Daily Ards Research Analysis

INTRODUCTION: Accurate and timely interpretation of chest radiographs is essential for assessing respiratory distress and guiding clinical management to improve outcomes of critically ill newborns. This study aimed to introduce a deep-learning-based automated algorithm designed to classify various neonatal respiratory diseases and healthy lungs using a large dataset of high-quality, multi-class labeled chest X-ray images from neonatal intensive care units. METHODS: Portable supine chest X-ray images for six common conditions (healthy lung, respiratory distress syndrome [RDS], transient tachypnea of the newborn [TTN], air leak syndrome [ALS], atelectasis, and bronchopulmonary dysplasia [BPD]) and demographic variables (gestational age and birth weight) were retrospectively collected from 10 university hospitals in Korea. Ground truth for manual classification of these conditions was generated by 20 neonatologists and validated by others from different hospitals. The dataset, consisting 34,598 for training, 4,370 for validation, and 4,370 for testing, was used to train a modified ResNet50-based deep-learning model for automatic classification. RESULTS: The automatic classification algorithm showed high concordance with human-annotated classifications, achieving an overall testing accuracy of 83.96% and an F1 score of 83.68%. The F1 score for each condition was 87.38% for "healthy lung" and 92.19% for "BPD," 90.65% for "ALS," 90.30% for "RDS," 86.56% for "atelectasis," and 70.84% for "TTN." CONCLUSION: We introduced a deep-learning-based automated algorithm to classify neonatal respiratory diseases using a large dataset of high-quality, multi-class labeled chest X-ray images, incorporating non-imaging data, which could support neonatologists in making timely and accurate decisions for critically ill newborns.

While dysregulated autophagy has been linked to acute respiratory distress syndrome (ARDS) development in sepsis, the exact regulatory mechanisms driving this process remain unclear. This study systematically investigated autophagy-related genes in sepsis-induced ARDS using integrative bioinformatics, including weighted gene coexpression network analysis (WGCNA), differential gene expression analysis (DEGs), receiver operating characteristic (ROC) curve analysis, Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analysis, protein‒protein interaction (PPI) network analysis, and immune infiltration analysis. Hub genes were further validated by qPCR in Beas-2B cells receiving lipopolysaccharide (LPS) stimulation. We identified 18 autophagy-related DEGs with diagnostic potential for sepsis-induced ARDS. These DEGs were linked to endocytosis, protein kinase inhibition, and enigmatic Ficolin-1-rich granules. The downregulated hallmark signaling pathways involved apoptosis, complement, IL-2/STAT5, and KRAS signaling. Immune infiltration analysis revealed alterations in 7 immune cell subsets, including CD8 + T-cell exhaustion, natural killer cell reduction, and the type 1 helper T-cell response. When Beas-2B cells were treated with LPS, we discovered that 6 out of the 18 hub genes were significantly downregulated. Our findings provide novel insights into autophagy-mediated ARDS pathogenesis in sepsis. The hub genes represent promising candidates for clinical biomarker development and therapeutic targeting, which necessitates further validation.

BACKGROUND: Understanding the dynamic changes in immune indicators during sepsis and their predictive value for Acute respiratory distress syndrome (ARDS) is crucial for improving patient outcomes. METHODS: This single-center, observational retrospective study was conducted at Lishui Central Hospital, Zhejiang Province. Patients diagnosed with Sepsis-3 were categorized into non-ARDS and ARDS groups based on ARDS development. Data collection included demographics, clinical data, and immune parameters. Immune parameters were collected on days 1, 3, and 7 post-admission. Multivariate logistic regression analysis identified independent risk factors for ARDS, and a nomogram model was constructed. The predictive ability of the model was evaluated using ROC curves. RESULTS: Multivariate analysis identified key factors for the nomogram, including CD4, CD8, Treg, lymphocyte, IgG, and IgA levels on Days 3 and 7. On Day 3, CD8 (P < 0.001), Tregs (P = 0.021), IgG (P < 0.001), and IgA (P < 0.001) showed significant negative correlations with ARDS development. On Day 7, CD4 (P < 0.001), CD8 (P < 0.001), lymphocyte count (P < 0.001), and IgA (P < 0.001) similarly demonstrated significant negative correlations with ARDS risk. The nomogram model had an AUC of 0.998 (95% CI: 0.997-0.999), indicating high predictive ability. CONCLUSION: Early dynamic changes in immune indicators, including CD8, CD4, Treg, IgA, IgG, and Lymphocyte, predict ARDS development in ICU sepsis patients.