RESUMEN
A high level of particulate matter (PM) in air is correlated with the onset and development of chronic respiratory diseases. We conducted a systematic literature review, searching the MEDLINE, EMBASE, and Cochrane databases for studies of biomarkers of the effect of PM exposure on chronic respiratory diseases and the progression thereof. Thirty-eight articles on biomarkers of the progression of chronic respiratory diseases after exposure to PM were identified, four of which were eligible for review. Serum, sputum, urine, and exhaled breath condensate biomarkers of the effect of PM exposure on chronic obstructive pulmonary disease (COPD) and asthma had a variety of underlying mechanisms. We summarized the functions of biomarkers linked to COPD and asthma and their biological plausibility. We identified few biomarkers of PM exposure-related progression of chronic respiratory diseases. The included studies were restricted to those on biomarkers of the relationship of PM exposure with the progression of chronic respiratory diseases. The predictive power of biomarkers of the effect of PM exposure on chronic respiratory diseases varies according to the functions of the biomarkers.
RESUMEN
Background@#Shift work, including night shift work, during pregnancy has been associated with adverse birth outcomes such as small for gestational age (SGA) infants and preterm births. This study, conducted in South Korea using the Korean CHildren’s ENvironmental health Study (Ko-CHENS) cohort, aimed to investigate the association between shift work and night shift status during pregnancy and adverse birth outcomes. @*Methods@#The Korean Ko-CHENS is a nationwide prospective birth cohort study of children’s environmental diseases, conducted by the Ministry of Environment and the National Institute of Environmental Research. This study included pregnant women recruited from 2015 to 2020 for Ko-CHENS Core Cohorts, and 4,944 out of a total of 5,213 pregnant women were selected as final subjects. A logistic regression model was used to identify the risk factors affecting SGA births, preterm births, and low-birth-weight infants, and the odds ratio (OR) was adjusted.This was confirmed by calculating ORs. Maternal age, infant sex, maternal educational status, body mass index, smoking status, alcohol consumption status, parity, gestational diabetes mellitus, preeclampsia, and abortion history were used as adjusted variables. @*Results@#No statistically significant differences were observed in the birth outcomes or maternal working patterns. There were no significant differences in the adjusted odds ratios (aORs) of SGA and preterm births between the non-worker, day worker, and shift worker.However, there was a significant difference in the aORs of SGA between non-workers and night shift workers. (aORs [95% confidence interval], 2.643 [1.193–5.859]). @*Conclusion@#Working during pregnancy did not increase the risk of SGA or preterm birth, and night shift work did not increase the risk of preterm birth. However, night-shift work increases the risk of SGA.
RESUMEN
Chronic respiratory diseases such as idiopathic pulmonary fibrosis, chronic obstructive pulmonary disease, and respiratory infections injure the alveoli; the damage evoked is mostly irreversible and occasionally leads to death. Achieving a detailed understanding of the pathogenesis of these fatal respiratory diseases has been hampered by limited access to human alveolar tissue and the differences between mice and humans. Thus, the development of human alveolar organoid (AO) models that mimic in vivo physiology and pathophysiology has gained tremendous attention over the last decade. In recent years, human pluripotent stem cells (hPSCs) have been successfully employed to generate several types of organoids representing different respiratory compartments, including alveolar regions. However, despite continued advances in three-dimensional culture techniques and single-cell genomics, there is still a profound need to improve the cellular heterogeneity and maturity of AOs to recapitulate the key histological and functional features of in vivo alveolar tissue. In particular, the incorporation of immune cells such as macrophages into hPSC-AO systems is crucial for disease modeling and subsequent drug screening. In this review, we summarize current methods for differentiating alveolar epithelial cells from hPSCs followed by AO generation and their applications in disease modeling, drug testing, and toxicity evaluation. In addition, we review how current hPSC-AOs closely resemble in vivo alveoli in terms of phenotype, cellular heterogeneity, and maturity.
RESUMEN
Objectives@#In the Fourth Industrial Revolution, there is a focus on managing diverse medical data to improve healthcare and prevent disease. The challenges include tracking detailed medical records across multiple institutions and the necessity of linking domestic public medical entities for efficient data sharing. This study explores MyHealthWay, a Korean healthcare platform designed to facilitate the integration and transfer of medical data from various sources, examining its development, importance, and legal implications. @*Methods@#To evaluate the management status and utilization of MyHealthWay, we analyzed data types, security, legal issues, domestic versus international issues, and infrastructure. Additionally, we discussed challenges such as resource and infrastructure constraints, regulatory hurdles, and future considerations for data management. @*Results@#The secure sharing of medical information via MyHealthWay can reduce the distance between patients and healthcare facilities, fostering personalized care and self-management of health. However, this approach faces legal challenges, particularly relating to data standardization and access to personal health information. Legal challenges in data standardization and access, particularly for secondary uses such as research, necessitate improved regulations. There is a crucial need for detailed governmental guidelines and clear data ownership standards at institutional levels. @*Conclusions@#This report highlights the role of Korea's MyHealthWay, which was launched in 2023, in transforming healthcare through systematic data integration. Challenges include data privacy and legal complexities, and there is a need for data standardization and individual empowerment in health data management within a systematic medical big data framework.
RESUMEN
Background@#Worldwide, sepsis is the leading cause of death in hospitals. If mortality rates in patients with sepsis can be predicted early, medical resources can be allocated efficiently. We constructed machine learning (ML) models to predict the mortality of patients with sepsis in a hospital emergency department. @*Methods@#This study prospectively collected nationwide data from an ongoing multicenter cohort of patients with sepsis identified in the emergency department. Patients were enrolled from 19 hospitals between September 2019 and December 2020. For acquired data from 3,657 survivors and 1,455 deaths, six ML models (logistic regression, support vector machine, random forest, extreme gradient boosting [XGBoost], light gradient boosting machine, and categorical boosting [CatBoost]) were constructed using fivefold cross-validation to predict mortality. Through these models, 44 clinical variables measured on the day of admission were compared with six sequential organ failure assessment (SOFA) components (PaO 2 /FIO 2 [PF], platelets (PLT), bilirubin, cardiovascular, Glasgow Coma Scale score, and creatinine).The confidence interval (CI) was obtained by performing 10,000 repeated measurements via random sampling of the test dataset. All results were explained and interpreted using Shapley’s additive explanations (SHAP). @*Results@#Of the 5,112 participants, CatBoost exhibited the highest area under the curve (AUC) of 0.800 (95% CI, 0.756–0.840) using clinical variables. Using the SOFA components for the same patient, XGBoost exhibited the highest AUC of 0.678 (95% CI, 0.626–0.730). As interpreted by SHAP, albumin, lactate, blood urea nitrogen, and international normalization ratio were determined to significantly affect the results. Additionally, PF and PLTs in the SOFA component significantly influenced the prediction results. @*Conclusion@#Newly established ML-based models achieved good prediction of mortality in patients with sepsis. Using several clinical variables acquired at the baseline can provide more accurate results for early predictions than using SOFA components. Additionally, the impact of each variable was identified.
RESUMEN
Del-Nido cardioplegia (DNc) is a single-dose cardioplegia that is widely used in human medicine because of its long duration. In this report, we describe two cases of open-heart surgery with cardiopulmonary bypass (CPB) using DNc. One dog was diagnosed with partial atrioventricular septal defect, and the other dog was diagnosed with myxomatous mitral valve disease stage D. Both dogs were treated with open-heart surgery with DNc to induce temporary cardiac arrest. No complications from DNc were observed, and the patients were discharged. Veterinary heart surgeons should consider DNc as an option for temporary cardiac arrest during open-heart surgery with CPB.
RESUMEN
Background@#Respiratory pathogen infections and air pollution are main causes of acute exacerbation of chronic obstructive pulmonary disease (AECOPD). Air pollution has a direct effect on the airway epithelial barrier and the immune system, which can have an influence on infection. However, studies on the relationship between respiratory infections and air pollutants in severe AECOPD are limited. Thus, the objective of this study was to investigate the correlation between air pollution and respiratory pathogen in severe AECOPD. @*Methods@#This multicenter observational study was conducted by reviewing electronic medical records of patients with AECOPD at 28 hospitals in South Korea. Patients were divided into four groups according to the comprehensive air-quality index (CAI) used in Korea. Identification rates of bacteria and viruses of each group were analyzed. @*Results@#Viral pathogens were identified in 270 (36.7%) of 735 patients. Viral identification rate was different (P = 0.012) according to air pollution. Specifically, the virus detection rate was 55.9% in the group of CAI ‘D’ with the highest air pollution. It was 24.4% in the group of CAI ‘A’ with the lowest air pollution. This pattern was clearly seen for influenza virus A (P = 0.042). When further analysis was performed with particulate matter (PM), the higher/lower the PM level, the higher/lower the virus detection rate. However, no significant difference was found in the analysis related to bacteria. @*Conclusion@#Air pollution may make COPD patients more susceptible to respiratory viral infections, especially influenza virus A. Thus, on days with poor air quality, COPD patients need to be more careful about respiratory infections.
RESUMEN
Background@#Although respiratory tract infection is one of the most important factors triggering acute exacerbation of chronic obstructive pulmonary disease (AE-COPD), limited data are available to suggest an epidemiologic pattern of microbiology in South Korea. @*Methods@#A multicenter observational study was conducted between January 2015 and December 2018 across 28 hospitals in South Korea. Adult patients with moderate-to-severe acute exacerbations of COPD were eligible to participate in the present study. The participants underwent all conventional tests to identify etiology of microbial pathogenesis. The primary outcome was the percentage of different microbiological pathogens causing AE-COPD. A comparative microbiological analysis of the patients with overlapping asthma–COPD (ACO) and pure COPD was performed. @*Results@#We included 1,186 patients with AE-COPD. Patients with pure COPD constituted 87.9% and those with ACO accounted for 12.1%. Nearly half of the patients used an inhaled corticosteroid-containing regimen and one-fifth used systemic corticosteroids. Respiratory pathogens were found in 55.3% of all such patients. Bacteria and viruses were detected in 33% and 33.2%, respectively. Bacterial and viral coinfections were found in 10.9%. The most frequently detected bacteria were Pseudomonas aeruginosa (9.8%), and the most frequently detected virus was influenza A (10.4%). Multiple bacterial infections were more likely to appear in ACO than in pure COPD (8.3% vs. 3.6%, p=0.016). @*Conclusion@#Distinct microbiological patterns were identified in patients with moderate-to-severe AE-COPD in South Korea. These findings may improve evidence-based management of patients with AE-COPD and represent the basis for further studies investigating infectious pathogens in patients with COPD.
RESUMEN
Genetic and environmental risk factors influence the development of respiratory diseases. While cigarette smoking is a personal risk factor, ambient air pollution and chemicals such as asbestos are major environmental risk factors for respiratory diseases. In addition, the growth of children’s lung is also sensitively affected by environmental exposure to pollutants and heavy metals. Many studies have found that certain populations including children, elderly and residents near chemical factories are more susceptible to environmental lung diseases, which indicate the importance and benefits of strategic planning at the national level. Although genetic risk factors may be hard to control, many of the environmental risk factors can be prevented and managed by correct policy-making. Therefore, in-depth researches should be continued, and careful considerations should be given to policy-making in efforts to lower environmental risk factors and make a better environment for the future generation. Environmental exposure leads to epigenetic changes in airway and lung tissues as well as blood cells. Although not yet completely understood, the mechanism involved in such changes can act as biomarkers or therapeutic targets for the diagnosis and treatment of environmental lung diseases.
RESUMEN
Genetic and environmental risk factors influence the development of respiratory diseases. While cigarette smoking is a personal risk factor, ambient air pollution and chemicals such as asbestos are major environmental risk factors for respiratory diseases. In addition, the growth of children’s lung is also sensitively affected by environmental exposure to pollutants and heavy metals. Many studies have found that certain populations including children, elderly and residents near chemical factories are more susceptible to environmental lung diseases, which indicate the importance and benefits of strategic planning at the national level. Although genetic risk factors may be hard to control, many of the environmental risk factors can be prevented and managed by correct policy-making. Therefore, in-depth researches should be continued, and careful considerations should be given to policy-making in efforts to lower environmental risk factors and make a better environment for the future generation. Environmental exposure leads to epigenetic changes in airway and lung tissues as well as blood cells. Although not yet completely understood, the mechanism involved in such changes can act as biomarkers or therapeutic targets for the diagnosis and treatment of environmental lung diseases.
RESUMEN
Periodontal disease is primarily associated with bacterial infection such as dental plaque. Dental plaque, an oral biofilm harboring a complex microbial community, can cause various inflammatory reactions in periodontal tissue. In many cases, the local bacterial invasion and host-mediated immune responses lead to severe alveolar bone destruction. To date, plaque control, non-surgical, and surgical interventions have been the conventional periodontal treatment modalities. Although adjuvant therapies including antibiotics or supplements have accompanied these procedures, their usage has been limited by antibiotic resistance, as well as their partial effectiveness. Therefore, new strategies are needed to control local inflammation in the periodontium and host immune responses. In recent years, target molecules that modulate microbial signaling mechanisms, host inflammatory substances, and bone immune responses have received considerable attention by researchers. In this review, we introduce three approaches that suggest a way forward for the development of new treatments for periodontal disease; (1) quorum quenching using quorum sensing inhibitors, (2) inflammasome targeting, and (3) use of FDA-approved anabolic agents, including Teriparatide and sclerostin antibody.
RESUMEN
Periodontal disease is primarily associated with bacterial infection such as dental plaque. Dental plaque, an oral biofilm harboring a complex microbial community, can cause various inflammatory reactions in periodontal tissue. In many cases, the local bacterial invasion and host-mediated immune responses lead to severe alveolar bone destruction. To date, plaque control, non-surgical, and surgical interventions have been the conventional periodontal treatment modalities. Although adjuvant therapies including antibiotics or supplements have accompanied these procedures, their usage has been limited by antibiotic resistance, as well as their partial effectiveness. Therefore, new strategies are needed to control local inflammation in the periodontium and host immune responses. In recent years, target molecules that modulate microbial signaling mechanisms, host inflammatory substances, and bone immune responses have received considerable attention by researchers. In this review, we introduce three approaches that suggest a way forward for the development of new treatments for periodontal disease; (1) quorum quenching using quorum sensing inhibitors, (2) inflammasome targeting, and (3) use of FDA-approved anabolic agents, including Teriparatide and sclerostin antibody.
RESUMEN
Background@#Chronic obstructive pulmonary disease (COPD) is a common chronic respiratory disease with increased prevalence in the elderly. Telomeres are repetitive DNA sequences found at the end of the chromosome, which progressively shorten as cells divide. Telomere length is known to be a molecular marker of aging. This study aimed to assess the relationship between telomere length and the risk of COPD, lung function, respiratory symptoms, and emphysema index in Chronic Obstructive Pulmonary Disease in Dusty Areas (CODA) cohort. @*Methods@#We extracted DNA from the peripheral blood samples of 446 participants, including 285 COPD patients and 161 control participants. We measured absolute telomere length using quantitative real-time polymerase chain reaction. All participants underwent spirometry and quantitative computed tomography scan. Questionnaires assessing respiratory symptoms and the COPD Assessment Test was filled by all the participants. @*Results@#The mean age of participants at the baseline visit was 72.5±7.1 years. Males accounted for 72% (321 participants) of the all participants. The mean telomere length was lower in the COPD group compared to the non-COPD group (COPD, 16.81±13.90 kb; non-COPD, 21.97±14.43 kb). In COPD patients, 112 (75.7%) were distributed as tertile 1 (shortest), 91 (61.1%) as tertile 2 and 82 (55%) as tertile 3 (longest). We did not find significant associations between telomere length and lung function, exacerbation, airway wall thickness, and emphysema index after adjusting for sex, age, and smoking status. @*Conclusion@#In this study, the relationship between various COPD phenotypes and telomere length was analyzed, but no significant statistical associations were shown.
RESUMEN
Background@#Chronic obstructive pulmonary disease (COPD) is a common chronic respiratory disease with increased prevalence in the elderly. Telomeres are repetitive DNA sequences found at the end of the chromosome, which progressively shorten as cells divide. Telomere length is known to be a molecular marker of aging. This study aimed to assess the relationship between telomere length and the risk of COPD, lung function, respiratory symptoms, and emphysema index in Chronic Obstructive Pulmonary Disease in Dusty Areas (CODA) cohort. @*Methods@#We extracted DNA from the peripheral blood samples of 446 participants, including 285 COPD patients and 161 control participants. We measured absolute telomere length using quantitative real-time polymerase chain reaction. All participants underwent spirometry and quantitative computed tomography scan. Questionnaires assessing respiratory symptoms and the COPD Assessment Test was filled by all the participants. @*Results@#The mean age of participants at the baseline visit was 72.5±7.1 years. Males accounted for 72% (321 participants) of the all participants. The mean telomere length was lower in the COPD group compared to the non-COPD group (COPD, 16.81±13.90 kb; non-COPD, 21.97±14.43 kb). In COPD patients, 112 (75.7%) were distributed as tertile 1 (shortest), 91 (61.1%) as tertile 2 and 82 (55%) as tertile 3 (longest). We did not find significant associations between telomere length and lung function, exacerbation, airway wall thickness, and emphysema index after adjusting for sex, age, and smoking status. @*Conclusion@#In this study, the relationship between various COPD phenotypes and telomere length was analyzed, but no significant statistical associations were shown.
RESUMEN
Background/Aims@#Lung function is an objective indicator of diagnosis and prognosis of respiratory diseases. Many common genetic variants have been associated with lung function in multiple ethnic populations. We looked for coding variants associated with forced expiratory volume in 1 second (FEV1) and FEV1/forced vital capacity (FVC) in the Korean general population. @*Methods@#We carried out exome array analysis and lung function measurements of the FEV1 and FEV1/FVC in 7,524 individuals of the Korean population. We evaluated single variants with minor allele frequency greater than 0.5%. We performed look-ups for candidate coding variants associations in the UK Biobank, SpiroMeta, and CHARGE consortia. @*Results@#We identified coding variants in the SMIM29 (C6orf1) (p = 1.2 × 10–5) and HMGA1 locus on chromosome 6p21, the GIT2 (p = 6.5 × 10–5) locus on chromosome 12q24, and the ARHGEF40 (p = 9.9 × 10–5) locus on chromosome 14q11 as having a significant association with lung function (FEV1). We also confirmed a previously reported association with lung function and chronic obstructive pulmonary disease in the FAM13A (p = 4.54 × 10–6) locus on chromosome 4q22, in TNXB (p = 1.30 × 10–6) and in AGER (p = 1.09 × 10–8) locus on chromosome 6p21. @*Conclusions@#Our exome array analysis identified that several protein coding variants were associated with lung function in the Korean population. Common coding variants in SMIM29 (C6orf1), HMGA1, GIT2, FAM13A, TNXB, AGER and low-frequency variant in ARHGEF40 potentially affect lung function, which warrant further study.
RESUMEN
Background@#Idiopathic pulmonary fibrosis (IPF) is a chronic and progressive interstitial lung disease. Despite alveolar epithelial cells is crucial role in lung, its contribution and the associated biomarker remain unknown in the pathogenesis of IPF. Recently, environmental factors including stone dust, silica and cigarette smoking were found as risk factors involved in IPF. Receptor for advanced glycation end products (RAGE) is a member of the immunoglobulin super family of cell surface receptors. It has been shown that interaction between RAGE and its ligands on immune cells mediates cellular migration and regulation of pro-inflammation. RAGE is highly expressed in the lung, in particular, alveolar epithelial cells. Therefore, we determined whether RAGE expression is associated with fibrosis-associated genes in patients with IPF and mice. @*Results@#When bleomycin (BLM) was intratracheally administered to C57BL/6 mice for 1, 2 weeks, macrophage and neutrophils were significantly increased. The fibrotic nodule formed and accumulation of collagen was determined after BLM injection in H&E- and Masson’s trichrome staining. Levels of elastin, Col1a1 and fibronectin were increased in quantitative real-time PCR and protein levels of α-SMA was increased in western blot analysis. In the lung tissues of 1 mg/kg BLM-induced mice, RAGE expression was gradually decreased in 1- and 2 weeks in immunohistochemistry and western blot analysis, and 3 mg/kg of BLM-induced mice exhibited decreased RAGE levels while α-SMA expression was increased. We next determined RAGE expression in the lungs of IPF patients using immunohistochemistry.As a result, RAGE expression was decreased, while α-SMA expression was increased compared with non-IPF subjects. @*Conclusions@#Our findings suggest that reduced RAGE was associated with increased fibrotic genes in BLM-induced mice and patients with IPF. Therefore, RAGE could be applied with a biomarker for prognosis and diagnosis in the pathogenesis of IPF.
RESUMEN
Purpose@#To evaluate the long-term radiologic and clinical outcomes of stent-graft placement for the treatment of post-pancreaticoduodenectomy arterial hemorrhage (PPAH) based on the imaging findings of stent-graft patency and results of liver function tests. @*Materials and Methods@#We retrospectively reviewed the medical records of nine consecutive patients who underwent stent-graft placement for PPAH between June 2012 and May 2017. We analyzed the immediate technical and clinical outcomes and liver function test results. Stentgraft patency was evaluated using serial CT angiography images. @*Results@#All stent-grafts were deployed in the intended position for the immediate cessation of arterial hemorrhage and preservation of hepatic arterial blood flow. Technical success was achieved in all nine patients. Eight patients survived after discharge, and one patient died on postoperative day 28. The median follow-up duration was 781 days (range: 28–1766 days). Follow-up CT angiography revealed stent-graft occlusion in all patients. However, serum aspartate aminotransferase or alanine aminotransferase levels in all patients were well below those observed in hepatic infarction cases. @*Conclusion@#Stent-graft placement is a safe and effective treatment method for acute life-threatening PPAH. Liver function and distal hepatic arterial blood flow were maintained postoperatively despite the high incidence of stent-graft occlusion observed on follow-up CT.
RESUMEN
Background@#Although patients with chronic obstructive pulmonary disease (COPD) experience high morbidity and mortality worldwide, few biomarkers are available for COPD.Here, we analyzed potential biomarkers for the diagnosis of COPD by using word embedding. @*Methods@#To determine which biomarkers are likely to be associated with COPD, we selected respiratory disease-related biomarkers. Degrees of similarity between the 26 selected biomarkers and COPD were measured by word embedding. And we infer the similarity with COPD through the word embedding model trained in the large-capacity medical corpus, and search for biomarkers with high similarity among them. We used Word2Vec, Canonical Correlation Analysis, and Global Vector for word embedding. We evaluated the associations of selected biomarkers with COPD parameters in a cohort of patients with COPD. @*Results@#Cytokeratin 19 fragment (Cyfra 21-1) was selected because of its high similarity and its significant correlation with the COPD phenotype. Serum Cyfra 21-1 levels were determined in patients with COPD and controls (4.3 ± 5.9 vs. 3.9 ± 3.6 ng/mL, P = 0.611). The emphysema index was significantly correlated with the serum Cyfra 21-1 level (correlation coefficient = 0.219,P = 0.015). @*Conclusion@#Word embedding may be used for the discovery of biomarkers for COPD and Cyfra 21-1 may be used as a biomarker for emphysema. Additional studies are needed to validate Cyfra 21-1 as a biomarker for COPD.
RESUMEN
Purpose@#To evaluate the long-term radiologic and clinical outcomes of stent-graft placement for the treatment of post-pancreaticoduodenectomy arterial hemorrhage (PPAH) based on the imaging findings of stent-graft patency and results of liver function tests. @*Materials and Methods@#We retrospectively reviewed the medical records of nine consecutive patients who underwent stent-graft placement for PPAH between June 2012 and May 2017. We analyzed the immediate technical and clinical outcomes and liver function test results. Stentgraft patency was evaluated using serial CT angiography images. @*Results@#All stent-grafts were deployed in the intended position for the immediate cessation of arterial hemorrhage and preservation of hepatic arterial blood flow. Technical success was achieved in all nine patients. Eight patients survived after discharge, and one patient died on postoperative day 28. The median follow-up duration was 781 days (range: 28–1766 days). Follow-up CT angiography revealed stent-graft occlusion in all patients. However, serum aspartate aminotransferase or alanine aminotransferase levels in all patients were well below those observed in hepatic infarction cases. @*Conclusion@#Stent-graft placement is a safe and effective treatment method for acute life-threatening PPAH. Liver function and distal hepatic arterial blood flow were maintained postoperatively despite the high incidence of stent-graft occlusion observed on follow-up CT.
RESUMEN
Background@#Although patients with chronic obstructive pulmonary disease (COPD) experience high morbidity and mortality worldwide, few biomarkers are available for COPD.Here, we analyzed potential biomarkers for the diagnosis of COPD by using word embedding. @*Methods@#To determine which biomarkers are likely to be associated with COPD, we selected respiratory disease-related biomarkers. Degrees of similarity between the 26 selected biomarkers and COPD were measured by word embedding. And we infer the similarity with COPD through the word embedding model trained in the large-capacity medical corpus, and search for biomarkers with high similarity among them. We used Word2Vec, Canonical Correlation Analysis, and Global Vector for word embedding. We evaluated the associations of selected biomarkers with COPD parameters in a cohort of patients with COPD. @*Results@#Cytokeratin 19 fragment (Cyfra 21-1) was selected because of its high similarity and its significant correlation with the COPD phenotype. Serum Cyfra 21-1 levels were determined in patients with COPD and controls (4.3 ± 5.9 vs. 3.9 ± 3.6 ng/mL, P = 0.611). The emphysema index was significantly correlated with the serum Cyfra 21-1 level (correlation coefficient = 0.219,P = 0.015). @*Conclusion@#Word embedding may be used for the discovery of biomarkers for COPD and Cyfra 21-1 may be used as a biomarker for emphysema. Additional studies are needed to validate Cyfra 21-1 as a biomarker for COPD.