The application of artificial intelligence (AI) in diagnostic imaging has gained significant interest in recent years, particularly in lung cancer detection. This systematic review aims to assess the accuracy of machine learning (ML) AI algorithms in lung cancer detection, identify the ML architectures currently in use, and evaluate the clinical relevance of these diagnostic imaging methods. A systematic search of PubMed, Web of Science, Cochrane, and Scopus databases was conducted in February 2023, encompassing the literature published up until December 2022. The review included nine studies, comprising five case–control studies, three retrospective cohort studies, and one prospective cohort study. Various ML architectures were analyzed, including artificial neural network (ANN), entropy degradation method (EDM), probabilistic neural network (PNN), support vector machine (SVM), partially observable Markov decision process (POMDP), and random forest neural network (RFNN). The ML architectures demonstrated promising results in detecting and classifying lung cancer across different lesion types. The sensitivity of the ML algorithms ranged from 0.81 to 0.99, while the specificity varied from 0.46 to 1.00. The accuracy of the ML algorithms ranged from 77.8% to 100%. The AI architectures were successful in differentiating between malignant and benign lesions and detecting small-cell lung cancer (SCLC) and non-small-cell lung cancer (NSCLC). This systematic review highlights the potential of ML AI architectures in the detection and classification of lung cancer, with varying levels of diagnostic accuracy. Further studies are needed to optimize and validate these AI algorithms, as well as to determine their clinical relevance and applicability in routine practice.

Sepsis, a life-threatening condition arising from a dysregulated immune response to infection, is a significant health burden globally. Interleukin-6 (IL-6), an inflammatory cytokine produced by immune cells as a response to infection and tissue damage, plays a key role in the pathogenesis of sepsis. This systematic review and meta-analysis aimed to investigate the association of the baseline plasma levels of IL-6, and the dynamic change in these levels over a timespan of 96 h, with short-term mortality. A systematic literature search was conducted across multiple databases. Studies were included if they assessed the independent prognostic value of IL-6 in adult sepsis patients, used well-defined sepsis criteria, and reported at least one IL-6 measurement. Pooled effect estimates for the association between IL-6 and 28–30-day mortality were determined using logistic regression and AUROC analysis. Thirty-one studies, encompassing 4566 patients, were included. While baseline IL-6 levels and 96 h IL-6 clearance were not significantly associated with mortality risk (pooled OR 1.001, 95% CI 0.999–1.003 and 1.019, 95% CI 0.925–1.112, respectively), AUROC analysis indicated moderate-to-good discriminatory power for both baseline (0.701, 95% CI 0.660–0.742) and 96 h IL-6 clearance (0.828, 95% CI 0.736–0.919) in predicting 28-day mortality. While not a strong independent predictor, IL-6 demonstrates some discriminatory ability, suggesting its potential value in conjunction with other biomarkers.

Clinical trials for COVID-19 vaccines initially excluded pregnant women due to safety concerns, and when the vaccines were authorized for emergency use, they were not recommended for this population. However, observational studies discovered that pregnant women infected with COVID-19 have higher risks of negative pregnancy and delivery outcomes compared to non-pregnant women, raising the question of the risks–benefits of administering COVID-19 vaccines to pregnant women. By mid-2021, there was general consensus on the relative safety of COVID-19 vaccination during pregnancy; therefore, it is critical to investigate the safety issues related to these vaccines, considering the increasing acceptance among pregnant women. To address these concerns, we developed a research project to study the short-term effects and outcomes of COVID-19 vaccination during the first trimester of pregnancy. Our research followed an observational retrospective design for 12 months from the beginning of the vaccination campaign, and included 124 cases of spontaneous abortions and 927 ongoing pregnancies. The odds of spontaneous abortion were non-significant for both versions of the mRNA vaccine (Pfizer BNT162b2 AOR = 1.04, CI = 0.91–1.12; Moderna mRNA-1273 AOR = 1.02, CI = 0.89–1.08). Overall, our data indicated that the risk of spontaneous abortion after mRNA COVID-19 immunization during the first trimester of pregnancy is commensurate with the predicted risk in non-vaccinated pregnant women. These findings contribute to the growing body of information regarding the safety of mRNA COVID-19 vaccination during pregnancy.

The Omicron (B.1.1.529) variant of the severe acute respiratory syndrome Coronavirus 2 (SARS-CoV-2) had an increased rate of spreading among the general population. Although this virus mutation resulted in milder symptoms, those on the vulnerable side of the population are still in danger of developing severe symptoms. Thus, this systematic review focused on identifying the clinical outcomes of older age patients (>65) that are hospitalized with the SARS-CoV-2 Omicron variant. The research was conducted using four electronic databases (PubMed, Scopus, Web of Science, and ProQuest Central), with a search query in December 2022 that comprised the duration of the COVID-19 pandemic. The inclusion criteria comprised (1) a population of patients older than 65 years, (2) a history of hospitalization for SARS-CoV-2 infection, and (3) infection with Omicron B.1.1.529 variant. The initial search generated 295 articles, out of which six were included in the systematic review, and a total of 7398 patients. The main findings were that when looking at the elderly population, the mortality and hospitalization rates remained high. This is because older people are more vulnerable and have more comorbidities that interfere with the virus’s progress. However, there is inconsistency in mortality rates, since the data reported by the included studies had different selection criteria based on the severity of the COVID-19 infection. Although no statistically significant differences were found between the unvaccinated and vaccinated groups, patients who got booster doses of vaccination had a lower likelihood of developing severe symptoms, serving as a protective factor for this population.

During the COVID-19 pandemic, it was observed that patients with heart disease are more likely to be hospitalized and develop severe COVID-19. Cardiac disease takes the top position among patient comorbidities, heart failure (HF) prevalence reaching almost 5% in the general population older than 35 years in Romania. This retrospective study aimed to determine the potential use of the NYHA classification for HF in hospitalized patients with COVID-19 as prognostic tool for in-hospital mortality, length of hospitalization, and probability of rehospitalization for HF decompensation. We observed that patients with advanced HF had a history of significantly more comorbid conditions that are associated with worse disease outcomes than the rest of patients classified as NYHA I and II. However, regardless of existing diseases, NYHA III, and, especially, NYHA IV, patients were at greatest risk for mortality following SARS-CoV-2 infection. They required significantly longer durations of hospitalization, ICU admission for mechanical ventilation, and developed multiple severe complications. NYHA IV patients required a median duration of 20 days of hospitalization, and their in-hospital mortality was as high as 47.8%. Cardiac biomarkers were significantly altered in patients with SARS-CoV-2 and advanced HF. Although the study sample was small, all patients with NYHA IV who recovered from COVID-19 required a rehospitalization in the following month, and 65.2% of the patients at initial presentation died during the next six months. The most significant risk factor for mortality was the development of severe in-hospital complications (OR = 4.38), while ICU admission was the strongest predictor for rehospitalization (OR = 5.19). Our result highlights that HF patients continue to be vulnerable post SARS-CoV-2 infection. Physicians and policymakers should consider this population’s high likelihood of hospital readmissions when making discharge, hospital capacity planning, and post-discharge patient monitoring choices.

Magnesium may contribute to the immune response during and after SARS-CoV-2 infection by acting as a cofactor for immunoglobulin production and other processes required for T and B cell activity. Considering magnesium as a recommended dietary supplement during pregnancy and the possible role of magnesium deficiency in COVID-19 and its complications, the current study sought to determine the effect of magnesium and magnesium-containing nutritional supplements on the immune response following SARS-CoV-2 infection in pregnant women, as well as to observe differences in pregnancy outcomes based on the supplements taken during pregnancy. The study followed a cross-sectional design, where patients with a history of SARS-CoV-2 infection during their pregnancy were surveyed for their preferences in nutritional supplementation and their profile compared with existing records from the institutional database. A cohort of 448 pregnant women with COVID-19 during 22 months of the pandemic was assembled, out of which 13.6% took a magnesium-only supplement, and 16.5% supplemented their diet with a combination of calcium, magnesium, and zinc. Around 60% of patients in the no-supplementation group had the SARS-CoV-2 anti-RBD lower than 500 U/mL, compared with 50% in those who took magnesium-based supplements. A quantity of magnesium >450 mg in the taken supplements determined higher levels of antibody titers after COVID-19. Low magnesium dosage (<450 mg) was an independent risk factor for a weak immune response (OR-1.25, p-value = 0.003). The observed findings suggest supplementing the nutritional intake of pregnant women with magnesium-based supplements to determine higher levels of SARS-CoV-2 anti-RBD antibodies, although causality remains unclear.