Machine Learning–Based Discovery of a Gene Expression Signature in Pediatric Acute Respiratory Distress Syndrome

Grunwell, Jocelyn R.; Rad, Milad Ghiasi; Stephenson, Susan; Mohammad, Ahmad F.; Opolka, Cydney; Fitzpatrick, Anne M.; Kamaleswaran, Rishikesan

doi:10.1097/cce.0000000000000431

Cited by 14 publications

(19 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Patients with bacterial pneumonia had neutrophils with increased markers of activation and a defective respiratory burst, with airway fluid containing higher MPO and NE activity and decreased killing of H. influenzae and S. aureus ( Grunwell et al, 2019 ). In a follow-up study comparing tracheal aspirates from intubated children with and without pediatric ARDS, increased type I interferon signaling (increased phosphorylation of STAT1 ), increased NET release ( Grunwell et al, 2021 ). Increased markers of neutrophil activation and degranulation were observed in children with PARDS, also associated with fewer ventilator days in patients with higher airway NE ( Grunwell et al, 2021 ).…”

Section: Summary Of Research To Datementioning

confidence: 99%

“…In a follow-up study comparing tracheal aspirates from intubated children with and without pediatric ARDS, increased type I interferon signaling (increased phosphorylation of STAT1 ), increased NET release ( Grunwell et al, 2021 ). Increased markers of neutrophil activation and degranulation were observed in children with PARDS, also associated with fewer ventilator days in patients with higher airway NE ( Grunwell et al, 2021 ). Similar findings were documented in lower airway neutrophils and neutrophils exposed to airway fluid from adults with vs. without ARDS ( Supplementary file 1 ), including decreased apoptosis and macrophage activity and increased NET formation in ARDS ( Grégoire et al, 2018 ).…”

Section: Summary Of Research To Datementioning

confidence: 99%

See 1 more Smart Citation

Evolution of multiple omics approaches to define pathophysiology of pediatric acute respiratory distress syndrome

Whitney

Lee

et al. 2022

eLife

View full text Add to dashboard Cite

Pediatric acute respiratory distress syndrome (PARDS), though both common and deadly in critically ill children, lacks targeted therapies. The development of effective pharmacotherapies has been limited, in part, by lack of clarity about the pathobiology of pediatric ARDS. Epithelial lung injury, vascular endothelial activation, and systemic immune activation are putative drivers of this complex disease process. Prior studies have used either hypothesis-driven (e.g., candidate genes and proteins, in vitro investigations) or unbiased (e.g., genome-wide association, transcriptomic, metabolomic) approaches to predict clinical outcomes and to define subphenotypes. Advances in multiple omics technologies, including genomics, transcriptomics, proteomics, and metabolomics, have permitted more comprehensive investigation of PARDS pathobiology. However, omics studies have been limited in children compared to adults, and analyses across multiple tissue types are lacking. Here, we synthesized existing literature on the molecular mechanism of PARDS, summarized our interrogation of publicly available genomic databases to determine the association of candidate genes with PARDS phenotypes across multiple tissues and cell types, and integrated recent studies that used single-cell RNA sequencing (scRNA-seq). We conclude that novel profiling methods such as scRNA-seq, which permits more comprehensive, unbiased evaluation of pathophysiological mechanisms across tissue and cell types, should be employed to investigate the molecular mechanisms of PRDS toward the goal of identifying targeted therapies.

show abstract

Section: Summary Of Research To Datementioning

confidence: 99%

Section: Summary Of Research To Datementioning

confidence: 99%

Evolution of multiple omics approaches to define pathophysiology of pediatric acute respiratory distress syndrome

Whitney

Lee

et al. 2022

eLife

View full text Add to dashboard Cite

show abstract

“…In recent years, applications of machine learning (ML) and artificial intelligence have shown great promise in advancing the field of healthcare and critical care [ 23 ]. ML models are able to identify physiomarkers that help in early detection of sepsis [ 24 ] and predict life-threatening conditions such as acute respiratory distress syndrome (ARDS) using ICU data [ 25 ] and gene expression signatures [ 26 ]. A major area of research currently is early and accurate detection of infections from microbial VOCs and several statistical and machine learning methods have been successfully developed to this end [ 4 , 27 ].…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Approaches to Identify Discriminative Signatures of Volatile Organic Compounds (VOCs) from Bacteria and Fungi Using SPME-DART-MS

et al. 2022

Self Cite

View full text Add to dashboard Cite

Point-of-care screening tools are essential to expedite patient care and decrease reliance on slow diagnostic tools (e.g., microbial cultures) to identify pathogens and their associated antibiotic resistance. Analysis of volatile organic compounds (VOC) emitted from biological media has seen increased attention in recent years as a potential non-invasive diagnostic procedure. This work explores the use of solid phase micro-extraction (SPME) and ambient plasma ionization mass spectrometry (MS) to rapidly acquire VOC signatures of bacteria and fungi. The MS spectrum of each pathogen goes through a preprocessing and feature extraction pipeline. Various supervised and unsupervised machine learning (ML) classification algorithms are trained and evaluated on the extracted feature set. These are able to classify the type of pathogen as bacteria or fungi with high accuracy, while marked progress is also made in identifying specific strains of bacteria. This study presents a new approach for the identification of pathogens from VOC signatures collected using SPME and ambient ionization MS by training classifiers on just a few samples of data. This ambient plasma ionization and ML approach is robust, rapid, precise, and can potentially be used as a non-invasive clinical diagnostic tool for point-of-care applications.

show abstract

“…Machine learning can yield a list of differential genes that combine to drive the prediction and consider the dependence between the genes. For example, Grunwell et al [ 20 ] applied machine learning to nanostring transcriptomics on primary airway cells and a neutrophil reporter assay to discover gene networks differentiating pediatric acute respiratory distress syndrome from non-pediatric ARDS. Cai et al [ 21 ] used gene expression data fed into three modeling methods—logistic regression, random forest and neural network—to develop a diagnostic gene signature for the diagnosis of VAP.…”

Section: Introductionmentioning

confidence: 99%

Predicting mechanical ventilation effects on six human tissue transcriptomes

et al. 2022

View full text Add to dashboard Cite

Background Mechanical ventilation (MV) is a lifesaving therapy used for patients with respiratory failure. Nevertheless, MV is associated with numerous complications and increased mortality. The aim of this study is to define the effects of MV on gene expression of direct and peripheral human tissues. Methods Classification models were applied to Genotype-Tissue Expression Project (GTEx) gene expression data of six representative tissues–liver, adipose, skin, nerve-tibial, muscle and lung, for performance comparison and feature analysis. We utilized 18 prediction models using the Random Forest (RF), XGBoost (eXtreme Gradient Boosting) decision tree and ANN (Artificial Neural Network) methods to classify ventilation and non-ventilation samples and to compare their prediction performance for the six tissues. In the model comparison, the AUC (area under receiver operating curve), accuracy, precision, recall, and F1 score were used to evaluate the predictive performance of each model. We then conducted feature analysis per each tissue to detect MV marker genes followed by pathway enrichment analysis for these genes. Results XGBoost outperformed the other methods and predicted samples had undergone MV with an average accuracy for the six tissues of 0.951 and average AUC of 0.945. The feature analysis detected a combination of MV marker genes per each tested tissue, some common across several tissues. MV marker genes were mainly related to inflammation and fibrosis as well as cell development and movement regulation. The MV marker genes were significantly enriched in inflammatory and viral pathways. Conclusion The XGBoost method demonstrated clear enhanced performance and feature analysis compared to the other models. XGBoost was helpful in detecting the tissue-specific marker genes for identifying transcriptomic changes related to MV. Our results show that MV is associated with reduced development and movement in the tissues and higher inflammation and injury not only in direct tissues such as the lungs but also in peripheral tissues and thus should be carefully considered before being implemented.

show abstract

Machine Learning–Based Discovery of a Gene Expression Signature in Pediatric Acute Respiratory Distress Syndrome

Abstract: Supplemental Digital Content is available in the text.

Cited by 14 publications

References 67 publications

Evolution of multiple omics approaches to define pathophysiology of pediatric acute respiratory distress syndrome

Evolution of multiple omics approaches to define pathophysiology of pediatric acute respiratory distress syndrome

Machine Learning Approaches to Identify Discriminative Signatures of Volatile Organic Compounds (VOCs) from Bacteria and Fungi Using SPME-DART-MS

Predicting mechanical ventilation effects on six human tissue transcriptomes

Contact Info

Product

Resources

About