Pneumonia Disease Research Articles

Exploring outcomes in hospitalized patients with COVID-19 based on nutritional status: Comparing those with and without a cancer diagnosis.

e23068 Background: This study explores how nutritional status impacts COVID-19 outcomes, particularly in patients with cancer. Obesity is known to heighten risk of adult respiratory distress syndrome in COVID-19, malnutrition and its associated effects related to the immune response, respiratory compromise, debility, and other adverse outcomes has not been well defined in this patient population. Methods: In this retrospective cohort study, we examined data from the Charleston Area Medical Center’s (CAMC) COVID-19 Registry, involving 5,479 adult, symptomatic, PCR-positive COVID-19 hospitalized patients (3/1/20 to 1/20/24). Low nutritional status (LNS) was defined as Body Mass Index (BMI) < 18.5 kg/m² or serum albumin < 3.5g/dL). Demographics, comorbidities, lab values, treatments, and outcomes were assessed. Propensity score matching (3:1) non-cancer patients vs those with an active cancer diagnosis was undertaken using sex, age, and BMI. SAS 9.4 was utilized for the analysis. The groups were compared using Chi-square/Fisher’s Exact tests for categorical variables and t-tests for continuous variables. Multivariate analysis was utilized to determine predictors of adverse outcomes. Results: A cohort of 1,146 non-cancer and 382 active cancer patients were included in the study. The LNS subgroup had a higher frequency of active cancer (29.2% vs 19.3%, p < 0.001), higher rates of diabetes (27.0% vs17.8%, p = 0.03) and chronic kidney disease (18.8% vs 11.7%, p = 0.02). They had greater frequencies of abnormal ferritin levels (57.8% vs 42.7%, p < 0.001), CRP levels > 3 mg/L (96.6% vs 90.3%, p < 0.001), and elevated procalcitonin levels > 0.05 ng/mL (71.2% vs 50.1%, p < 0.001). LNS patients had a higher mortality rate (22.3% vs 9.7%, p < 0.001), a higher need for mechanical ventilation (19.3% vs 9.5%, p < 0.001), and intensive care unit (ICU) admission (35.7% vs 19.5%, p < 0.001. Predictors of mortality included LNS (OR = 2.2, 95%CI [1.5-3.2], p < 0.001), an active cancer diagnosis (OR = 1.7, 95% CI [1.2-2.6], p = 0.003), chronic kidney disease (OR = 1.8 95%CI [1.3-2.5], p = 0.004) and concurrent bacterial pneumonia (OR = 4.9 95%CI [3.3-7.2], p < 0.001). Conclusions: In patients with COVID-19, those with LNS had higher rates of co-morbid conditions including active cancer, higher rates of elevated inflammatory markers, mechanical ventilation, ICU admission, and mortality. Predictors of mortality included concurrent bacterial pneumonia, cancer diagnosis and chronic kidney disease, with LNS increasing the risk of mortality by more than two-fold. These results support the recommendation of early nutritional assessment and a multi-disciplinary approach to aggressive nutritional support in the COVID-19 patient population particularly in those with a concurrent high-risk condition such as cancer.

Shufeng Jiedu capsule alleviates influenza A (H1N1) virus induced acute lung injury by regulating the lung inflammatory microenvironment

BackgroundDeath caused by respiratory tract infection is one of the leading causes of death in the world today. Shufeng Jiedu Capsule (SFJDC) is a traditional Chinese medicine that has been widely used clinically for coronavirus disease 2019 (COVID-19), H1N1 influenza virus pneumonia and other diseases. Its pharmacological effect is to inhibit inflammation and improve the body's ability to clear viruses. However, the mechanism of SFJDC in the treatment of viral pneumonia, especially its effect on the inflammatory-immune microenvironment of lung tissue remains unclear. MethodsMice with H1N1 influenza virus pneumonia were used as a model to verify the efficacy of SFJDC through death protection, lung index, viral load, and HE staining of lung tissue. The levels of inflammatory cytokines and chemokines in lung tissue were investigated by multi-analyte immunoassay. The number and proportion of cells in peripheral blood were detected by blood routine. The percentage of infiltrating immune cells in lung tissue was detected by flow cytometry and immunofluorescence. ResultsSFJDC (2.2 g/kg·d−1 and 1.1 g/kg·d−1) increased survival rate (P＜0.01, P＜0.05), prolonged the survival period of mice, and alleviated the histopathological damage in lung (P＜0.01). SFJDC (2.2 g/kg·d−1, 1.1 g/kg·d−1 and 0.055 g/kg·d−1) increased body weight(P＜0.01, P＜0.05), improved activity status, reduced the lung index (P＜0.01, P＜0.05) and viral load (P＜0.01). SFJDC (2.2 g/kg·d−1 and 1.1 g/kg·d−1) reduced interleukin-1β (IL-1β), interleukin-18(IL-18), tumour necrosis factor α (TNF-α), monocyte chemoattractant protein (MCP), chemokine (C-X-C motif) ligand 1 (CXCL1) (P＜0.01, P＜0.05), and SFJDC (2.2 g/kg·d−1) increased IL-10 levels (P＜0.05) to regulate inflammation. SFJDC (2.2 g/kg·d−1) increased the percentages of CD4+ T cells (P＜0.01), CD8+ T cells (P＜0.05), and B cells(P＜0.05), and decreased F4/80+ macrophages (P＜0.05). ConclusionOur findings indicated that SFJDC could inhibit inflammation and lung injury while maintaining the function of the adaptive immune response mediated by T and B cells, and promote the clearance of the virus, thereby treating influenza A (H1N1) virus-induced pneumonia.

Dyspnea management in patients with pneumonia and coronary artery disease: A case study

Background: Cardiovascular disease, particularly Coronary Artery Disease (CAD), is strongly linked to pneumonia. Patients suffering from both pneumonia and CAD frequently experience dyspnea as a symptom. Dyspnea, caused by both conditions, can significantly impact the patient's quality of life. Consequently, it is crucial to address and manage dyspnea in individuals with pneumonia and CAD. Purpose: To provide a thorough overview of managing dyspnea in patients with pneumonia and CAD in public hospitals in West Java, Indonesia. Method: Employing a case study methodology using a nursing care approach, encompassing nursing assessment, data analysis, diagnosis, intervention, implementation, evaluation, and documentation. The assessment indicated that the patient experienced shortness of breath, with a blood pressure of 145/86 mmHg, a respiratory rate of 24 breaths per minute, a pulse rate of 95 beats per minute, and an oxygen saturation level of 88%. The patient received 5 liters per minute of oxygen via a nasal cannula, and their body temperature measured 36.4ºC. Results: In this case study, dyspnea management involved positioning the patient, administering oxygen therapy in stages, and providing pharmacological treatments, including diuretics and antibiotics. Additional therapies included respiratory muscle training and effective cough exercises. These interventions successfully reduced the patient's respiratory rate to 18 breaths per minute and increased their oxygen saturation to 97% with a nasal cannula. Additionally, the patient's Medical Research Council (MRC) dyspnea scale score decreased to 1 out of 5. Conclusion: Nursing care management that includes positioning the patient in a semi-Fowler's position while resting and a Fowler's position when awake, administering oxygen therapy in stages, providing pharmacological treatments such as diuretics and antibiotics, and conducting respiratory muscle training, can lower the breathing rate and alleviate symptoms of shortness of breath in patients with pneumonia and coronary artery disease.

Automated detection of COVID-19 and pneumonia diseases using data mining and transfer learning algorithms with focal loss from chest X-ray images

Pneumonia is a lung infection that produces severe inflammation, which can be caused by viruses, bacteria, or fungi. The global occurrence of pneumonia cases has been notably affected by the outbreak of Coronavirus Disease 2019 (COVID-19). Recent studies have demonstrated the capability of Deep Learning (DL) algorithms in detecting COVID-19 and pneumonia in medical images like X-rays. In this study, we employ four different Chest X-ray (CXR) datasets to evaluate four pre-trained Convolutional Neural Network (CNN) models: InceptionResNet V2, Inception V3, Xception, and MobileNet. These models were fine-tuned using either the Cross-Entropy (CE) loss function only for balanced datasets or separately using both the CE and Focal Loss (FL) functions for imbalanced datasets. For the first dataset, the InceptionResNet V2 model achieved the highest multi-classification accuracy of 88.63%. The superior model for the second and fourth datasets is Inception V3, with 94.35% and 97.67% multi-classification accuracy, respectively. For the third dataset, the best model is Xception, with a binary classification accuracy of 100.00%. Our results emphasize the significance of using the FL function in solving class imbalance problems in DL models. Additionally, it highlights the effectiveness of individual DL models in detecting different pneumonia infections using different CXR datasets.

Nasopharyngeal carriage of Streptococcus pneumoniae in Latin America and the Caribbean: A systematic review and meta-analysis.

Streptococcus pneumoniae is a leading cause of morbidity and mortality globally, causing bacteremic pneumonia, meningitis, sepsis, and other invasive pneumococcal diseases. Evidence supports nasopharyngeal pneumococcal carriage as a reservoir for transmission and precursor of pneumococcal disease. To estimate the pneumococcal nasopharyngeal burden in all age groups in Latin America and the Caribbean (LAC) before, during, and after the introduction of pneumococcal vaccine conjugate (PVC). Systematic literature review of international, regional, and country-published and unpublished data, together with reports including data from serotype distribution in nasopharyngeal carriage in children and adults from LAC countries following Cochrane methods. The protocol was registered in PROSPERO database (ID: CRD42023392097). We included 54 studies with data on nasopharyngeal pneumococcal carriage and serotypes from 31,803 patients. In children under five years old, carriage was found in 41% and in adults over 65, it was 26%. During the study period, children under five showed a colonization proportion of 34% with PCV10 serotypes and 45% with PCV13 serotypes. When we analyze the carriage prevalence of PCV serotypes in all age groups between 1995 and 2019, serotypes included in PCV10 and those included in PCV13, both showed a decreasing trend along analysis by lustrum. The data presented in this study highlights the need to establish national surveillance programs to monitor pneumococcal nasopharyngeal carriage to monitor serotype prevalence and replacement before and after including new pneumococcal vaccines in the region. In addition, to analyze differences in the prevalence of serotypes between countries, emphasize the importance of approaches to local realities to reduce IPD effectively.

WELLENS SYNDROME OR PNEUMONIA?

Abstract Background Wellens syndrome, also known as "left anterior descending coronary syndrome," is characterized by the appearance of T–wave changes recorded on the ECG and it is an ECG manifestation of critical proximal left anterior descending artery stenosis. Case Report A 65–year–old man from Bangladesh with a history of chronic ischemic heart disease and trivessel coronary artery disease following surgical revascularization (CABG 2007). Recent admission for NSTEMI (June 2022) with unchanged coronary angiography compared to the previous one. Comorbidities include peripheral arterial disease, type II diabetes with organ damage, and COPD with recent exacerbations. Last myocardial scintigraphy (2021) was positive for inducible myocardial ischemia in the posterolateral region. Admission due to fever, productive cough, and severe chest pain. Initial instrumental assessments revealed ST–segment alterations in inferior leads and V1–V2 with negative/isodiphasic T–waves, not present in previous ECG tracings. A slight troponin elevation with ischemic curve (101 → 303 → 277 → 155 pg/dl, normal range < 50 pg/dl) led to the diagnosis of NSTEMI. Echocardiogram showed concentric remodeling of the left ventricle with normal global systolic function and hypokinesia of the mid–basal inferior wall (noted). Additionally, chest CT revealed pulmonary consolidations in the right middle lobe and upper left lobe, prompting antibiotic therapy and bronchodilator inhalation. Arterial blood gas analysis: pH 7.45, pO2 83, Lactate 0.8, HCO3– 24, P/F 360. Coronary angiography showed an unchanged picture compared to the previous one (patent AMIS and AMID, good run–off in native branches, no distal stenosis at the anastomosis). Clinical symptoms, inflammatory indices, and myocardial damage markers clinically improved during hospitalization. Discharged after optimization of anti–ischemic therapy with DAPT and diagnosis of NSTEMI. However, ECG abnormalities persisted at discharge (negative T–waves in DI–aVL–V1–V2). Post–discharge cardiac MRI was requested. Conclusions Diagnostic hypotheses include, primarily, a possible type II myocardial infarction due to an ongoing pneumonia (although hypoxia/hypovolemia/hypotension sufficient to cause MI was never documented during hospitalization), MINOCA, or microcirculatory disease (functional tests such as iFR/FFR, ACh, IMR were not performed during coronary angiography), or a possible myocarditic outcome (pending MRI).

In Vivo Immune-Modulatory Activity of Lefamulin in an Influenza Virus A (H1N1) Infection Model in Mice

Lefamulin is a first-in-class systemic pleuromutilin antimicrobial and potent inhibitor of bacterial translation, and the most recent novel antimicrobial approved for the treatment of community-acquired pneumonia (CAP). It exhibits potent antibacterial activity against the most prevalent bacterial pathogens that cause typical and atypical pneumonia and other infectious diseases. Early studies indicate additional anti-inflammatory activity. In this study, we further investigated the immune-modulatory activity of lefamulin in the influenza A/H1N1 acute respiratory distress syndrome (ARDS) model in BALB/c mice. Comparators included azithromycin, an anti-inflammatory antimicrobial, and the antiviral oseltamivir. Lefamulin significantly decreased the total immune cell infiltration, specifically the neutrophils, inflammatory monocytes, CD4+ and CD8+ T-cells, NK cells, and B-cells into the lung by Day 6 at both doses tested compared to the untreated vehicle control group (placebo), whereas azithromycin and oseltamivir did not significantly affect the total immune cell counts at the tested dosing regimens. Bronchioalveolar lavage fluid concentrations of pro-inflammatory cytokines and chemokines including TNF-α, IL-6, IL-12p70, IL-17A, IFN-γ, and GM-CSF were significantly reduced, and MCP-1 concentrations were lowered (not significantly) by lefamulin at the clinically relevant ‘low’ dose on Day 3 when the viral load peaked. Similar effects were also observed for oseltamivir and azithromycin. Lefamulin also decreased the viral load (TCID50) by half a log10 by Day 6 and showed positive effects on the gross lung pathology and survival. Oseltamivir and lefamulin were efficacious in the suppression of the development of influenza-induced bronchi-interstitial pneumonia, whereas azithromycin did not show reduced pathology at the tested treatment regimen. The observed anti-inflammatory and immune-modulatory activity of lefamulin at the tested treatment regimens highlights a promising secondary pharmacological property of lefamulin. While these results require confirmation in a clinical trial, they indicate that lefamulin may provide an immune-modulatory activity beyond its proven potent antibacterial activity. This additional activity may benefit CAP patients and potentially prevent acute lung injury (ALI) and ARDS.

Qualitative and Quantitative Analysis of Chemical Components in Yinhua Pinggan Granule with High-Performance Liquid Chromatography Coupled with Q-Exactive Mass Spectrometry.

Yinhua Pinggan Granule (YPG) is an approved compounded traditional Chinese medicine (TCM) prescription for the treatment of cold, cough, viral pneumonia, and related diseases. Due to its complicated chemical composition, the material basis of YPG has not been systematically investigated. In this study, an analytical method based on high-performance liquid chromatography (HPLC) coupled with Q-Exactive mass spectrometry was established. Together with the help of a self-built compound database and Compound Discoverer software 3.1, the chemical components in YPG were tentatively identified. Subsequently, six main components in YPG were quantitatively characterized with a high-performance liquid chromatography-diode array detector (HPLC-DAD) method. As a result, 380 components were annotated, including 19 alkaloids, 8 organic acids, 36 phenolic acids, 27 other phenols, 114 flavonoids, 75 flavonoid glycoside, 72 terpenes, 11 anthraquinones, and 18 other compounds. Six main components, namely, chlorogenic acid, puerarin, 3'-methoxypuerarin, polydatin, glycyrrhizic acid, and emodin, were quantified simultaneously. The calibration curves of all six analytes showed good linearity (R2 > 0.9990) within the test ranges. The precision, repeatability, stability, and recovery values were all in acceptable ranges. In addition, the total phenol content and DPPH scavenging activity of YPG were also determined. The systematic elucidation of the chemical components in YPG in this study may provide clear chemical information for the quality control and pharmacological research of YPG and related TCM compounded prescriptions.

Silent pulmonary shadows

An elderly woman with a 1-year history of pulmonary shadows was admitted because of intermittent cough and sputum production for 2 months. Chest computed tomography (CT) scans showed bilateral consolidations and ground-glass opacities, with areas of low attenuation inside consolidative opacities on the mediastinal window. Previous history of radiotherapy for nasopharyngeal carcinoma and long-term use of a compound menthol nasal drops provided were important clues to the diagnosis. CT scan-guided needle lung biopsy and bronchoalveolar lavage were performed, and lipid-laden macrophages were confirmed in both bronchoalveolar lavage and lung tissue. Final diagnosis of exogenous lipoid pneumonia was made on the basis of her risk factors for aspiration, history of oil exposure, and classic radiological and histopathological features. Symptoms improved after discontinuation of causative exposure. It is important for clinicians to raise awareness of exogenous lipoid pneumonia and other aspiration lung diseases.

Antibiotic appropriateness at outpatient settings in Ethiopia: the need for an antibiotic stewardship programme.

Antibiotics are drugs of natural or synthetic origin used to treat various infections. The practice of excessive and inappropriate antibiotics use is the main global cause of bacterial resistance, which is one of the most serious global public health threats. It is estimated that about 50% of global antibiotic prescriptions are inappropriate. This study assesses the prevalence and pattern of inappropriate prescriptions of antibiotics amongst ambulatory care visits in Ethiopia. A facility-based, cross-sectional study with a quantitative approach was conducted amongst randomly selected prescriptions issued for outpatients from May to June 2022 at Debre Markos Specialized Comprehensive Hospital, Northwest Ethiopia. Descriptive statistics, such as frequencies and percentages, were computed. For group comparisons, χ2 and independent sample t-tests were computed. The statistical significance of the association was considered at p<0.05. A total of 2640 antibiotics were prescribed for patients in the outpatient setting with various bacterial infections via 911 prescriptions, of which 49.5% were non-compliant with the national treatment guideline. Guideline non-compliant prescriptions increased remarkably amongst patients in the outpatient setting diagnosed with community-acquired pneumonia (38.8% versus 30.1%; p=0.006) and peptic ulcer disease (14.9% versus 9%; p=0.006). Moreover, inappropriate prescription was significantly higher amongst patients taking amoxicillin/clavulanic acid (33.2% versus 48.2%; p<0.001) and cephalexin (17.8% versus 24.3%; p=0.016). Large proportions of antibiotic prescriptions for outpatients were non-compliant with the national treatment guideline, suggesting that prescribers need to give special attention to outpatients whilst ordering antibiotics such as amoxicillin/clavulanic acid and cephalexin. Antibiotic stewardship efforts to optimize outpatient antibiotic prescriptions and reduce the use of potentially inappropriate antibiotics are needed in Ethiopia.

Underlying Diseases Associated with Persistent Pneumonia in Children Aged 2 Months to 5 Years

Background: Persistent pneumonia in children pose a significant challenge to the pediatricians as there are underlying reasons of persistence. There are limited data on the underlying diseases predisposing to persistence of pneumonia in children. Objective: To identify the underlying diseases of persistent pneumonia in children. Methods: The cross sectional observational study was conducted at Bangladesh Shishu (Children) Hospital &amp; Institute from November, 2019 to October, 2020. Children 2 months to 5 years of age admitted with persistent pneumonia were analyzed to find out the underlying diseases. Results: Among 49 cases of persistent pneumonia, underlying disease could be determined in 41 (83.7%) cases. The diseases were cystic fibrosis 13 (26.5%), congenital heart disease 10 (20.4%), primary immunodeficiency 10 (20.4%), gastro-esophageal reflux disease 5 (10.2%), pulmonary tuberculosis 4 (8.1%) and congenital anomalies of respiratory tract 1 (2%). Conclusion: The most common underlying diseases of persistent pneumonia are cystic fibrosis, congenital heart disease, primary immunodeficiency followed by gastro-esophageal reflux disease, pulmonary tuberculosis and congenital anomalies of respiratory tract. J Bangladesh Coll Phys Surg 2024; 42: 114-119

A novel study of the impact of vaccination on pneumonia via fractional approach

Substantial advancements have been made in applying fractional calculus to understanding the epidemiology of viral diseases. However, it remains troubling that over 2,000,000 children, particularly those under the age of 5 and elderly individuals over 65, succumb to pneumonia annually in developing nations. This paper uses a deterministic SVEIR (susceptible, vaccinated, exposed, infected, and recovered) model to investigate pneumonia disease dynamics from a mathematical perspective. The governing model has been generalized from Caputo fractional derivatives, and the generalized Euler’s method has been used to calculate the approximate solution of the governing model. The dynamical systems theory examines the model’s stability analysis, basic reproduction number, and equilibrium points. The linearization method for spatial equilibrium and the Lyapunov functional method demonstrate that the model is locally asymptotic stable for disease-free equilibrium. Graphical results are showcased through MATLAB21 to illustrate the resolution of the problem. The research findings suggest that the disease will eventually disappear from the population if vaccination coverage rises over the necessary vaccination threshold. According to sensitivity analysis, the most sensitive factors are the transmission rate and the pace at which exposed individuals become contagious. According to the study, we must strengthen treatment effectiveness to prevent disease spreading.

High-resolution genomics identifies pneumococcal diversity and persistence of vaccine types in children with community-acquired pneumonia in the UK and Ireland

BackgroundStreptococcus pneumoniae is a global cause of community-acquired pneumonia (CAP) and invasive disease in children. The CAP-IT trial (grant No. 13/88/11; https://www.capitstudy.org.uk/) collected nasopharyngeal swabs from children discharged from hospitals with clinically diagnosed CAP, and found no differences in pneumococci susceptibility between higher and lower antibiotic doses and shorter and longer durations of oral amoxicillin treatment. Here, we studied in-depth the genomic epidemiology of pneumococcal (vaccine) serotypes and their antibiotic resistance profiles.MethodsThree-hundred and ninety pneumococci cultured from 1132 nasopharyngeal swabs from 718 children were whole-genome sequenced (Illumina) and tested for susceptibility to penicillin and amoxicillin. Genome heterogeneity analysis was performed using long-read sequenced isolates (PacBio, n = 10) and publicly available sequences.ResultsAmong 390 unique pneumococcal isolates, serotypes 15B/C, 11 A, 15 A and 23B1 were most prevalent (n = 145, 37.2%). PCV13 serotypes 3, 19A, and 19F were also identified (n = 25, 6.4%). STs associated with 19A and 19F demonstrated high genome variability, in contrast to serotype 3 (n = 13, 3.3%) that remained highly stable over a 20-year period. Non-susceptibility to penicillin (n = 61, 15.6%) and amoxicillin (n = 10, 2.6%) was low among the pneumococci analysed here and was independent of treatment dosage and duration. However, all 23B1 isolates (n = 27, 6.9%) were penicillin non-susceptible. This serotype was also identified in ST177, which is historically associated with the PCV13 serotype 19F and penicillin susceptibility, indicating a potential capsule-switch event.ConclusionsOur data suggest that amoxicillin use does not drive pneumococcal serotype prevalence among children in the UK, and prompts consideration of PCVs with additional serotype coverage that are likely to further decrease CAP in this target population. Genotype 23B1 represents the convergence of a non-vaccine genotype with penicillin non-susceptibility and might provide a persistence strategy for ST types historically associated with vaccine serotypes. This highlights the need for continued genomic surveillance.

Contribution to pulmonary diseases diagnostic from X-ray images using innovative deep learning models

Pulmonary disease identification and characterization are among the most intriguing research topics of recent years since they require an accurate and prompt diagnosis. Although pulmonary radiography has helped in lung disease diagnosis, the interpretation of the radiographic image has always been a major concern for doctors and radiologists to reduce diagnosis errors. Due to their success in image classification and segmentation tasks, cutting-edge artificial intelligence techniques like machine learning (ML) and deep learning (DL) are widely encouraged to be applied in the field of diagnosing lung disorders and identifying them using medical images, particularly radiographic ones. For this end, the researchers are concurring to build systems based on these techniques in particular deep learning ones. In this paper, we proposed three deep-learning models that were trained to identify the presence of certain lung diseases using thoracic radiography. The first model, named “CovCXR-Net”, identifies the COVID-19 disease (two cases: COVID-19 or normal). The second model, named “MDCXR3-Net”, identifies the COVID-19 and pneumonia diseases (three cases: COVID-19, pneumonia, or normal), and the last model, named “MDCXR4-Net”, is destined to identify the COVID-19, pneumonia and the pulmonary opacity diseases (4 cases: COVID-19, pneumonia, pulmonary opacity or normal). These models have proven their superiority in comparison with the state-of-the-art models and reached an accuracy of 99,09 %, 97.74 %, and 90,37 % respectively with three benchmarks.

X-ray Image Recognition of Pneumonia Based on Three Different Neural Networks

With the outbreak of new coronary pneumonia, a variety of pneumonia diseases are emerging, doctors often have misdiagnoses and omissions. To assist doctors in better clinical diagnosis, a variety of high-performance neural network structures have been applied to the X-ray recognition of pneumonia, and the X-ray image recognition accuracy will be improved, will effectively improve the efficiency of the hospital detection, at the same time, can also avoid the patient to miss the best rescue time. To this end, this paper compares and analyses the recognition performance of the three currently used neural network structures in the recognition of pneumonia X-ray images, uses some publicly available datasets and a mixed set composed of different datasets to conduct experiments, and summarises the advantages of the models and the direction of possible improvement. The three neural network models are presented, compared, and analysed to suggest useful references for the recognition of pneumonia X-ray images. Finally, an analysis and outlook for future neural network models for pneumonia x-ray image recognition is presented.

An effective ensemble approach for classification of chest X-ray images having symptoms of COVID: A precautionary measure for the COVID-19 subvariants

In recent years many people have died due to COVID-19 infection. The death rate increases due to the lack of proper diagnosis and treatment. It can be detected by RT-PCR test and from chest X-rays. Chest X-ray images can identify lung diseases such as COVID-19, viral pneumonia, and tuberculosis (TB). Because many illnesses share similar patterns and diagnoses, radiologists and clinicians find it challenging to distinguish between them. This study uses convolutional neural networks (CNN) and ensemble models (VGG-19, ResNet50, vision transformer) to analyze chest X-ray images from internet sources to identify lung illness. The present research proposed an ensemble model comprised of VGG-19, ResNet50, and a vision transformer for the detection of COVID-19 and normal images with an accuracy of 92.46 percent and 94.52 % for the detection of COVID-19, normal and viral pneumonia respectively. Also, a comparative study has been conducted between CNN and ensemble approach for detecting COVID-19 and pneumonia disease from chest x-ray images. The proposed approach may also help in the early detection of other variants of COVID-19 such as JN.1, and HV.1 in the future.

Correlation between cerebroplacental doppler ratio and neonatal respiratory disorders: A reference marker of fetal lung maturation.

The aim of this study was to investigate the role of cerebroplacental ratio (CPR) in the final prenatal care for neonatal respiratory diseases and to analyze the risk of relevant factors associated with neonatal respiratory disorders. A prospective cohort study of 795 singleton pregnancies was conducted. The pulsatility indices (PI) of the umbilical artery (UA) and the middle cerebral artery (MCA) were measured, and the MCA to UA ratio (CPR) was determined. The severity of the case is determined by whether or not the newborn has respiratory problems. Compare the CPR correlation between the two groups and examine the illness prediction factors through a binary logistic regression method. Of the 795 participants, 124 had neonatal respiratory disorders. The mean values of CPR between neonatal respiratory diseases group and control group were 1.78±0.6, 1.97±0.9, respectively (P < 0.001). Maternal age, abortion history, cesarean section history, placental thickness, placental maturity, and amniotic fluid index (AFI) were determined to have no significant link between the two groups after comparison analysis (P > 0.05). It could be found that compared with the control group, CPR MoM indicators of neonatal respiratory distress syndrome, neonatal pneumonia and wet lung disease all show significant decreases. In binary logistic regression analysis, among the variables included in the model, CPR (OR:2.90, P = 0.015), fetal heart monitoring (OR:5.26, P < 0.001), delivery mode (OR:2.86, P < 0.001) and gestational age of delivery (OR:0.92, P < 0.001) were statistically significant in both groups. The findings of this study showed that infant respiratory problems were substantially related to CPR value. The correlation indicates that CPR was a powerful reference marker for respiratory disorders.

Analyzing the performance of a bio-sensor integrated improved blended learning model for accurate pneumonia prediction

Pneumonia has been considered a life-threatening disease for elderly human beings and those with weakened immune systems in the present medical era. The contemporary scenario highlights the significance of intelligent and automatic handheld devices to detect pneumonia and other pulmonary diseases. Hence, this research has designed an improved blended learning paradigm (IBLP) for real-time pneumonia detection from chest X-rays, and early detection of lung diseases from alveolar gas using biosensors with a graphical processing unit (GPU) developed to overcome and resolve such challenges. It emphasizes the medical applications of blended learning techniques, particularly for identifying pneumonia from chest X-ray images and other pulmonary diseases from exhaled breath using biosensors and support vector machine (SVM). The experimental findings indicate that the blended learning based VGG16 (91.99%) consistently outperforms the VGG19 (88.91%) and ResNet50 (87.02%) model in diagnostic accuracy. IBLP VGG16 provided 95.5% precision, 97.69% F1 score, and a 100% recall rate with no false-negative results. The future of X-ray classification in pneumonia diagnosis will likely involve using artificial intelligence-based systems that can provide accurate and timely analysis of X-ray images, thereby improving patient outcomes and reducing healthcare costs.

Retrospective study on the health and economic burden of hospitalized patients due to pneumonia and invasive pneumococcal infections in Belgium settings

Introductionpneumococcal infections are associated with high morbidity, hospitalisation and mortality. The objective of this study was to investigate the health and economic burden of all-cause pneumonia and invasive pneumococcal disease in Belgian hospital settings, by patient’s age and risk profile. Methods:This descriptive retrospective study was conducted in 17 Belgian hospitals. Univariate and multivariate logistic linear regression models were performed. The Health Insurance and patient’s cost perspectives were considered because a few studies report these costs. Results:The analysis has included 4,712 hospital admissions over the year 2018. Median hospitalization costs were higher for invasive pneumococcal infection diagnosis than for all-cause pneumonia (p < 0,001), respectively 4,051€ and 3,362€. Other factors associated with higher hospitalization cost were patient’s high-risk profile, admission to emergency unit, transfer from nursing home, admission to intensive care unit and length of stay. Conclusion:Streptococcus pneumoniae infections remain a public health problem with significant cost for the Health Insurance and poor prognosis. Invasive pneumococcal infections are associated with longer hospital stays and required more intensive care than all other causes of pneumonia, in addition to be more costly, which justifies more attention for vaccination. This study also suggests an increase of economic and health burden with age and presence of underlying conditions.

D-Dimer As A Parameter Of Disease And Death Of Covid-19 Patients In Islamic Hospital, Surabaya

Background: Previous studies of Community Associated Pneumonia (CAP) and Chronic Obstructive Pulmonary Disease (COPD), patients have shown that D-Dimer increases higher in severe cases and can be used as a prognostic biomarker and whilst D-Dimer&gt; 1 mcg/ ml tends to be death for hospitalized adult patient with a diagnosis of Covid-19. However, D-Dimer's role in Covid-19 patients has not been fully studied. We aim to conduct research on D-Dimer as a parameter of Clinical Severity and Death of Covid-19 Patients in Islamic Hospital, in Surabaya. Methods: This type of research is an analytic observational study with a retrospective approach. The population in this study were all patient’s data retrieved from the Dahlia Room’s database from June to July 2020 which were taken through EMR (an Electrical Medical Records) from a total of 189 patients with the total sample of 82 patients. Data analysis in this study used chi-square (X2) with a significant value of p &lt;0.05. Results: Age over 60 years is associated with a higher risk of severe Covid-19 infection (P&lt;0.05). A history of hypertension significantly affects the severity of Covid-19 infection (P &lt; 0.05). The proportion of recoveries (53.7%) was higher than the number of deaths (46.3%), although the majority of patients experienced severe clinical severity (39%). Laboratory parameters, such as D-dimer values, correlated significantly with patient age (P = 0.027, &lt;0.05). Conclusion: The study highlights the importance of factors such as age and history of comorbid diseases in predicting the severity of Covid-19 infection. A better understanding of these risk factors can help in more effective management and management of Covid-19 patients.