Machine Learning Characterization of COPD Subtypes: Insights From the COPDGene Study

Evaluation of retrieval accuracy and visual similarity in content-based image retrieval of chest CT for obstructive lung disease

The aim of our study was to assess the performance of content-based image retrieval (CBIR) for similar chest computed tomography (CT) in obstructive lung disease. This retrospective study included patients with obstructive lung disease who underwent volumetric chest CT scans. The CBIR database included 600 chest CT scans from 541 patients. To assess the system performance, follow-up chest CT scans of 50 patients were evaluated as query cases, which showed the stability of the CT findings between baseline and follow-up chest CT, as confirmed by thoracic radiologists. The CBIR system retrieved the top five similar CT scans for each query case from the database by quantifying and comparing emphysema extent and size, airway wall thickness, and peripheral pulmonary vasculatures in descending order from the database. The rates of retrieval of the same pairs of query CT scans in the top 1-5 retrievals were assessed. Two expert chest radiologists evaluated the visual similarities between the query and retrieved CT scans using a five-point scale grading system. The rates of retrieving the same pairs of query CTs were 60.0% (30/50) and 68.0% (34/50) for top-three and top-five retrievals. Radiologists rated 64.8% (95% confidence interval 58.8-70.4) of the retrieved CT scans with a visual similarity score of four or five and at least one case scored five points in 74% (74/100) of all query cases. The proposed CBIR system for obstructive lung disease integrating quantitative CT measures demonstrated potential for retrieving chest CT scans with similar imaging phenotypes. Further refinement and validation in this field would be valuable.

Blood-based Transcriptomic and Proteomic Biomarkers of Emphysema

Rationale: Emphysema is a chronic obstructive pulmonary disease phenotype with important prognostic implications. Identifying blood-based biomarkers of emphysema will facilitate early diagnosis and development of targeted therapies. Objectives: To discover blood omics biomarkers for chest computed tomography-quantified emphysema and develop predictive biomarker panels. Methods: Emphysema blood biomarker discovery was performed using differential gene expression, alternative splicing, and protein association analyses in a training sample of 2,370 COPDGene participants with available blood RNA sequencing, plasma proteomics, and clinical data. Internal validation was conducted in a COPDGene testing sample (n = 1,016), and external validation was done in the ECLIPSE study (n = 526). Because low body mass index (BMI) and emphysema often co-occur, we performed a mediation analysis to quantify the effect of BMI on gene and protein associations with emphysema. Elastic net models with bootstrapping were also developed in the training sample sequentially using clinical, blood cell proportions, RNA-sequencing, and proteomic biomarkers to predict quantitative emphysema. Model accuracy was assessed by the area under the receiver operating characteristic curves for subjects stratified into tertiles of emphysema severity. Measurements and Main Results: Totals of 3,829 genes, 942 isoforms, 260 exons, and 714 proteins were significantly associated with emphysema (false discovery rate, 5%) and yielded 11 biological pathways. Seventy-four percent of these genes and 62% of these proteins showed mediation by BMI. Our prediction models demonstrated reasonable predictive performance in both COPDGene and ECLIPSE. The highest-performing model used clinical, blood cell, and protein data (area under the receiver operating characteristic curve in COPDGene testing, 0.90; 95% confidence interval, 0.85-0.90). Conclusions: Blood transcriptome and proteome-wide analyses revealed key biological pathways of emphysema and enhanced the prediction of emphysema.

Joint clinical and molecular subtyping of COPD with variational autoencoders

Chronic Obstructive Pulmonary Disease (COPD) is a complex, heterogeneous disease. Traditional subtyping methods generally focus on either the clinical manifestations or the molecular endotypes of the disease, resulting in classifications that do not fully capture the disease's complexity. Here, we bridge this gap by introducing a subtyping pipeline that integrates clinical and gene expression data with variational autoencoders. We apply this methodology to the COPDGene study, a large study of current and former smoking individuals with and without COPD. Our approach generates a set of vector embeddings, called Personalized Integrated Profiles (PIPs), that recapitulate the joint clinical and molecular state of the subjects in the study. Prediction experiments show that the PIPs have a predictive accuracy comparable to or better than other embedding approaches. Using trajectory learning approaches, we analyze the main trajectories of variation in the PIP space and identify five well-separated subtypes with distinct clinical phenotypes, expression signatures, and disease outcomes. Notably, these subtypes are more robust to data resampling compared to those identified using traditional clustering approaches. Overall, our findings provide new avenues to establish fine-grained associations between the clinical characteristics, molecular processes, and disease outcomes of COPD.

Addressing the unmet needs in patients with type 2 inflammatory diseases: when quality of life can make a difference

Background

Patients with asthma (AS), atopic dermatitis (AD), allergic rhinitis (AR), eosinophilic esophagitis (EoE), chronic rhinosinusitis with nasal polyps (CRSwNP), chronic urticaria (CU), non-steroidal anti-inflammatory drugs-exacerbated respiratory disease (N-ERD), and certain phenotypes of chronic obstructive pulmonary disease (COPD), among others, have a common underlying pathogenesis known as Type 2 inflammation (T2i). These diseases often coexist with other T2i conditions and have a substantial impact on the quality of life (QoL) of patients. However, limited data on patients' experiences, perspectives, and current management of T2i diseases have been published thus far.

Aims

This survey, promoted by the patient-driven T2i Network Project, aimed at identifying the common drivers and challenges related to the QoL of patients with T2i diseases by putting the patient's perspective at the force and including it in the design of new care strategies.

Methodology

An anonymous online survey was carried out through convenience sampling between May and June 2023. The survey was codesigned by members of different patient associations, healthcare professionals and healthcare quality experts, and implemented using EUSurvey and distributed through eight patient associations from Spain. The survey consisted of 29 questions related to the participant's sociodemographic features, a series of self-reported multiple choice or rating scale questions, including diagnosis, QoL measures, disease severity, healthcare resource utilization, and quality of care.

Results

The survey included 404 participants, members from eight patient associations, the majority of whom had moderate-to-severe self-reported disease severity (93%) and one or more coexisting pathologies related to T2i (59%). Patients with more than one pathology had a significantly greater impact on QoL than those with only one pathology (p < .001). Participants with self-reported severe symptoms reported significantly worse QoL than those with mild-to-moderate severity (p < .001). More than half of the patients (56%) felt constantly bothered by the unpredictability of their illness caused by potential exposure to known or unknown disease triggers. The lack of coordination between specialists and primary care was also expressed as an area of dissatisfaction by participants, with 52% indicating a complete lack of coordination and 21% indicating an average coordination.

Conclusion

This article reports the initial findings of a patient-led initiative, which highlights the common QoL challenges faced by individuals with type 2 inflammation-related diseases and emphasizes the importance of further clinical research to improve the management of this patient group. Considering the significant impact on QoL, a multidisciplinary approach integrated into new healthcare protocols has the potential to improve patient management and QoL, shorten the time to diagnosis and reduce healthcare resource utilization.

Pulmonary emphysema subtypes defined by unsupervised machine learning on CT scans

BACKGROUND

Treatment and preventative advances for chronic obstructive pulmonary disease (COPD) have been slow due, in part, to limited subphenotypes. We tested if unsupervised machine learning on CT images would discover CT emphysema subtypes with distinct characteristics, prognoses and genetic associations.

METHODS

New CT emphysema subtypes were identified by unsupervised machine learning on only the texture and location of emphysematous regions on CT scans from 2853 participants in the Subpopulations and Intermediate Outcome Measures in COPD Study (SPIROMICS), a COPD case-control study, followed by data reduction. Subtypes were compared with symptoms and physiology among 2949 participants in the population-based Multi-Ethnic Study of Atherosclerosis (MESA) Lung Study and with prognosis among 6658 MESA participants. Associations with genome-wide single-nucleotide-polymorphisms were examined.

RESULTS

The algorithm discovered six reproducible (interlearner intraclass correlation coefficient, 0.91-1.00) CT emphysema subtypes. The most common subtype in SPIROMICS, the combined bronchitis-apical subtype, was associated with chronic bronchitis, accelerated lung function decline, hospitalisations, deaths, incident airflow limitation and a gene variant near DRD1, which is implicated in mucin hypersecretion (p=1.1 ×10-8). The second, the diffuse subtype was associated with lower weight, respiratory hospitalisations and deaths, and incident airflow limitation. The third was associated with age only. The fourth and fifth visually resembled combined pulmonary fibrosis emphysema and had distinct symptoms, physiology, prognosis and genetic associations. The sixth visually resembled vanishing lung syndrome.

CONCLUSION

Large-scale unsupervised machine learning on CT scans defined six reproducible, familiar CT emphysema subtypes that suggest paths to specific diagnosis and personalised therapies in COPD and pre-COPD.

Valaciclovir for Epstein-Barr Virus Suppression in Moderate-to-Severe COPD: A Randomized Double-Blind Placebo-Controlled Trial

BACKGROUND

Epstein-Barr virus (EBV) frequently is measured at high levels in COPD using sputum quantitative polymerase chain reaction, whereas airway immunohistochemistry analysis has shown EBV detection to be common in severe disease.

RESEARCH QUESTION

Is valaciclovir safe and effective for EBV suppression in COPD?

STUDY DESIGN AND METHODS

The Epstein-Barr Virus Suppression in COPD (EViSCO) trial was a randomized double-blind placebo-controlled trial conducted at the Mater Hospital Belfast, Northern Ireland. Eligible patients had stable moderate-to-severe COPD and sputum EBV (measured using quantitative polymerase chain reaction) and were assigned randomly (1:1) to valaciclovir (1 g tid) or matching placebo for 8 weeks. The primary efficacy outcome was sputum EBV suppression (defined as ≥ 90% sputum viral load reduction) at week 8. The primary safety outcome was the incidence of serious adverse reactions. Secondary outcome measures were FEV1 and drug tolerability. Exploratory outcomes included changes in quality of life, sputum cell counts, and cytokines.

RESULTS

From November 2, 2018, through March 12, 2020, 84 patients were assigned randomly (n = 43 to valaciclovir). Eighty-one patients completed trial follow-up and were included in the intention-to-treat analysis of the primary outcome. A greater number of participants in the valaciclovir group achieved EBV suppression (n = 36 [87.8%] vs n = 17 [42.5%]; P < .001). Valaciclovir was associated with a significant reduction in sputum EBV titer compared with placebo (-90,404 copies/mL [interquartile range, -298,000 to -15,200 copies/mL] vs -3,940 copies/mL [interquartile range, -114,400 to 50,150 copies/mL]; P = .002). A statistically nonsignificant 24-mL numerical FEV1 increase was shown in the valaciclovir group (difference, -44 mL [95% CI, -150 to 62 mL]; P = .41). However, a reduction in sputum white cell count was noted in the valaciclovir group compared with the placebo group (difference, 2.89 [95% CI, 1.5 × 106-7.4 × 106]; P = .003).

INTERPRETATION

Valaciclovir is safe and effective for EBV suppression in COPD and may attenuate the sputum inflammatory cell infiltrate. The findings from the current study provide support for a larger trial to evaluate long-term clinical outcomes.

TRIAL REGISTRY

ClinicalTrials.gov; No.: NCT03699904; URL: www.

CLINICALTRIALS

gov.

A radiomics-based logistic regression model for the assessment of emphysema severity

Introduction

The aim of this study is to develop a model that differentiates between the radiological patterns of severe and mild emphysema using radiomics parameters, as well as to examine the parameters included in the model.

Materials and Methods

Over the last 12 months, a total of 354 patients were screened based on the presence of terms such as “Fleischner”, “CLE”, and “centriacinar” in their thoracic CT reports, culminating in a study population of 82 patients. The study population was divided into Group 1 (Fleischner mild and moderate; n= 45) and Group 2 (Fleischner confluent and advanced destructive; n= 37). Volumetric segmentation was performed, focusing on the upper lobe segments of both lungs. From these segmented volumes, radiomics parameters including shape, size, first-order, and second-order features were calculated. The best model parameters were selected based on the Bayesian Information Criterion and further optimized through grid search. The final model was tested using 1000 iterations of bootstrap resampling.

Results

In the training set, performance metrics were calculated with a sensitivity of 0.862, specificity of 0.870, accuracy of 0.863, and AUC of 0.910. Correspondingly, in the test set, these values were sensitivity= 0.848; specificity= 0.865; accuracy= 0.857; and AUC= 0.907.

Conclusion

The logistic regression model, composed of radiomics parameters and trained on a limited number of cases, effectively differentiated between mild and severe radiological patterns of emphysema using computed tomography images.

Emphysema subtyping on thoracic computed tomography scans using deep neural networks

Accurate identification of emphysema subtypes and severity is crucial for effective management of COPD and the study of disease heterogeneity. Manual analysis of emphysema subtypes and severity is laborious and subjective. To address this challenge, we present a deep learning-based approach for automating the Fleischner Society's visual score system for emphysema subtyping and severity analysis. We trained and evaluated our algorithm using 9650 subjects from the COPDGene study. Our algorithm achieved the predictive accuracy at 52%, outperforming a previously published method's accuracy of 45%. In addition, the agreement between the predicted scores of our method and the visual scores was good, where the previous method obtained only moderate agreement. Our approach employs a regression training strategy to generate categorical labels while simultaneously producing high-resolution localized activation maps for visualizing the network predictions. By leveraging these dense activation maps, our method possesses the capability to compute the percentage of emphysema involvement per lung in addition to categorical severity scores. Furthermore, the proposed method extends its predictive capabilities beyond centrilobular emphysema to include paraseptal emphysema subtypes.

Advancing Treatment Strategies: A Comprehensive Review of Drug Delivery Innovations for Chronic Inflammatory Respiratory Diseases

Chronic inflammatory respiratory diseases, such as asthma, chronic obstructive pulmonary disease (COPD), and cystic fibrosis, present ongoing challenges in terms of effective treatment and management. These diseases are characterized by persistent inflammation in the airways, leading to structural changes and compromised lung function. There are several treatments available for them, such as bronchodilators, immunomodulators, and oxygen therapy. However, there are still some shortcomings in the effectiveness and side effects of drugs. To achieve optimal therapeutic outcomes while minimizing systemic side effects, targeted therapies and precise drug delivery systems are crucial to the management of these diseases. This comprehensive review focuses on the role of drug delivery systems in chronic inflammatory respiratory diseases, particularly nanoparticle-based drug delivery systems, inhaled corticosteroids (ICSs), novel biologicals, gene therapy, and personalized medicine. By examining the latest advancements and strategies in these areas, we aim to provide a thorough understanding of the current landscape and future prospects for improving treatment outcomes in these challenging conditions.

Phenomics and Robust Multiomics Data for Cardiovascular Disease Subtyping

The complex landscape of cardiovascular diseases encompasses a wide range of related pathologies arising from diverse molecular mechanisms and exhibiting heterogeneous phenotypes. This variety of manifestations poses significant challenges in the development of treatment strategies. The increasing availability of precise phenotypic and multiomics data of cardiovascular disease patient populations has spurred the development of a variety of computational disease subtyping techniques to identify distinct subgroups with unique underlying pathogeneses. In this review, we outline the essential components of computational approaches to select, integrate, and cluster omics and clinical data in the context of cardiovascular disease research. We delve into the challenges faced during different stages of the analysis, including feature selection and extraction, data integration, and clustering algorithms. Next, we highlight representative applications of subtyping pipelines in heart failure and coronary artery disease. Finally, we discuss the current challenges and future directions in the development of robust subtyping approaches that can be implemented in clinical workflows, ultimately contributing to the ongoing evolution of precision medicine in health care.

Cigarette smoke prevents M1 polarization of alveolar macrophages by suppressing NLRP3

Chronic obstructive pulmonary disease (COPD) is an inflammatory condition mainly caused by cigarette smoke (CS). Alveolar macrophages (AMs) contribute to its development, although the polarization of AMs is controversial. This study explored the polarization of AMs and mechanisms underlying their involvement in COPD. AM gene expression data from non-smokers, smokers, and COPD patients were downloaded from the GSE13896 and GSE130928 datasets. Macrophage polarization was evaluated by CIBERSORT and gene set enrichment analysis (GSEA). Polarization-related differentially expressed genes (DEGs) were identified in GSE46903. KEGG enrichment analysis and single sample GSEA were performed. M1 polarization levels were decreased in smokers and COPD patients, whereas M2 polarization did not change. In the GSE13896 and GSE130928 datasets, 27 and 19 M1-related DEGs, respectively, showed expression changes opposite to those in M1 macrophages in smokers and COPD patients compared with the control group. These M1-related DEGs were enriched in NOD-like receptor signaling pathway. Next, C57BL/6 mice were divided into control, lipopolysaccharide (LPS), CS, and LPS + CS groups, and cytokine levels in bronchoalveolar lavage fluid (BALF) and AM polarization were determined. The expression of macrophage polarization markers and NLRP3 was determined in AMs treated with CS extract (CSE), LPS, and an NLRP3 inhibitor. Cytokines levels and the percentage of M1 AMs in BALF were lower in the LPS + CS group than in the LPS group. Exposure to CSE downregulated the expression of M1 polarization markers and NLRP3 induced by LPS in AMs. The present results indicate that M1 polarization of AMs is repressed in smokers and COPD patients, and CS may inhibit LPS-induced M1 polarization of AMs by suppressing NLRP3.

Characterising paediatric mortality during and after acute illness in Sub-Saharan Africa and South Asia: a secondary analysis of the CHAIN cohort using a machine learning approach

BACKGROUND

A better understanding of which children are likely to die during acute illness will help clinicians and policy makers target resources at the most vulnerable children. We used machine learning to characterise mortality in the 30-days following admission and the 180-days after discharge from nine hospitals in low and middle-income countries (LMIC).

METHODS

A cohort of 3101 children aged 2-24 months were recruited at admission to hospital for any acute illness in Bangladesh (Dhaka and Matlab Hospitals), Pakistan (Civil Hospital Karachi), Kenya (Kilifi, Mbagathi, and Migori Hospitals), Uganda (Mulago Hospital), Malawi (Queen Elizabeth Central Hospital), and Burkina Faso (Banfora Hospital) from November 2016 to January 2019. To record mortality, children were observed during their hospitalisation and for 180 days post-discharge. Extreme gradient boosted models of death within 30 days of admission and mortality in the 180 days following discharge were built. Clusters of mortality sharing similar characteristics were identified from the models using Shapley additive values with spectral clustering.

FINDINGS

Anthropometric and laboratory parameters were the most influential predictors of both 30-day and post-discharge mortality. No WHO/IMCI syndromes were among the 25 most influential mortality predictors of mortality. For 30-day mortality, two lower-risk clusters (N = 1915, 61%) included children with higher-than-average anthropometry (1% died, 95% CI: 0-2), and children without signs of severe illness (3% died, 95% CI: 2-4%). The two highest risk 30-day mortality clusters (N = 118, 4%) were characterised by high urea and creatinine (70% died, 95% CI: 62-82%); and nutritional oedema with low platelets and reduced consciousness (97% died, 95% CI: 92-100%). For post-discharge mortality risk, two low-risk clusters (N = 1753, 61%) were defined by higher-than-average anthropometry (0% died, 95% CI: 0-1%), and gastroenteritis with lower-than-average anthropometry and without major laboratory abnormalities (0% died, 95% CI: 0-1%). Two highest risk post-discharge clusters (N = 267, 9%) included children leaving against medical advice (30% died, 95% CI: 25-37%), and severely-low anthropometry with signs of illness at discharge (46% died, 95% CI: 34-62%).

INTERPRETATION

WHO clinical syndromes are not sufficient at predicting risk. Integrating basic laboratory features such as urea, creatinine, red blood cell, lymphocyte and platelet counts into guidelines may strengthen efforts to identify high-risk children during paediatric hospitalisations.

FUNDING

Bill & Melinda Gates FoundationOPP1131320.

Identifying COPD subtypes using multi-trait genetics

Chronic Obstructive Pulmonary Disease (COPD) has a simple physiological diagnostic criterion but a wide range of clinical characteristics. The mechanisms underlying this variability in COPD phenotypes are unclear. To investigate the potential contribution of genetic variants to phenotypic heterogeneity, we examined the association of genome-wide associated lung function, COPD, and asthma variants with other phenotypes using phenome-wide association results derived in the UK Biobank. Our clustering analysis of the variants-phenotypes association matrix identified three clusters of genetic variants with different effects on white blood cell counts, height, and body mass index (BMI). To assess the potential clinical and molecular effects of these groups of variants, we investigated the association between cluster-specific genetic risk scores and phenotypes in the COPDGene cohort. We observed differences in steroid use, BMI, lymphocyte counts, chronic bronchitis, and differential gene and protein expression across the three genetic risk scores. Our results suggest that multi-phenotype analysis of obstructive lung disease-related risk variants may identify genetically driven phenotypic patterns in COPD.

Distinct COPD subtypes in former smokers revealed by gene network perturbation analysis

BACKGROUND

Chronic obstructive pulmonary disease (COPD) varies significantly in symptomatic and physiologic presentation. Identifying disease subtypes from molecular data, collected from easily accessible blood samples, can help stratify patients and guide disease management and treatment.

METHODS

Blood gene expression measured by RNA-sequencing in the COPDGene Study was analyzed using a network perturbation analysis method. Each COPD sample was compared against a learned reference gene network to determine the part that is deregulated. Gene deregulation values were used to cluster the disease samples.

RESULTS

The discovery set included 617 former smokers from COPDGene. Four distinct gene network subtypes are identified with significant differences in symptoms, exercise capacity and mortality. These clusters do not necessarily correspond with the levels of lung function impairment and are independently validated in two external cohorts: 769 former smokers from COPDGene and 431 former smokers in the Multi-Ethnic Study of Atherosclerosis (MESA). Additionally, we identify several genes that are significantly deregulated across these subtypes, including DSP and GSTM1, which have been previously associated with COPD through genome-wide association study (GWAS).

CONCLUSIONS

The identified subtypes differ in mortality and in their clinical and functional characteristics, underlining the need for multi-dimensional assessment potentially supplemented by selected markers of gene expression. The subtypes were consistent across cohorts and could be used for new patient stratification and disease prognosis.

Unsupervised Learning Identifies Computed Tomographic Measurements as Primary Drivers of Progression, Exacerbation, and Mortality in Chronic Obstructive Pulmonary Disease

Rationale: Chronic obstructive pulmonary disease (COPD) is a heterogeneous syndrome with phenotypic manifestations that tend to be distributed along a continuum. Unsupervised machine learning based on broad selection of imaging and clinical phenotypes may be used to identify primary variables that define disease axes and stratify patients with COPD. Objectives: To identify primary variables driving COPD heterogeneity using principal component analysis and to define disease axes and assess the prognostic value of these axes across three outcomes: progression, exacerbation, and mortality. Methods: We included 7,331 patients between 39 and 85 years old, of whom 40.3% were Black and 45.8% were female smokers with a mean of 44.6 pack-years, from the COPDGene (Genetic Epidemiology of COPD) phase I cohort (2008-2011) in our analysis. Out of a total of 916 phenotypes, 147 continuous clinical, spirometric, and computed tomography (CT) features were selected. For each principal component (PC), we computed a PC score based on feature weights. We used PC score distributions to define disease axes along which we divided the patients into quartiles. To assess the prognostic value of these axes, we applied logistic regression analyses to estimate 5-year (n = 4,159) and 10-year (n = 1,487) odds of progression. Cox regression and Kaplan-Meier analyses were performed to estimate 5-year and 10-year risk of exacerbation (n = 6,532) and all-cause mortality (n = 7,331). Results: The first PC, accounting for 43.7% of variance, was defined by CT measures of air trapping and emphysema. The second PC, accounting for 13.7% of variance, was defined by spirometric and CT measures of vital capacity and lung volume. The third PC, accounting for 7.9% of the variance, was defined by CT measures of lung mass, airway thickening, and body habitus. Stratification of patients across each disease axis revealed up to 3.2-fold (95% confidence interval [CI] 2.4, 4.3) greater odds of 5-year progression, 5.4-fold (95% CI 4.6, 6.3) greater risk of 5-year exacerbation, and 5.0-fold (95% CI 4.2, 6.0) greater risk of 10-year mortality between the highest and lowest quartiles. Conclusions: Unsupervised learning analysis of the COPDGene cohort reveals that CT measurements may bolster patient stratification along the continuum of COPD phenotypes. Each of the disease axes also individually demonstrate prognostic potential, predictive of future forced expiratory volume in 1 second decline, exacerbation, and mortality.

A computed tomography imaging-based subject-specific whole-lung deposition model

The respiratory tract is an important route for beneficial drug aerosol or harmful particulate matter to enter the body. To assess the therapeutic response or disease risk, whole-lung deposition models have been developed, but were limited by compartment, symmetry or stochastic approaches. In this work, we proposed an imaging-based subject-specific whole-lung deposition model. The geometries of airways and lobes were segmented from computed tomography (CT) lung images at total lung capacity (TLC), and the regional air-volume changes were calculated by registering CT images at TLC and functional residual capacity (FRC). The geometries were used to create the structure of entire subject-specific conducting airways and acinar units. The air-volume changes were used to estimate the function of subject-specific ventilation distributions among acinar units and regulate flow rates in respiratory airway models. With the airway dimensions rescaled to a desired lung volume and the airflow field simulated by a computational fluid dynamics model, particle deposition fractions were calculated using deposition probability formulae adjusted with an enhancement factor to account for the effects of secondary flow and airway geometry in proximal airways. The proposed model was validated in silico against existing whole-lung deposition models, three-dimensional (3D) computational fluid and particle dynamics (CFPD) for an acinar unit, and 3D CFPD deep lung model comprising conducting and respiratory regions. The model was further validated in vivo against the lobar particle distribution and the coefficient of variation of particle distribution obtained from CT and single-photon emission computed tomography (SPECT) images, showing good agreement. Subject-specific airway structure increased the deposition fraction of 10.0-μm particles and 0.01-μm particles by approximately 10%. An enhancement factor increased the overall deposition fractions, especially for particle sizes between 0.1 and 1.0 μm.

Novel Prehospital Phenotypes and Outcomes in Adult-Patients with Acute Disease

An early identification of prehospital phenotypes may allow health care workers to speed up and improve patients’ treatment. To determine emergency phenotypes by exclusively using prehospital clinical data, a multicenter, prospective, and observational ambulance-based study was conducted with a cohort of 3,853 adult patients treated consecutively and transferred with high priority from the scene to the hospital emergency department. Cluster analysis determined three clusters with highly different outcome scores and pathological characteristics. The first cluster presented a 30-day mortality after the index event of 45.9%. The second cluster presented a mortality of 26.3%, while mortality of the third cluster was 5.1%. This study supports the detection of three phenotypes with different risk stages and with different clinical, therapeutic, and prognostic considerations. This evidence could allow adapting treatment to each phenotype thereby helping in the decision-making process.

Applications of artificial intelligence in common pulmonary diseases

Artificial intelligence (AI) is a branch of computer science where machines are trained to imitate human-level intelligence and perform well-defined tasks. AI can provide accurate results as well as analyze vast amounts of data that cannot be analyzed via conventional statistical methods. AI has been utilized in pulmonary medicine for almost two decades and its utilization continues to expand. AI can help in making diagnoses and predicting outcomes in pulmonary diseases based on clinical data, chest imaging, lung pathology, and pulmonary function testing. AI-based applications enable physicians to use enormous amounts of data and improve their precision in the treatment of pulmonary diseases. Given the growing role of AI in pulmonary medicine, it is important for practitioners caring for patients with pulmonary diseases to understand how AI can work in order to implement it into clinical practices and improve patient care. The goal of this mini-review is to discuss the use of AI in pulmonary medicine and imaging in cases of obstructive lung disease, interstitial lung disease, infections, nodules, and lung cancer.

Axes of Prognosis: Identifying Subtypes of COVID-19 Outcomes

COVID-19 is a disease with vast impact, yet much remains unclear about patient outcomes. Most approaches to risk prediction of COVID-19 focus on binary or tertiary severity outcomes, despite the heterogeneity of the disease. In this work, we identify heterogeneous subtypes of COVID-19 outcomes by considering 'axes' of prognosis. We propose two innovative clustering approaches - 'Layered Axes' and 'Prognosis Space' - to apply on patients' outcome data. We then show how these clusters can help predict a patient's deterioration pathway on their hospital admission, using random forest classification. We illustrate this methodology on a cohort from Wuhan in early 2020. We discover interesting subgroups of poor prognosis, particularly within respiratory patients, and predict respiratory subgroup membership with high accuracy. This work could assist clinicians in identifying appropriate treatments at patients' hospital admission. Moreover, our method could be used to explore subtypes of 'long COVID' and other diseases with heterogeneous outcomes.

Application of P4 (Predictive, Preventive, Personalized, Participatory) Approach to Occupational Medicine

In recent years there has been a growth in the role of prevention in controlling the disease burden. Increasing efforts have been conveyed in the screening implementation and public health policies, and the spreading knowledge on risk factors reflects on major attention to health checks. Despite this, lifestyle changes are difficult to be adopted and the adherence to current public health services like screening and vaccinations remains suboptimal. Additionally, the prevalence and outcome of different chronic diseases and cancers is burdened by social disparities. P4 [predictive, preventive, personalized, participatory] medicine is the conceptualization of a new health care model, based on multidimensional data and machine-learning algorithms in order to develop public health intervention and monitoring the health status of the population with focus on wellbeing and healthy ageing. Each of the characteristics of P4 medicine is relevant to occupational medicine, and indeed the P4 approach appears to be particularly relevant to this discipline. In this review, we discuss the potential applications of P4 to occupational medicine, showing examples of its introduction on workplaces and hypothesizing its further implementation at the occupational level.

Individual trajectory-based care for COPD: getting closer, but not there yet

Chronic obstructive pulmonary disease (COPD) is a main cause of death due to interplaying factors, including comorbidities that interfere with symptoms and response to therapy. It is now admitted that COPD management should be based on clinical symptoms and health status and should consider the heterogeneity of patients' phenotypes and treatable traits. This precision medicine approach involves a regular assessment of the patient's status and of the expected benefits and risks of therapy. The cornerstone of COPD pharmacological therapy is inhaled long-acting bronchodilation. In patients with persistent or worsened symptoms, factors likely to interfere with treatment efficacy include the patient's non-adherence to therapy, treatment preference, inhaler misuse and/or comorbidities, which should be systematically investigated before escalation is considered. Several comorbidities are known to impact symptoms, physical and social activity and lung function. The possible long-term side-effects of inhaled corticosteroids contrasting with their over-prescription in COPD patients justify the regular assessment of their benefits and risks, and de-escalation under close monitoring after a sufficient period of stability is to be considered. While commonly used in clinical trials, the relevance of routine blood eosinophil counts to guide therapy adjustment is not fully clear. Patients' characteristics, which define phenotypes and treatable traits and thus guide therapy, often change during life, forming the basis of the concept of clinical trajectory. The application of individual trajectory-based management of COPD in clinical practice therefore implies that the benefit:risk ratio is regularly reviewed according to the evolution of the patient's traits over time to allow optimised therapy adjustments.

Different Risks of Mortality and Longitudinal Transition Trajectories in New Potential Subtypes of the Preserved Ratio Impaired Spirometry: Evidence From the English Longitudinal Study of Aging

Background: Preserved ratio impaired spirometry (PRISm), characterized by the decreased forced expiratory volume in 1 s (FEV₁) and forced vital capacity (FVC) with a preserved FEV₁/FVC ratio, is highly prevalent and heterogeneous. We aimed to identify the subtypes of PRISm and examine their differences in clinical characteristics, long-term mortality risks, and longitudinal transition trajectories.

Methods: A total of 6,616 eligible subjects were included from the English longitudinal study of aging. Two subtypes of the PRISm were identified as mild PRISm (either of FEV₁ and FVC <80% predicted value, FEV₁/FVC ≥0.7) and severe PRISm (both FEV₁ and FVC <80% predicted values, FEV₁/FVC ≥0.7). Normal spirometry was defined as both FEV₁ and FVC ≥80% predicted values and FEV₁/FVC ≥0.7. Hazard ratios (HRs) and 95% CIs were calculated by the multiple Cox regression models. Longitudinal transition trajectories were described with repeated spirometry data.

Results: At baseline, severe PRISm had increased respiratory symptoms, including higher percentages of phlegm, wheezing, dyspnea, chronic bronchitis, and emphysema than mild PRISm. After an average of 7.7 years of follow-up, severe PRISm significantly increased the risks of all-cause mortality (HR=1.91, 95%CI = 1.58–2.31), respiratory mortality (HR = 6.02, 95%CI = 2.83–12.84), and CVD mortality (HR = 2.11, 95%CI = 1.42–3.13) compared with the normal spirometry, but no significantly increased risks were found for mild PRISm. In the two longitudinal transitions, mild PRISm tended to transition toward normal spirometry (40.2 and 54.7%), but severe PRISm tended to maintain the status (42.4 and 30.4%) or transition toward Global Initiative for Chronic Obstructive Lung Disease (GOLD)2–4 (28.3 and 33.9%).

Conclusion: Two subtypes of PRISm were identified. Severe PRISm had increased respiratory symptoms, higher mortality risks, and a higher probability of progressing to GOLD2–4 than mild PRISm. These findings provided new evidence for the stratified management of PRISm.

Lung proteomic biomarkers associated with chronic obstructive pulmonary disease

Identifying protein biomarkers for chronic obstructive pulmonary disease (COPD) has been challenging. Most previous studies have used individual proteins or preselected protein panels measured in blood samples. Mass spectrometry proteomic studies of lung tissue have been based on small sample sizes. We used mass spectrometry proteomic approaches to discover protein biomarkers from 150 lung tissue samples representing COPD cases and controls. Top COPD-associated proteins were identified based on multiple linear regression analysis with false discovery rate (FDR) < 0.05. Correlations between pairs of COPD-associated proteins were examined. Machine learning models were also evaluated to identify potential combinations of protein biomarkers related to COPD. We identified 4,407 proteins passing quality controls. Twenty-five proteins were significantly associated with COPD at FDR < 0.05, including interleukin 33, ferritin (light chain and heavy chain), and two proteins related to caveolae (CAV1 and CAVIN1). Multiple previously reported plasma protein biomarkers for COPD were not significantly associated with proteomic analysis of COPD in lung tissue, although RAGE was borderline significant. Eleven pairs of top significant proteins were highly correlated (r > 0.8), including several strongly correlated with RAGE (EHD2 and CAVIN1). Machine learning models using Random Forests with the top 5% of protein biomarkers demonstrated reasonable accuracy (0.707) and area under the curve (0.714) for COPD prediction. Mass spectrometry-based proteomic analysis of lung tissue is a promising approach for the identification of biomarkers for COPD.

Identification of Metabolism-Associated Molecular Subtypes of Chronic Obstructive Pulmonary Disease

Purpose

This study aimed to identify the COPD molecular subtypes reflecting pulmonary function damage on the basis of metabolism-related gene expression, which provided the opportunity to study the metabolic heterogeneity and the association of metabolic pathways with pulmonary function damage.

Methods

Univariate linear regression and the Boruta algorithm were used to select metabolism-related genes associated with forced expiratory volume in the first second (FEV1) and FEV1/forced vital capacity (FVC) in the Evaluation of COPD to Longitudinally Identify Predictive Surrogate Endpoints (ECLIPSE) cohort. COPD subtypes were further identified by consensus clustering with best-fit. Then, we analyzed the differences in the clinical characteristics, metabolic pathways, immune cell characteristics, and transcription features among the subtypes.

Results

This study identified two subtypes (C1 and C2). C1 exhibited higher levels of lower pulmonary function and innate immunity than C2. Ten metabolic pathways were confirmed as key metabolic pathways. The pathways related to N-glycan, hexosamine, purine, alanine, aspartate and glutamate tended to be positively associated with the abundance of adaptive immune cells and negatively associated with the abundance of innate immune cells. In addition, other pathways had opposite trends. All results were verified in Genetic Epidemiology of COPD (COPDGene) datasets.

Conclusion

The two subtypes reflect the pulmonary function damage and help to further understand the metabolic mechanism of pulmonary function in COPD. Further studies are needed to prove the prognostic and therapeutic value of the subtypes.

Pulmonary Functional Imaging: Part 2-State-of-the-Art Clinical Applications and Opportunities for Improved Patient Care

Pulmonary functional imaging may be defined as the regional quantification of lung function by using primarily CT, MRI, and nuclear medicine techniques. The distribution of pulmonary physiologic parameters, including ventilation, perfusion, gas exchange, and biomechanics, can be noninvasively mapped and measured throughout the lungs. This information is not accessible by using conventional pulmonary function tests, which measure total lung function without viewing the regional distribution. The latter is important because of the heterogeneous distribution of virtually all lung disorders. Moreover, techniques such as hyperpolarized xenon 129 and helium 3 MRI can probe lung physiologic structure and microstructure at the level of the alveolar-air and alveolar-red blood cell interface, which is well beyond the spatial resolution of other clinical methods. The opportunities, challenges, and current stage of clinical deployment of pulmonary functional imaging are reviewed, including applications to chronic obstructive pulmonary disease, asthma, interstitial lung disease, pulmonary embolism, and pulmonary hypertension. Among the challenges to the deployment of pulmonary functional imaging in routine clinical practice are the need for further validation, establishment of normal values, standardization of imaging acquisition and analysis, and evidence of patient outcomes benefit. When these challenges are addressed, it is anticipated that pulmonary functional imaging will have an expanding role in the evaluation and management of patients with lung disease.

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.

Systemic Cytokine Profiles of CD4+ T Lymphocytes Correlate with Clinical Features and Functional Status in Stable COPD

Aims

To evaluate the expressions of intracellular cytokines in CD4+ T lymphocytes and to investigate the correlation between biomarker expressions and clinical and functional characteristics of stable COPD patients.

Patients and Methods

Peripheral blood was collected from 36 COPD patients, and the expression of cytokines (IL-8, IL-13, IL-17, IL-6, IL-2, IL-10, and TNF-α) in T lymphocytes CD4 + was investigated. In addition, lung function, dyspnea symptoms, quality of life, vital signs, body composition, level of physical activity, peripheral muscle strength, and functional capacity were assessed.

Results

Individuals with greater bronchial obstruction present a higher proportion of CD4 + IL-2 + lymphocytes compared to individuals with less severe bronchial obstruction. We found a positive correlation between the expression of the cytokines IL-13, IL-17, IL-6, IL-2, IL-10, and TNF-α in CD4+ T lymphocytes. In addition, we found a positive correlation between CD4+ IL-10+ T lymphocytes and lower limb muscle strength and a negative correlation between CD4+ IL-8+ T lymphocytes and peripheral oxygen saturation and steps per day.

Conclusion

Systemic CD4+IL-2+, IL-8+, and IL-10+ T lymphocytes presented a correlation with clinical characteristics and functional status in stable COPD.

Area under the expiratory flow-volume curve: predicted values by artificial neural networks

Area under expiratory flow-volume curve (AEX) has been proposed recently to be a useful spirometric tool for assessing ventilatory patterns and impairment severity. We derive here normative reference values for AEX, based on age, gender, race, height and weight, and by using artificial neural network (ANN) algorithms. We analyzed 3567 normal spirometry tests with available AEX values, performed on subjects from two countries (United States and Spain). Regular linear or optimized regression and ANN models were built using traditional predictors of lung function. The ANN-based models outperformed the de novo regression-based equations for AEX_predicted and AEX z scores using race, gender, age, height and weight as predictor factors. We compared these reference values with previously developed equations for AEX (by gender and race), and found that the ANN models led to the most accurate predictions. When we compared the performance of ANN-based models in derivation/training, internal validation/testing, and external validation random groups, we found that the models based on pooling samples from various geographic areas outperformed the other models (in both central tendency and dispersion of the residuals, ameliorating any cohort effects). In a geographically diverse cohort of subjects with normal spirometry, we computed by both regression and ANN models several predicted equations and z scores for AEX, an alternative measurement of respiratory function. We found that the dynamic nature of the ANN allows for continuous improvement of the predictive models’ performance, thus promising that the AEX could become an essential tool in assessing respiratory impairment.

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.