BACKGROUND. The COVID-19 vaccines currently in use require 2 doses to achieve optimal protection. Currently, there is no indication as to whether individuals who have been exposed to SARS-CoV-2 should be vaccinated, or whether they should receive 1 or 2 vaccine doses. METHODS. We tested the antibody response developed after administration of the Pfizer/BioNTech vaccine in 124 health care professionals, of whom 57 had a previous history of SARS-CoV-2 exposure with or without symptoms. RESULTS. Postvaccine antibodies in SARS-CoV-2–exposed individuals increased exponentially within 5 to 18 days after the first dose compared to naive subjects (P < 0.0001). In a multivariate linear regression (LR) model we showed that the antibody response depended on the IgG prevaccine titer and on the exposure to SARS-CoV-2. In symptomatic SARS-CoV-2–exposed individuals, IgG reached a plateau after the second dose, and those who voluntarily refrained from receiving the second dose (n = 7) retained their antibody response. Gastrointestinal symptoms, muscle pain, and fever markedly positively correlated with increased IgG responses. By contrast, all asymptomatic/paucisymptomatic and unexposed individuals showed an important increase after the second dose. CONCLUSION. One vaccine dose is sufficient in symptomatic SARS-CoV-2–exposed subjects to reach a high titer of antibodies, suggesting no need for a second dose, particularly in light of current vaccine shortage. TRIAL REGISTRATION. ClinicalTrials.gov NCT04387929. FUNDING. Dolce & Gabbana and the Italian Ministry of Health (Ricerca corrente).

Objective Gastrointestinal (GI) bleeding commonly requires intensive care unit (ICU) in cases of potentialhaemodynamiccompromise or likely urgent intervention. However, manypatientsadmitted to the ICU stop bleeding and do not require further intervention, including blood transfusion. The present work proposes an artificial intelligence (AI) solution for the prediction of rebleeding in patients with GI bleeding admitted to ICU. Methods A machine learning algorithm was trained and tested using two publicly available ICU databases, the Medical Information Mart for Intensive Care V.1.4 database and eICU Collaborative Research Database using freedom from transfusion as a proxy for patients who potentially did not require ICU-level care. Multiple initial observation time frames were explored using readily available data including labs, demographics and clinical parameters for a total of 20 covariates. Results The optimal model used a 5-hour observation period to achieve an area under the curve of the receiving operating curve (ROC-AUC) of greater than 0.80. The model was robust when tested against both ICU databases with a similar ROC-AUC for all. Conclusions The potential disruptive impact of AI in healthcare innovation is acknowledge, but awareness of AI-related risk on healthcare applications and current limitations should be considered before implementation and deployment. The proposed algorithm is not meant to replace but to inform clinical decision making. Prospective clinical trial validation as a triage tool is warranted.

Objective. Extraction of temporal features of neuronal activity from electrophysiological data can be used for accurate classification of neural networks in healthy and pathologically perturbed conditions. In this study, we provide an extensive approach for the classification of human in vitro neural networks with and without an underlying pathology, from electrophysiological recordings obtained using a microelectrode array (MEA) platform. Approach. We developed a Dirichlet mixture (DM) Point Process statistical model able to extract temporal features related to neurons. We then applied a machine learning algorithm to discriminate between healthy control and pathologically perturbed in vitro neural networks. Main Results. We found a high degree of separability between the classes using DM point process features (p-value <0.001 for all the features, paired t-test), which reaches 93.10 of accuracy (92.37 of ROC AUC) with the Random Forest classifier. In particular, results show a higher latency in firing for pathologically perturbed neurons (43 ± 16 ms versus 67 ± 31 ms, μ I G feature distribution). Significance. Our approach has been successful in extracting temporal features related to the neurons’ behaviour, as well as distinguishing healthy from pathologically perturbed networks, including classification of responses to a transient induced perturbation.

Background: Differentiating radionecrosis from neoplastic progression after stereotactic radiosurgery (SRS) for brain metastases is a diagnostic challenge. Previous studies have often been limited by datasets lacking histologically confirmed diagnoses. This study aimed to develop automated models for distinguishing radionecrosis from disease progression on brain MRI, utilizing cases with definitive histopathological confirmation. Methods: This multi-center retrospective study included patients who underwent surgical resection for suspected brain metastasis progression after SRS. Presurgical FLAIR and postcontrast T1 (T1w-ce) were segmented using a convolutional neural network (CNN) and compared with manual segmentation by means of Dice score. Radiomics features were extracted from each lesion, and a Random Forest model was trained on 70% of the internal dataset and evaluated on the remaining 30% and the complete external dataset. A 3DResNet-CNN was trained on the same split dataset. Validation was performed on the external dataset. Postsurgical histology was available for all cases. Results: One hundred and twenty four brain metastases were included (104 from center 1 and 20 from center 2). Sole radionecrosis was histologically detected in 34 cases (27.4%). In the internal dataset, univariate and multivariate analysis identified 131 significantly different radiomics features, including GLDM_DNUN and GLDM_SDE within the enhancing area on the T1w-ce. On the external test dataset, the Random Forest model and the 3DResNet-CNN yielded accurate results in terms of accuracy (80.0%, 85.0%), AUROC (0.830, 0.893) and sensitivity (92.8%, 100%) in radionecrosis prediction, respectively. Conclusion: Artificial intelligence could be employed to differentiate between radionecrosis and brain metastasis progression upon SRS, potentially reducing unnecessary surgical interventions.

In an observational study, we analyzed 1293 healthcare workers previously infected with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), of which 34.1% developed postacute sequelae of SARS-CoV-2 infection (also known as long COVID). Using a multivariate logistic regression model, we demonstrate that the likelihood of developing long COVID in infected individuals rises with the increasing of duration of infection and that 3 doses of the BNT162b2 vaccine are protective, even during the Omicron wave.

The advent of vaccines against SARS-CoV-2 has drastically reduced the level of hospitalization with severe COVID-19 disease in infected individuals. However, the diffusion of variants of concern still challenge the protection conferred by vaccines raised against the wild-type form of the virus. Here, we have characterized the antibody response to the BNT162b2 (Comirnaty) mRNA vaccine in patients infected with the Omicron variant. We analyzed a population of 4354 vaccinated healthcare workers (HCW) from 7 different hospitals in Italy and monitored infection with SARS-CoV-2 Omicron. We correlated infection with the antibody response after vaccination. We found that a lower level of IgG, younger age, and the presence of allergies correlate with increased infection during the Omicron wave, and that infections correlate with wild-type spike protein antibody titers below 350 BAU/mL. These results support the necessity of a fourth booster dose, particularly for individuals with lower levels of antibodies.