scholarly journals Prediction of lung emphysema in COPD by spirometry and clinical symptoms: results from COSYCONET

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Christina Kellerer ◽  
Rudolf A. Jörres ◽  
Antonius Schneider ◽  
Peter Alter ◽  
Hans-Ulrich Kauczor ◽  
...  
Keyword(s):  
Machine Learning ◽  
Clinical Symptoms ◽  
Ct Scanning ◽  
Machine Learning Algorithms ◽  
Chronic Obstructive ◽  
Diffusing Capacity ◽  
Obstructive Pulmonary Disease ◽  
Lung Emphysema ◽  
Copd Patients ◽  
St George's Respiratory Questionnaire

Abstract Background Lung emphysema is an important phenotype of chronic obstructive pulmonary disease (COPD), and CT scanning is strongly recommended to establish the diagnosis. This study aimed to identify criteria by which physicians with limited technical resources can improve the diagnosis of emphysema. Methods We studied 436 COPD patients with prospective CT scans from the COSYCONET cohort. All items of the COPD Assessment Test (CAT) and the St George’s Respiratory Questionnaire (SGRQ), the modified Medical Research Council (mMRC) scale, as well as data from spirometry and CO diffusing capacity, were used to construct binary decision trees. The importance of parameters was checked by the Random Forest and AdaBoost machine learning algorithms. Results When relying on questionnaires only, items CAT 1 & 7 and SGRQ 8 & 12 sub-item 3 were most important for the emphysema- versus airway-dominated phenotype, and among the spirometric measures FEV1/FVC. The combination of CAT item 1 (≤ 2) with mMRC (> 1) and FEV1/FVC, could raise the odds for emphysema by factor 7.7. About 50% of patients showed combinations of values that did not markedly alter the likelihood for the phenotypes, and these could be easily identified in the trees. Inclusion of CO diffusing capacity revealed the transfer coefficient as dominant measure. The results of machine learning were consistent with those of the single trees. Conclusions Selected items (cough, sleep, breathlessness, chest condition, slow walking) from comprehensive COPD questionnaires in combination with FEV1/FVC could raise or lower the likelihood for lung emphysema in patients with COPD. The simple, parsimonious approach proposed by us might help if diagnostic resources regarding respiratory diseases are limited. Trial registration ClinicalTrials.gov, Identifier: NCT01245933, registered 18 November 2010, https://clinicaltrials.gov/ct2/show/record/NCT01245933.

Prediction of chronic obstructive pulmonary disease stages using machine learning algorithms

2022 ◽  
Vol 14 (1) ◽  
pp. 0-0
Keyword(s):  
Machine Learning ◽  
Chronic Obstructive Pulmonary Disease ◽  
Pulmonary Disease ◽  
Predictive Value ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Chronic Obstructive ◽  
Optimal Prediction ◽  
Obstructive Pulmonary Disease ◽  
Disease Stages

Identifying chronic obstructive pulmonary disease (COPD) severity stages is of great importance to control the related mortality rates and reduce the associated costs. This study aims to build prediction models for COPD stages and, to compare the relative performance of five machine learning algorithms to determine the optimal prediction algorithm. This research is based on data collected from a private hospital in Egypt for the two calendar years 2018 and 2019. Five machine learning algorithms were used for the comparison. The F1 score, specificity, sensitivity, accuracy, positive predictive value and negative predictive value were the performance measures used for algorithms comparison. Analysis included 211 patients’ records. Our results show that the best performing algorithm in most of the disease stages is the PNN with the optimal prediction accuracy and hence it can be considered as a powerful prediction tool used by decision makers in predicting severity stages of COPD.

scholarly journals Study on correlation between six minute walk test and BODE index in chronic obstructive pulmonary disease patients

2020 ◽  
Vol 8 (11) ◽  
pp. 3911
Author(s):  
Babulal Bansiwal ◽  
Anees K. V. ◽  
Maneesha Jelia ◽  
Satyam Agarwal
Keyword(s):  
Chronic Obstructive Pulmonary Disease ◽  
Pulmonary Disease ◽  
Clinical Symptoms ◽  
Pearson Correlation ◽  
Outpatient Department ◽  
Airflow Limitation ◽  
Chronic Obstructive ◽  
Obstructive Pulmonary Disease ◽  
Bode Index ◽  
Copd Patients

Background: Chronic obstructive pulmonary disease is preventable and treatable disease with progressive persistent airflow limitation and enhanced chronic inflammatory response in the airways. Indian council of medical research conducted a study and found that total burden of COPD in India has more than doubled to about 14.84 million in 2011 from about 6.45 million in 1971Methods: It was an open label cross sectional study. It was conducted on patients attending the outpatient department of respiratory medicine, new medical college and hospital, Kota, over a period of one year. 100 COPD patients attending the respiratory outpatient department of GMC, Kota and fulfilling the inclusion criteria’s were included in the study. A diagnosis and severity of COPD was established by clinical symptoms and spirometric data as per GOLD guideline (ratio of FEV1 and forced vital capacity <0.7).Results: We found a significant negative correlation (Pearson correlation coefficient r = -0.664, p< 0.001) between 6 MWD and BODE index in study population.Conclusions: Thus, we concluded that the functional exercise capacity of COPD patients measured by 6MWT deteriorates linearly with severity of the disease assessed by the GOLD staging criteria. Hence we can use 6 MWT for assessing the severity of COPD in place of spirometry where the facility of spirometry is not feasible.

scholarly journals The Potential of Machine Learning Algorithms in Discriminating Chronic Obstructive Pulmonary Disease and Healthy Saliva Samples

2021 ◽  
Vol 10 (4) ◽  
pp. 155-163
Author(s):  
Atefeh Goshvarpour ◽  
Ateke Goshvarpour
Keyword(s):  
Machine Learning ◽  
Chronic Obstructive Pulmonary Disease ◽  
Pulmonary Disease ◽  
Intelligent System ◽  
Smoking Status ◽  
Human Life ◽  
Machine Learning Algorithms ◽  
Chronic Obstructive ◽  
Obstructive Pulmonary Disease ◽  
Age Range

Background: Today, with the spread of tobacco use and increased environmental pollutions, respiratory diseases are considered important factors threatening human life. Chronic obstructive pulmonary disease (COPD) is a kind of inflammatory lung disease. Clinically, COPD is currently diagnosed and monitored by spirometry as the gold-standard technique although spirometry systems encounter some limitations. Thanks to the economical handling and sampling, practicality, and non-invasiveness of saliva biomarkers, it is promising for the testing environment. Accordingly, the current analytic observational study aimed to propose an intelligent system for COPD detection. Materials and Methods: To this end, 40 COPD (8 females and 32 males in the age range of 71.67±8.27 years) and 40 controls (17 females and 23 males within the age range of 38.23±14.05 years) were considered in this study. The samples were characterized by absolute minimum value and the average value of the real and imaginary parts of saliva permittivity. Additionally, the age, gender, and smoking status of the participants were determined, and then the performance of various classifiers was evaluated by adjusting k in k-fold cross-validation (CV) and classifier parameterization. Results: The results showed that the k-nearest neighbor outperformed other classifiers. Using both 8- and 10-fold CV, the maximum classification rates of 100% were achieved for all k values. On the other hand, increasing the k in k-fold CV improved classification performances. The positive role of parameterization was revealed as well. Conclusions: Overall, these findings authenticated the potential of machine learning (ML) algorithms in the diagnosis of COPD using subjects’ saliva features and demographic information.

scholarly journals Diffusing capacity in chronic obstructive pulmonary disease assessment: A meta-analysis

2021 ◽  
Vol 18 ◽  
pp. 147997312110563
Author(s):  
Yingmeng Ni ◽  
Youchao Yu ◽  
Ranran Dai ◽  
Guochao Shi
Keyword(s):  
Chronic Obstructive Pulmonary Disease ◽  
Carbon Monoxide ◽  
Pulmonary Hypertension ◽  
Pulmonary Disease ◽  
Meta Analysis ◽  
Chronic Obstructive ◽  
Diffusing Capacity ◽  
Obstructive Pulmonary Disease ◽  
Copd Patients ◽  
Exacerbation Risk

To achieve a multidimensional evaluation of chronic obstructive pulmonary disease (COPD) patients, the spirometry measures are supplemented by assessment of symptoms, risk of exacerbations, and CT imaging. However, the measurement of diffusing capacity of the lung for carbon monoxide (DLCO) is not included in most common used models of COPD assessment. Here, we conducted a meta-analysis to evaluate the role of DLCO in COPD assessment. The studies were identified by searching the terms “diffusing capacity” OR “diffusing capacity for carbon monoxide” or “DLCO” AND “COPD” AND “assessment” in Pubmed, Cochrane Central Register of Controlled Trials (CENTRAL), MEDLINE, Embase, Scopus, and Web of Science databases. The mean difference of DLCO % predict was assessed in COPD patient with different severity (according to GOLD stage and GOLD group), between COPD patients with or without with frequent exacerbation, between survivors and non-survivors, between emphysema dominant and non-emphysema dominant COPD patients, and between COPD patients with or without pulmonary hypertension. 43 studies were included in the meta-analysis. DLCO % predicted was significantly lower in COPD patients with more severe airflow limitation (stage II/IV), more symptoms (group B/D), and high exacerbation risk (group C/D). Lower DLCO % predicted was also found in exacerbation patients and non-survivors. Low DLCO % predicted was related to emphysema dominant phenotype, and COPD patients with PH. The current meta-analysis suggested that DLCO % predicted might be an important measurement for COPD patients in terms of severity, exacerbation risk, mortality, emphysema domination, and presence of pulmonary hypertension. As diffusion capacity reflects pulmonary ventilation and perfusion at the same time, the predictive value of DLCO or DLCO combined with other criteria worth further exploration.

scholarly journals Extended Bacteria Culture-Based Clustering Identifies a Phenotype Associating Increased Cough and Enterobacterales in Stable Chronic Obstructive Pulmonary Disease

2021 ◽  
Vol 12 ◽  
Author(s):  
Anaëlle Muggeo ◽  
Jeanne-Marie Perotin ◽  
Audrey Brisebarre ◽  
Sandra Dury ◽  
Valérian Dormoy ◽  
...  
Keyword(s):  
Chronic Obstructive Pulmonary Disease ◽  
Pulmonary Disease ◽  
Clinical Symptoms ◽  
Bacterial Load ◽  
Stable State ◽  
Airflow Limitation ◽  
Chronic Obstructive ◽  
Obstructive Pulmonary Disease ◽  
Copd Patients ◽  
Mass Spectrometry Identification

Chronic obstructive pulmonary disease (COPD) is a chronic inflammatory lung disease characterized by airflow limitation. This chronic respiratory disease represents the third leading cause of death worldwide. Alteration of the airway microbiota has been reported to be associated with exacerbation frequency in COPD, but its role on the symptoms in patients at stable state is still incompletely described. This study aimed to determine whether bacteria isolated in sputum can be associated with the clinical features of COPD patients within stable state. Our study highlights, for the first time, that altered microbiota with Enterobacterales is associated with pejorative clinical symptoms in stable COPD patients. The airway microbiota of 38 patients was analyzed using an extended culture approach and mass spectrometry identification. Cluster analysis by principal coordinate analysis of the bacterial communities showed that the patients could be classified into three distinct clusters in our cohort. The clusters showed no differences in proportions of the phylum, but one of them was associated with a high prevalence of Enterobacterales (71.4% in cluster 1 vs. 0% in cluster 3), loss of microbiota diversity, and higher bacterial load (107 vs. 105 CFU/ml, respectively) and characterized by predominant cough and impact on mental health. These novel findings, supported by further studies, could lead to modifying the processing of COPD sputum in the everyday practice of clinical microbiology laboratories.

scholarly journals Using machine learning approaches to predict high-cost chronic obstructive pulmonary disease patients in China

2019 ◽  
Vol 26 (3) ◽  
pp. 1577-1598 ◽  
Author(s):  
Li Luo ◽  
Jialing Li ◽  
Shuhao Lian ◽  
Xiaoxi Zeng ◽  
Lin Sun ◽  
...  
Keyword(s):  
Machine Learning ◽  
Chronic Obstructive Pulmonary Disease ◽  
Logistic Regression ◽  
Pulmonary Disease ◽  
Predictive Performance ◽  
Western China ◽  
Chronic Obstructive ◽  
Learning Approaches ◽  
Obstructive Pulmonary Disease ◽  
Copd Patients

The accurate identification and prediction of high-cost Chronic obstructive pulmonary disease (COPD) patients is important for addressing the economic burden of COPD. The objectives of this study were to use machine learning approaches to identify and predict potential high-cost patients and explore the key variables of the forecasting model, by comparing differences in the predictive performance of different variable sets. Machine learning approaches were used to estimate the medical costs of COPD patients using the Medical Insurance Data of a large city in western China. The prediction models used were logistic regression, random forest (RF), and extreme gradient boosting (XGBoost). All three models had good predictive performance. The XGBoost model outperformed the others. The areas under the ROC curve for Logistic Regression, RF and XGBoost were 0.787, 0.792 and 0.801. The precision and accuracy metrics indicated that the methods achieved correct and reliable results. The results of this study can be used by healthcare data analysts, policy makers, insurers, and healthcare planners to improve the delivery of health services.

Comparative study of the efficacy and safety of theophylline and doxofylline in patients with bronchial asthma and chronic obstructive pulmonary disease

2015 ◽  
Vol 26 (5) ◽  
Author(s):  
Dushyant Lal ◽  
Sachin Manocha ◽  
Arunabha Ray ◽  
V.K. Vijayan ◽  
Raj Kumar
Keyword(s):  
Chronic Obstructive Pulmonary Disease ◽  
Comparative Study ◽  
Pulmonary Disease ◽  
Bronchial Asthma ◽  
Clinical Symptoms ◽  
Chronic Obstructive ◽  
Efficacy And Safety ◽  
Obstructive Pulmonary Disease ◽  
Beneficial Effects ◽  
Copd Patients

AbstractBronchial asthma and chronic obstructive pulmonary disease (COPD) are the major obstructive disorders that may contribute to the severity in individual patients. The present study was designed to compare the efficacy and safety of theophylline and doxofylline in patients with bronchial asthma and COPD.A total of 60 patients, 30 each with bronchial asthma and COPD, were enrolled for the study. Each group of 30 patients received standard treatment for asthma and COPD. Each group was again subdivided into two with 15 patients each, who received theophylline or doxofylline in addition to standard therapy, for a period of 2 months. Each patient was followed up fortnightly for the assessment of efficacy parameters using a pulmonary function test (PFT), clinical symptoms and emergency drug use, and safety was assessed by recording adverse drug reactions.Both theophylline and doxofylline produced enhancements in PFT at different time intervals in both asthma and COPD patients. The maximum beneficial effects were seen at 6 weeks for asthma patients and at 8 weeks for COPD patients for both theophylline and doxofylline.The comparative study showed that doxofylline was more effective as evidenced by improvement in PFT as well as clinical symptoms, and reduced incidence of adverse effects and emergency bronchodilator use.

scholarly journals Clinical characteristics of tobacco smoke-induced versus biomass fuelinduced chronic obstructive pulmonary disease

2015 ◽  
Vol 3 (3) ◽  
pp. 126-129 ◽  
Author(s):  
Lin-ling Cheng ◽  
Ya-ya Liu ◽  
Zhu-quan Su ◽  
Jun Liu ◽  
Rong-chang Chen ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Tobacco Smoke ◽  
Clinical Symptoms ◽  
Chronic Obstructive ◽  
General Health Status ◽  
Biomass Fuels ◽  
Obstructive Pulmonary Disease ◽  
Male And Female ◽  
Copd Patients ◽  
Significant Difference

Abstract Objective: To investigate differences in clinical features between tobacco smoke-induced and biomass fuel-induced chronic obstructive pulmonary disease (COPD). Methods: We retrospectively analyzed 206 patients with COPD caused by exposure to tobacco smoke and 81 cases of COPD caused by exposure to biomass fuels who received treatment in our hospital between 2011 March and 2014 March. Difference in general health status, clinical symptoms, the dyspnea score, and comorbidities between the two groups were compared. In addition, pulmonary function, grading, and acute exacerbations were also compared. Results: (1) Difference in general health status: Male and female patients with COPD caused by exposure to tobacco smoke were 83.5 and 16.5%, respectively. Male and female patients with COPD caused by exposure to smoke from biomass fuels were 14.8 and 85.2% (χ2 = 27.2, P < 0.05), respectively. Tobacco smoke-induced COPD was more prevalent in men, and COPD caused by exposure to smoke from biomass fuels was more prevalent in women. After gender adjustment, body mass index (BMI) was lower in women with COPD caused by exposure to smoke from biomass fuels than those by tobacco smoke. There was no statistically significant difference in other indicators, such as age. (2): Difference in clinical symptoms: No statistically significant difference in the modified British Medical Research Counsel (mMRC) Questionnaire, a measure of breathlessness, was observed between the two groups. Dyspnea was more common in COPD patients that was caused by exposure to biomass fuels (38.3%) than by tobacco smoke (11.1%) (χ2 = 17.9, P < 0.05). The comorbidities of allergic diseases (such as allergic rhinitis, bronchial asthma) were more prevalent in COPD patients that was caused by exposure to smoke from biomass fuels (43.2%) than by tobacco smoke (18%) (χ2= 16.1, P < 0.05). However, COPD comorbid with lung cancer was more prevalent in those cases that were caused by exposure to tobacco smoke (7.77%) than in cases caused by exposure to smoke from biomass fuels (3.7%) (χ2 = 9.7, P < 0.05). (3) Differences in grading of pulmonary function: After gender adjustment, patients with COPD caused by exposure to biomass fuels were mostly in grade B or D. (4) Exacerbations: No significant difference in exacerbations per year was noted between the two groups. Conclusions: Marked differences exist between patients with COPD caused by exposure to tobacco smoke and smoke from biomass fuels. Patients with COPD caused by exposure to biofuels are mostly females with lower BMI and often with many clinical symptoms and complications, such as allergic rhinitis and bronchial asthma. Such patients are often in stage B or D. Tobacco smoke-induced COPD is more prevalent in male patients, often with complications in the form of lung cancer.

Sign in / Sign up

Export Citation Format

Share Document