were selected as the most represented antibiotic molecules within the aminoglycoside and carbapenem classes, commonly used for the treatment of K. pneumoniae infections. After preprocessing, K. pneumoniae spectra were fed to machine learning classifiers within a nested cross-validation framework. Several performance metrics were computed to compare models and identify the most appropriate one for each antibiotic. Given the multicentric nature of the study, a batch-effect correction step was applied to reduce site-specific variability using the in-house developed Python package combatlearn (available on GitHub: https://github.com/EttoreRocchi/combatlearn ). Results: The XGBoost model achieved the best performance for both antibiotics (AUROC = 0.822 ± 0.028 for amikacin; AUROC = 0.887 ± 0.019 for meropenem). A per-site performance analysis revealed that, while performances’ variability was inherently linked to each center’s sample size, combatlearn -based harmonization effectively aligned mean AUROC values across sites. Conclusions: Our study demonstrates the capability of MALDI-TOF mass spectra to predict amikacin and meropenem resistance in K. pneumoniae directly from clinical spectra, supporting its potential as a rapid and cost-effective approach for both antimicrobial resistance surveillance through machine learning models and clinical decision support in routine microbiology practice.