Diagnostic Accuracy of Machine Learning AI Architectures in Detection and Classification of Lung Cancer: A Systematic Review.

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.

Concurrent Sphingomonas paucimobilis and Mycobacterium tuberculosis Meningitis in an Immunocompromised Patient: A Rare Case Report and Comprehensive Review of Literature.

Sphingomonas paucimobilis is a gram-negative bacillus that is widely distributed in the environment but rarely causes infections in humans. Meningitis caused by S. paucimobilis is an extremely rare clinical entity with very few reported cases in the literature. The clinical presentation and management of S. paucimobilis meningitis are not well established, and further research is needed to better understand this rare infection. Therefore, the goal of this study was to present probably the only case of meningitis caused by co-infection with S. paucimobilis and Mycobacterium tuberculosis and to describe the diagnostic and therapeutic challenges encountered, in correlation with the other very few reported cases of S. paucimobilis meningitis. A 64-year-old male farmer residing in a rural area was admitted with symptoms of severe headache, somnolence, and confusion. He had several comorbidities, including adrenal insufficiency, duodenal ulcer, and hypercholesterolemia. Lumbar puncture showed elevated leukocyte counts, glucose, and a marked rise of cerebrospinal fluid (CSF) proteins, indicating bacterial meningitis, which was confirmed by CSF culture that isolated S. paucimobilis and Mycobacterium tuberculosis. Antituberculosis therapy was initiated with isoniazid (300 mg/day), rifampicin (600 mg/day), pyrazinamide (2000 mg/day), and streptomycin (1 g/day). Ceftriaxone was introduced nine days later, after CSF culture grew S. paucimobilis, and was discharged without complications after 40 days of hospitalization. The literature search revealed a total of 12 published cases of S. paucimobilis meningitis in patients ranging from two months old to 66 years old. Among these cases, eight (66%) reported a favorable outcome, while two (17%) cases resulted in a poor outcome, and two (17%) were fatal. It was observed among the 13 identified cases (including ours) that the CSF white blood cell count had an average of 178.9 × 103/mm3, an average glucose level of 33.0 mg/dL, and an average protein count of 294.2 mg/dL. Most cases improved appropriately under antibiotic therapy with intravenous ceftriaxone, Meropenem, and Vancomycin. In conclusion, although extremely rare, S. paucimobilis meningitis has good outcomes even in immunocompromised patients with appropriate antibiotic therapy and close monitoring, while the diagnosis should not be excluded even in immunocompetent patients.

Laboratory Findings and Clinical Outcomes of ICU-admitted COVID-19 Patients: A Retrospective Assessment of Particularities Identified among Romanian Minorities.

The Roma population accounts for over 3% (approximately 10 to 15 million) of Romania's permanent population, and it represents one of Europe's most impoverished populations. Due to poverty and unemployment, Romania's Roma minority may have diminished access to healthcare and preventive medicine. The limited existing evidence suggests that the European Roma group has been at a higher risk of becoming ill and dying during the pandemic owing to their lifestyle choices, socioeconomic circumstances, and genetic pathophysiological traits. As a result, the purpose of the present research was to investigate the link between the inflammatory markers implicated and the clinical progression of COVID-19 in Roma patients who were brought to the intensive care unit. We considered 71 Roma patients admitted to the ICU with SARS-CoV-2 infection and 213 controls from the general population with the same inclusion criteria. The body mass index of patients was statistically significantly higher among Roma patients, with more than 57% being overweight, compared with 40.7% in the control group. Frequent smoking was more prevalent in patients of Roma ethnicity admitted to the ICU and the number of comorbidities. We observed a significantly higher proportion of severe imaging features at admission in the group of cases, although this difference may have been associated with the higher prevalence of smoking in this group. The mean duration of hospitalization was longer by 1.8 days than the control group. Elevated ESR levels were observed in 54.0% of Roma patients at admission, compared with 38.9% in the control group. Similarly, 47.6% of them had elevated CRP levels. IL-6 increased significantly at the time of ICU admission, similarly to the significant rise in the CRP levels, compared with the general population. However, the proportion of intubated patients and mortality did not differ significantly. On multivariate analysis, the Roma ethnicity significantly influenced the CRP (ß = 1.93, p-value = 0.020) and IL-6 (ß = 1.85, p-value = 0.044). It is necessary to plan different healthcare strategies aimed at special populations, such as the Roma ethnicity, to prevent the reduced disparities presented in in this study.

A Retrospective Assessment of Laboratory Findings and Cytokine Markers in Severe SARS-CoV-2 Infection among Patients of Roma Population.

Growing research data suggests that the severity of COVID-19 is linked with higher levels of inflammatory mediators, such as cytokines, chemokines, tumor necrosis factor, C-reactive protein, ferritin, and D-dimers. In addition, it was evident from the existing research data that the severity of SARS-CoV-2 infection differs according to independent risk factors such as race and ethnicity. Some scarce evidence shows that the European Roma community is likely to be at an elevated risk of illness and death during the pandemic due to their lifestyle, social factors, and economics. Assuming that precautions must be taken to protect this population from coronavirus infections and from widening existing disparities in comparison with the Romanian ethnic population, the current study aimed to observe the clinical evolution of the Roma patients with severe SARS-CoV-2 infection in correlation with the laboratory findings and inflammatory markers involved. After calculating the sample size requirements, we included 83 Roma patients admitted to the hospital with severe COVID-19 and 236 patients of Romanian ethnicity with the same inclusion criteria. Patients were selected from the period stretching from March 2020 to December 2021, before COVID-19 vaccines were introduced. Compared with the general population, the Roma patients with severe SARS-CoV-2 infection had a higher unemployment rate (39.8%), and most of them were residing in rural regions (65.4%). There were significantly more overweight patients in the Roma group than in the control group (57.8% vs. 40.7%), and it was also observed that high blood pressure and diabetes mellitus were significantly more prevalent in the Roma patients. They had significantly longer mean duration of hospitalization was significantly longer in the group of Roma patients (18.1 days vs. 16.3 days). IL-6 and CRP levels were significantly more elevated during admission in the group of Roma patients (43.4% vs. 28.4%); however, IL-6 levels normalized at discharge, but ESR remained high. Although ICU admissions were significantly more frequent in this group, the mortality rate was not significantly higher than in the general population. It is necessary to plan different healthcare strategies aimed at special populations, such as the Roma ethnicity to prevent disparities in negative outcomes reflected in this study. The results imply that community-health collaborations between organizations of minority groups and healthcare professionals can mitigate the disproportionate consequences of the pandemic on Roma.

Individual Characteristics as Prognostic Factors of the Evolution of Hospitalized COVID-19 Romanian Patients: A Comparative Observational Study between the First and Second Waves Based on Gaussian Graphical Models and Structural Equation Modeling.

This study examines the role played by individual characteristics and specific treatment methods in the evolution of hospitalized patients with coronavirus disease 2019 (COVID-19), through the lens of an observational study performed in a comparative approach between the first and second waves of coronavirus pandemic in Romania. The research endeavor is configured on a two-fold approach, including a detailed observation of the evolution of 274 hospitalized patients with COVID-19 (145 in the first wave and 129 in the second wave of infection) according to specific treatment methods applied and patients' individual features, as well as an econometric (quantitative) analysis through structural equation modeling and Gaussian graphical models designed to acknowledge the correlations and causal relationship between all considered coordinates. The main results highlight that the specific treatment methods applied had a positive influence on the evolution of COVID-19 patients, particularly in the second wave of coronavirus pandemic. In case of the first wave of COVID-19 infection, GGM results entail that there is a strong positive correlation between the evolution of the patients and the COVID-19 disease form, which is further positively correlated with the treatment scheme. The evolution of the patients is strongly and inversely correlated with the symptomatology and the ICU hospitalization. Moreover, the disease form is strongly and inversely correlated with oxygen saturation and the residence of patients (urban/rural). The symptomatology at first appearance also strongly depends on the age of the patients (positive correlation) and of the fact that the patient is a smoker or non-smoker and has other comorbidities. Age and gender are also important credentials that shape the disease degree and patient evolution in responding to treatment as well, our study attesting strong interconnections between these coordinates, the form of disease, symptomatology and overall evolution of the patients.