Novel biomarker genes which distinguish between smokers and chronic obstructive pulmonary disease patients with machine learning approach

Unveiling the Influence of AI on Advancements in Respiratory Care: Narrative Review

BACKGROUND

Artificial intelligence is experiencing rapid growth, with continual innovation and advancements in the health care field.

OBJECTIVE

This study aims to evaluate the application of artificial intelligence technologies across various domains of respiratory care.

METHODS

We conducted a narrative review to examine the latest advancements in the use of artificial intelligence in the field of respiratory care. The search was independently conducted by respiratory care experts, each focusing on their respective scope of practice and area of interest.

RESULTS

This review illuminates the diverse applications of artificial intelligence, highlighting its use in areas associated with respiratory care. Artificial intelligence is harnessed across various areas in this field, including pulmonary diagnostics, respiratory care research, critical care or mechanical ventilation, pulmonary rehabilitation, telehealth, public health or health promotion, sleep clinics, home care, smoking or vaping behavior, and neonates and pediatrics. With its multifaceted utility, artificial intelligence can enhance the field of respiratory care, potentially leading to superior health outcomes for individuals under this extensive umbrella.

CONCLUSIONS

As artificial intelligence advances, elevating academic standards in the respiratory care profession becomes imperative, allowing practitioners to contribute to research and understand artificial intelligence's impact on respiratory care. The permanent integration of artificial intelligence into respiratory care creates the need for respiratory therapists to positively influence its progression. By participating in artificial intelligence development, respiratory therapists can augment their clinical capabilities, knowledge, and patient outcomes.

Identifying allergic-rhinitis-associated genes with random-walk-based method in PPI network

Allergic rhinitis is a common allergic disease with a complex pathogenesis and many unresolved issues. Studies have shown that the incidence of allergic rhinitis is closely related to genetic factors, and research on the related genes could help further understand its pathogenesis and develop new treatment methods. In this study, 446 allergic rhinitis-related genes were obtained on the basis of the DisGeNET database. The protein-protein interaction network was searched using the random-walk-with-restart algorithm with these 446 genes as seed nodes to assess the linkages between other genes and allergic rhinitis. Then, this result was further examined by three screening tests, including permutation, interaction, and enrichment tests, which aimed to pick up genes that have strong and special associations with allergic rhinitis. 52 novel genes were finally obtained. The functional enrichment test confirmed their relationships to the biological processes and pathways related to allergic rhinitis. Furthermore, some genes were extensively analyzed to uncover their special or latent associations to allergic rhinitis, including IRAK2 and MAPK, which are involved in the pathogenesis of allergic rhinitis and the inhibition of allergic inflammation via the p38-MAPK pathway, respectively. The new found genes may help the following investigations for understanding the underlying molecular mechanisms of allergic rhinitis and developing effective treatments.

Screening and staging of chronic obstructive pulmonary disease with deep learning based on chest X-ray images and clinical parameters

BACKGROUND

Chronic obstructive pulmonary disease (COPD) is underdiagnosed with the current gold standard measure pulmonary function test (PFT). A more sensitive and simple option for early detection and severity evaluation of COPD could benefit practitioners and patients.

METHODS

In this multicenter retrospective study, frontal chest X-ray (CXR) images and related clinical information of 1055 participants were collected and processed. Different deep learning algorithms and transfer learning models were trained to classify COPD based on clinical data and CXR images from 666 subjects, and validated in internal test set based on 284 participants. External test including 105 participants was also performed to verify the generalization ability of the learning algorithms in diagnosing COPD. Meanwhile, the model was further used to evaluate disease severity of COPD by predicting different grads.

RESULTS

The Ensemble model showed an AUC of 0.969 in distinguishing COPD by simultaneously extracting fusion features of clinical parameters and CXR images in internal test, better than models that used clinical parameters (AUC = 0.963) or images (AUC = 0.946) only. For the external test set, the AUC slightly declined to 0.934 in predicting COPD based on clinical parameters and CXR images. When applying the Ensemble model to determine disease severity of COPD, the AUC reached 0.894 for three-classification and 0.852 for five-classification respectively.

CONCLUSION

The present study used DL algorithms to screen COPD and predict disease severity based on CXR imaging and clinical parameters. The models showed good performance and the approach might be an effective case-finding tool with low radiation dose for COPD diagnosis and staging.

Recent evidence from omic analysis for redox signalling and mitochondrial oxidative stress in COPD

COPD is driven by exogenous and endogenous oxidative stress derived from inhaled cigarette smoke, air pollution and reactive oxygen species from dysregulated mitochondria in activated inflammatory cells within the airway and lung. This is compounded by the loss in antioxidant defences including FOXO and NRF2 and other antioxidant transcription factors together with various key enzymes that attenuate oxidant effects. Oxidative stress enhances inflammation; airway remodelling including fibrosis and emphysema; post-translational protein modifications leading to autoantibody generation; DNA damage and cellular senescence. Recent studies using various omics technologies in the airways, lungs and blood of COPD patients has emphasised the importance of oxidative stress, particularly that derived from dysfunctional mitochondria in COPD and its role in immunity, inflammation, mucosal barrier function and infection. Therapeutic interventions targeting oxidative stress should overcome the deleterious pathologic effects of COPD if targeted to the lung. We require novel, more efficacious antioxidant COPD treatments among which mitochondria-targeted antioxidants and Nrf2 activators are promising.

Bronchopulmonary dysplasia and wnt pathway-associated single nucleotide polymorphisms

AIM

Genetic variants contribute to the pathogenesis of bronchopulmonary dysplasia (BPD). The aim of this study is to evaluate the association of 45 SNPs with BPD susceptibility in a Turkish premature infant cohort.

METHODS

Infants with gestational age <32 weeks were included. Patients were divided into BPD or no-BPD groups according to oxygen need at 28 days of life, and stratified according to the severity of BPD. We genotyped 45 SNPs, previously identified as BPD risk factors, in 192 infants.

RESULTS

A total of eight SNPs were associated with BPD risk at allele level, two of which (rs4883955 on KLF12 and rs9953270 on CHST9) were also associated at the genotype level. Functional relationship maps suggested an interaction between five of these genes, converging on WNT5A, a member of the WNT pathway known to be implicated in BPD pathogenesis. Dysfunctional CHST9 and KLF12 variants may contribute to BPD pathogenesis through an interaction with WNT5A.

CONCLUSIONS

We suggest investigating the role of SNPs on different genes which are in relation with the Wnt pathway in BPD pathogenesis. We identified eight SNPs as risk factors for BPD in this study. In-silico functional maps show an interaction of the genes harboring these SNPs with the WNT pathway, supporting its role in BPD pathogenesis.

TRIAL REGISTRATION

NCT03467828.

IMPACT

It is known that genetic factors may contribute to the development of BPD in preterm infants. Further studies are required to identify specific genes that play a role in the BPD pathway to evaluate them as a target for therapeutic interventions. Our study shows an association of BPD predisposition with certain polymorphisms on MBL2, NFKBIA, CEP170, MAGI2, and VEGFA genes at allele level and polymorphisms on CHST9 and KLF12 genes at both allele and genotype level. In-silico functional mapping shows a functional relationship of these five genes with WNT5A, suggesting that Wnt pathway disruption may play a role in BPD pathogenesis.

Donor-to-donor variability of a human three-dimensional bronchial epithelial model: A case study of cigarette smoke exposure

Three-dimensional (3D) cultured primary cells are used to predict the toxicity of substances towards humans because these 3D cultures closely mimic the physiological architecture of tissues. Nonetheless, it is important to consider primary-cell-specific variability for endpoint selection and appropriate evaluation of toxicity because donor-dependent characteristics may be retained even in in vitro cell cultures. In this report, 3D differentiated bronchial epithelial cells from three donors were used to investigate donor-to-donor variability, with an aqueous extract of cigarette smoke (CS) used as the test substance. Ciliary function, cytokine secretion, and histopathology, which are affected by CS, were examined, and transcriptomic analysis was also performed. The results revealed that interleukin-8 secretion and oxidative stress-related gene expression were consistently altered for all donors; however, their amplitudes varied. Moreover, one of the donors showed unique responses to CS, suggesting that this donor was an outlier. This donor showed intrinsic differences in histology, cytokine secretion, and gene expression profile. Such donors may help evaluate potential toxicological concerns and aid our understanding of disease pathogenesis. Conversely, these donors may confound toxicological assessment and endpoint selection. Fit-for-purpose handling of inter-donor variability is warranted.

Volatile organic compounds released in the mainstream smoke of flavor capsule cigarettes

In this study, the composition of mainstream smoke was investigated with an emphasis on a list of volatile organic compounds (VOCs: e.g., isoprene, acrylonitrile, methyl ethyl ketone, benzene, toluene, m-xylene and styrene) using the two types of flavor capsule cigarettes (FCCs, here coded as F1 and F2) in reference to one commercial, non-flavored (NF) and 3R4F cigarette. The concentrations of all the target compounds from FCCs were quantified under two contrasting conditions (i.e., with and without breaking the capsules). The effect of breaking the capsule was apparent in the FCC products with the enhancement of VOC levels, specifically between after and before breaking the capsules (e.g., 1.10-1.58 folds (benzene) and 1.30-1.53 folds (acetonitrile)). Such increases were apparent in both FCC samples if assessed in terms of the total amount of VOCs (TVOC): (1) F1 (from 2159 to 2530 μg cig-1 (p = 9.42 × 10-6)) and (2) F2 (from 1470 to 2014 μg cig-1 (p = 0.05)). In addition, these TVOC levels determined from the FCCs were 1.62- to 1.83- and 1.29- to 1.46-fold higher than those of the NF cigarette and the 3R4F cigarette, respectively. Thus, these FCC products are suspected to play a role as stronger sources of VOCs than the general cigarette products.

Effect of Smoking and Its Cessation on the Transcript Profile of Peripheral Monocytes in COPD Patients

Rationale

Smoking is the primary cause of chronic obstructive pulmonary disease (COPD); however, only 10–20% of smokers develop the disease suggesting possible genomic association in the causation of the disease. In the present study, we aimed to explore the whole genome transcriptomics of blood monocytes from COPD smokers (COPD-S), COPD Ex-smokers (COPD-ExS), Control smokers (CS), and Control Never-smokers (CNS) to understand the differential effects of smoking, COPD and that of smoking cessation.

Methods

Exploratory analyses in form of principal component analysis (PCA) and hierarchical component analysis (uHCA) were performed to evaluate the similarity in gene expression patterns, while differential expression analyses of different supervised groups of smokers and never smokers were performed to study the differential effect of smoking, COPD and smoking cessation. Differentially expressed genes among groups were subjected to post-hoc enrichment analysis. Candidate genes were subjected to external validation by quantitative RT-PCR experiments.

Results

CNS made a cluster completely segregated from the other three subgroups (CS, COPDS and COPD-ExS). About 550, 8 and 5 genes showed differential expression, respectively, between CNS and CS, between CS and COPD-S, and between COPD-S and COPD-ExS. Apoptosis, immune response, cell adhesion, and inflammation were the top process networks identified in enrichment analysis. Two candidate genes (CASP9 and TNFRSF1A) found to be integral to several pathways in enrichment analysis were validated in an external validation experiment.

Conclusion

Control never smokers had formed a cluster distinctively separated from all smokers (COPDS, COPD-ExS, and CS), while amongst all smokers, control smokers had aggregated in a separate cluster. Smoking cessation appeared beneficial if started at an early stage as many genes altered due to smoking started reverting towards the baseline, whereas only a few COPD-related genes showed reversal after smoking cessation.

Analyzing the use of artificial intelligence for the management of chronic obstructive pulmonary disease (COPD)

OBJECTIVE

Chronic obstructive pulmonary disease (COPD) is a disease that causes airflow limitation to the lungs and has a high morbidity around the world. The objective of this study was to evaluate how artificial intelligence (AI) is being applied for the management of the disease, analyzing the objectives that are raised, the algorithms that are used and what results they offer.

METHODS

We conducted a scoping review following the Arksey and O'Malley (2005) and Levac et al. (2010) guidelines. Two reviewers independently searched, analyzed and extracted data from papers of five databases: Web of Science, PubMed, Scopus, Cinahl and Cochrane. To be included, the studies had to apply some AI techniques for the management of at least one stage of the COPD clinical process. In the event of any discrepancy between both reviewers, the criterion of a third reviewer prevailed.

RESULTS

380 papers were identified through database searches. After applying the exclusion criteria, 67 papers were included in the study. The studies were of a different nature and pursued a wide range of objectives, highlighting mainly those focused on the identification, classification and prevention of the disease. Neural nets, support vector machines and decision trees were the AI algorithms most commonly used. The mean and median values of all the performance metrics evaluated were between 80% and 90%.

CONCLUSIONS

The results obtained show a growing interest in the development of medical applications that manage the different phases of the COPD clinical process, especially predictive models. According to the performance shown, these models could be a useful complementary tool in the decision-making by health specialists, although more high-quality ML studies are needed to endorse the findings of this study.

USP13 Deficiency Aggravates Cigarette-smoke-induced Alveolar Space Enlargement

Alveolar enlargement is a pathological feature of emphysema. Long-term exposure to cigarette smoke (CS) is a high-risk factor for the development of emphysema. Abnormal protein ubiquitination has been implicated to regulate the development of human disorders, however, the role of protein ubiquitination in emphysema has not been well-studied. In this study, we attempted to investigate if a deubiquitinase, USP13, regulates the development of emphysema. Under a mild CS exposure condition, USP13-deficient mice show significant increases in alveolar chord length, indicating that USP13-deficient mice are susceptible to CS-induced alveolar enlargement. It has been shown that USP13 knockout reduced fibronectin expression in lungs. Here, we found that collagen levels were reduced in USP13 siRNA-transfected lung fibroblast cells. This suggests that a loss of extracellular matrix in connective tissues contributes to alveolar enlargement in USP13-deficient mice in response to CS exposure. Further, we investigated the role of USP13 in the expression of oxidative stress markers TXNIP and HMOX1. An increase in HMOX1 abundance was observed in USP13 knockdown lung fibroblast and epithelial cells. Overexpression of USP13 reduced HMOX1 protein levels in lung fibroblast cells, suggesting that modulation of USP13 levels may affect oxidative stress. Knockdown of USP13 significantly reduced TXNIP levels in lungs or lung fibroblast cells. A protein stability pulse-chase assay showed that TXNIP is instable within USP13 knockdown lung fibroblast cells. Further, the reduction of TXNIP was observed in USP13 inhibitor-treated lung epithelial cells. USP13-deficient mice also show higher levels of IgG in bronchoalveolar lavage fluid. This study provides evidence showing that USP13 deficiency plays a role in alveolar space enlargement.

Fully integrating pathophysiological insights in COPD: an updated working disease model to broaden therapeutic vision

Our starting point is that relatively new findings into the pathogenesis and pathophysiology of airway disease in smokers that lead to chronic obstructive pulmonary disease (COPD) need to be reassessed as a whole and integrated into "mainstream" thinking along with traditional concepts which have stood the test of time. Such a refining of the accepted disease paradigm is urgently needed as thinking on therapeutic targets is currently under active reconsideration. We feel that generalised airway wall "inflammation" is unduly over-emphasised, and highlight the patchy and variable nature of the pathology (with the core being airway remodelling). In addition, we present evidence for airway wall disease in smokers/COPD as including a hypocellular, hypovascular, destructive, fibrotic pathology, with a likely spectrum of epithelial-mesenchymal transition states as significant drivers of this remodelling. Furthermore, we present data from a number of research modalities and integrate this with the aetiology of lung cancer, the role of chronic airway luminal colonisation/infection by a specific group of "respiratory" bacteria in smokers (which results in luminal inflammation) and the central role for oxidative stress on the epithelium. We suggest translation of these insights into more focus on asymptomatic smokers and early COPD, with the potential for fresh preventive and therapeutic approaches.

Artificial Intelligence and Machine Learning in Chronic Airway Diseases: Focus on Asthma and Chronic Obstructive Pulmonary Disease

Chronic airway diseases are characterized by airway inflammation, obstruction, and remodeling and show high prevalence, especially in developing countries. Among them, asthma and chronic obstructive pulmonary disease (COPD) show the highest morbidity and socioeconomic burden worldwide. Although there are extensive guidelines for the prevention, early diagnosis, and rational treatment of these lifelong diseases, their value in precision medicine is very limited. Artificial intelligence (AI) and machine learning (ML) techniques have emerged as effective methods for mining and integrating large-scale, heterogeneous medical data for clinical practice, and several AI and ML methods have recently been applied to asthma and COPD. However, very few methods have significantly contributed to clinical practice. Here, we review four aspects of AI and ML implementation in asthma and COPD to summarize existing knowledge and indicate future steps required for the safe and effective application of AI and ML tools by clinicians.

Artificial Intelligence in COPD: New Venues to Study a Complex Disease

Chronic obstructive pulmonary disease (COPD) is a complex and heterogeneous disease that can benefit from novel approaches to understanding its evolution and divergent trajectories. Artificial intelligence (AI) has revolutionized how we can use clinical, imaging, and molecular data to understand and model complex systems. AI has shown impressive results in areas related to automated clinical decision making, radiological interpretation and prognostication. The unique nature of COPD and the accessibility to well-phenotyped populations result in an ideal scenario for AI development. This review provides an introduction to AI and deep learning and presents some recent successes in applying AI in COPD. Finally, we will discuss some of the opportunities, challenges, and limitations for AI applications in the context of COPD.