Clinical and Pathogenic Characteristics of Lower Respiratory Tract Infection Treated at the Vietnam National Children's Hospital

Efficient federated learning for pediatric pneumonia on chest X-ray classification

According to the World Health Organization (WHO), pneumonia kills about 2 million children under the age of 5 every year. Traditional machine learning methods can be used to diagnose chest X-rays of pneumonia in children, but there is a privacy and security issue in centralizing the data for training. Federated learning prevents data privacy leakage by sharing only the model and not the data, and it has a wide range of application in the medical field. We use federated learning method for classification, which effectively protects data security. And for the data heterogeneity phenomenon existing in the actual scenario, which will seriously affect the classification effect, we propose a method based on two-end control variables. Specifically, based on the classical federated learning FedAvg algorithm, we modify the loss function on the client side by adding a regular term or a penalty term, and add momentum after the average aggregation on the server side. The federated learning approach prevents the data privacy leakage problem compared to the traditional machine learning approach. In order to solve the problem of low classification accuracy due to data heterogeneity, our proposed method based on two-end control variables achieves an average improvement of 2% and an accuracy of 98% on average, and 99% individually, compared to the previous federated learning algorithms and the latest diffusion model-based method. The classification results and methodology of this study can be utilized by clinicians worldwide to improve the overall detection of pediatric pneumonia.

Viral and bacterial microorganisms in Vietnamese children with severe and non-severe pneumonia

To investigate potential respiratory pathogens in children with community-acquired pneumonia (CAP) and risk factors for severe disease. This prospective study was conducted among 467 children at the Thai Binh Paediatric Hospital, Vietnam between 1 July 2020 and 30 June 2021. Clinical data and laboratory results were collected. Twenty-four respiratory microorganisms were tested from nasopharyngeal swabs using real-time PCR. Logistical regression was used to estimate a factor's adjusted odd ratios of the severity of disease. Mean age of patients = 15.4 ± 13.3 months, 63.0% were male. Over 97% of patients had a positive PCR result. 87% of patients were positive for multiple (up to eight) microorganisms. Rhinovirus (46%), respiratory syncytial virus (RSV) (24%), enterovirus (17%), and parainfluenza viruses-3 (13%) were the most frequent viruses. H. influenzae (61%), S. pneumoniae (45%) and M. catarrhalis (30%) were the most common bacteria. 128 (27%) cases were classified as severe pneumonia. Presence of smokers at home (aOR 2.11, 95% CI 1.27-3.52, P value = 0.004), CRP level ≥ 50 mg/dL (aOR  6.11, 95% CI  3.86-9.68, P value < 0.0001), RSV (aOR  1.78, 95% CI  1.07-2.96, P value = 0.03) and H. influenzae (aOR  1.66, 95% CI  1.03-2.67, P value = 0.04) PCR detection associated with a higher risk of severe pneumonia; ,. Causative agents of pneumonia in children are complex. Children positive with RSV and H. influenzae need to be closely monitored to prevent severe pneumonia.

Clinical profile of acute lower respiratory tract infections in children aged 2-60 months: An observational study

Background:

Assessment of risk factors and clinical profile for acute lower respiratory tract infections (ALRIs) with severe and very severe pneumonia in children <5 years age is obligatory.

Objective:

To study the clinical profile, risk factors, and clinical outcomes associated with ALRIs in children aged 2–60 months.

Methodology:

In total, 130 children of either gender, diagnosed with ALRIs, admitted in a tertiary care hospital were enrolled. Demographic data and clinical history was collected. Clinical profile data such as respiratory and heart rate, oxygen supplementation, ventilator use, and lab investigation such as erythrocyte sedimentation rate, hemoglobin, total leucocyte count, differential leucocytes count, and blood culture were analyzed and noted.

Results:

The study findings demonstrated male gender predominance for ALRIs with 1.3:1 male to female ratio. Around 16% of them had pneumonia, 61% had severe pneumonia, and 23% had very severe pneumonia. The birth weight of child, maternal and paternal literacy, socioeconomic status, overcrowding at home, immunization status of children, type of kitchen and fuel used for cooking, malnutrition, anemia, and need for oxygen supplementation were found to be associated with the occurrence of ALRIs (P < 0.05). Most of the presented symptoms were cough (100%), breathlessness (96.92%), and fever (92.31%). Bronchiolitis (63%), bronchopneumonia (27%), and lobar pneumonia (25%) were the major clinical outcomes.

Conclusion:

The study identified various sociodemographic, environmental, and nutritional risk factors for ALRIs along with the clinical profile, which can be managed by effective peripheral health personnel's training and persuasive community health education.

Auxiliary role of mesenchymal stem cells as regenerative medicine soldiers to attenuate inflammatory processes of severe acute respiratory infections caused by COVID-19

Acute respiratory infections as one of the most common problems of healthcare systems also can be considered as an important reason for worldwide morbidity and mortality from infectious diseases. Coronaviruses are a group of well-known respiratory viruses that can cause acute respiratory infections. At the current state, the 2019 novel coronavirus is cited as the most worldwide problematic agent for the respiratory system. According to investigations, people with old age and underlying diseases are at higher risk of 2019 novel coronavirus infection. Indeed, they may show a severe form of the disease (with severe acute respiratory infections). Based on the promising role of cell therapy and regenerative medicine approaches in the treatment of several life-threatening diseases, it seems that applying cell-based approaches can also be a hopeful strategy for improving subjects with severe acute respiratory infections caused by the 2019 novel coronavirus. Herein, due to the amazing effects of mesenchymal stem cells in the treatment of various diseases, this review focuses on the auxiliary role of mesenchymal stem cells to reduce inflammatory processes of acute respiratory infections caused by the 2019 novel coronavirus.