Dataset Information

Machine Learning Prediction of Progression in Forced Expiratory Volume in 1 Second in the COPDGene® Study.

ABSTRACT:

Background

The heterogeneous nature of chronic obstructive pulmonary disease (COPD) complicates the identification of the predictors of disease progression. We aimed to improve the prediction of disease progression in COPD by using machine learning and incorporating a rich dataset of phenotypic features.

Methods

We included 4496 smokers with available data from their enrollment and 5-year follow-up visits in the COPD Genetic Epidemiology (COPDGene^®) study. We constructed linear regression (LR) and supervised random forest models to predict 5-year progression in forced expiratory in 1 second (FEV₁) from 46 baseline features. Using cross-validation, we randomly partitioned participants into training and testing samples. We also validated the results in the COPDGene 10-year follow-up visit.

Results

Predicting the change in FEV₁ over time is more challenging than simply predicting the future absolute FEV₁ level. For random forest, R-squared was 0.15 and the area under the receiver operator characteristic (ROC) curves for the prediction of participants in the top quartile of observed progression was 0.71 (testing) and respectively, 0.10 and 0.70 (validation). Random forest provided slightly better performance than LR. The accuracy was best for Global initiative for chronic Obstructive Lung Disease (GOLD) grades 1-2 participants, and it was harder to achieve accurate prediction in advanced stages of the disease. Predictive variables differed in their relative importance as well as for the predictions by GOLD.

Conclusion

Random forest, along with deep phenotyping, predicts FEV₁ progression with reasonable accuracy. There is significant room for improvement in future models. This prediction model facilitates the identification of smokers at increased risk for rapid disease progression. Such findings may be useful in the selection of patient populations for targeted clinical trials.

SUBMITTER: Boueiz A

PROVIDER: S-EPMC9448009 | biostudies-literature | 2022 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine Learning Prediction of Progression in Forced Expiratory Volume in 1 Second in the COPDGene® Study.

Boueiz Adel A Xu Zhonghui Z Chang Yale Y Masoomi Aria A Gregory Andrew A Lutz Sharon M SM Qiao Dandi D Crapo James D JD Dy Jennifer G JG Silverman Edwin K EK Castaldi Peter J PJ

Chronic obstructive pulmonary diseases (Miami, Fla.) 20220701 3

<h4>Background</h4>The heterogeneous nature of chronic obstructive pulmonary disease (COPD) complicates the identification of the predictors of disease progression. We aimed to improve the prediction of disease progression in COPD by using machine learning and incorporating a rich dataset of phenotypic features.<h4>Methods</h4>We included 4496 smokers with available data from their enrollment and 5-year follow-up visits in the COPD Genetic Epidemiology (COPDGene<sup>®</sup>) study. We constructe ...[more]

PMID: 35649102

Similar Datasets

Project description:BackgroundThe clinical implication of bronchodilator response (BDR) is not fully understood. However, BDR is frequently present in patients with chronic obstructive pulmonary disease (COPD). We identified the differences in clinical features regarding BDR. In addition, we divided BDR into BDR for forced expiratory volume in 1 s (FEV1) and BDR for forced vital capacity (FVC; i.e., BDR-FEV1 and BDR-FVC, respectively) and analyzed clinical significance.MethodsWe used data from the Korea COPD Subgroup Study, a multicenter cohort study of COPD patients recruited from 54 centers in South Korea since April 2012. We analyzed differences in baseline characteristics, 1-year exacerbation rate, and 3-year FEV1 decline between BDR negative and positive patients. Moreover, we analyzed the differences in clinical features between BDR-FEV1 positive and negative patients and between BDR-FVC positive and negative patients.ResultsOf the 2,181 patients enrolled in this study, 366 (16.8%) were BDR positive. BDR positive patients were more likely to be ever-smokers and to have a lower body mass index and higher symptom scores compared to BDR negative patients. Baseline FEV1 and FEV1/FVC were lower in the BDR positive compared to the BDR negative group (1.7 ± 0.6 and 1.6 ± 0.5, respectively, p < 0.01; 50.9 ± 12.1 and 46.5 ± 14.8, respectively, p < 0.01). BDR positive patients were more likely to have been diagnosed with asthma-COPD overlap and to receive inhaled corticosteroids (ICS) than BDR negative patients. BDR-FVC patients were more likely to be smokers, suffer from worse symptoms and have lower lung function than those with no BDR-FVC. BDR had no significant effect on 1-year moderate to severe or severe exacerbation rates or 3-year annual FEV1 decline. Interactive effects of ICS and BDR on the exacerbation rate were not significant in any group.ConclusionsIn this study, BDR positive patients were more likely to be ever-smokers and to have worse symptoms and lung function than BDR negative patients. BDR-FVC was associated with worse symptom control and lung function compared to BDR-FEV1. However, there were no significant differences in exacerbation rate or decline in lung function in any BDR group. In addition, the effects of ICS on exacerbations were not significant in any group.

Project description:BackgroundCough variant asthma (CVA) is characterized by cough as a sole symptom and normal pulmonary function. However, it is unclear whether CVA really common among asthmatic patients with normal forced expiratory volume in 1 second (FEV1). The aim of this study was to evaluate the incidence of cough alone symptom among the subjects with normal FEV1 and to evaluate their differences from ordinary asthmatic subjects.MethodsWe defined normal FEV1 as ≥90% predicted based on the article of Kotti GH. Of the patients with normal FEV1, we chose subjects without wheeze, and the duration of cough was not to ask, since the symptoms often occurred with acute exacerbation and timing of visiting a doctor depended on each patient's perception. Test for airway hyperresponsiveness was not performed in this study. Visual analogue scale (VAS) scores for cough and dyspnea, FEV1, and fractional exhaled nitric oxide (FeNO) responsiveness to inhaled corticosteroid (ICS)/long-acting beta2 agonist (LABA) treatment were compared in patients with normal FEV1 and with low FEV1 <90%. Correlations of changes in symptoms with changes of FEV1, FeNO, peripheral eosinophil count, and serum immunoglobulin E (IgE) at single time point were also examined in each group and in overall patients.ResultsThe participants were 329 physician-diagnosed treatment-naive patients with asthma who were divided into 187 in normal FEV1 and 142 in low FEV1 groups. Cough without dyspnea was present in 16 patients (8.6%) in the normal FEV1 group, suggesting candidates for CVA in this analysis were quite few. Improvement in symptoms after treatment was similar between both groups. But VAS scores of dyspnea were still higher in the low FEV1 group. The degree of improvement in FEV1 after ICS/LABA treatment was less in the normal FEV1 group than in the low FEV1 group, but was still evident. Peripheral eosinophil count, serum IgE, and FeNO values before treatment were lower in the normal FEV1 group. In overall patients, improvements of symptoms after treatment were significantly correlated with FEV1 changes. Improvement of dyspnea was also significantly related to peripheral eosinophil count and change of FeNO, whereas improvement of cough was not related to these T helper 2 (Th2) response markers.ConclusionsCandidates for CVA among the patients with asthma with predicted FEV1 ≥90% were few. Participants with normal FEV1 respond well to ICS/LABA treatment for improvement of symptom. The change of FEV1 after treatment, and the pre-treatment blood eosinophil count, serum IgE, and FeNO were lower in normal FEV1 cases than in low FEV1 cases. These observations suggest asthmatic patients with normal FEV1, including candidates for CVA having just common mild asthma. In overall participants, symptoms of cough and dyspnea were similar, but were not identical in relation to the Th2 background.

Project description:Rationale: The American Thoracic Society (ATS)/European Respiratory Society defines a positive bronchodilator response (BDR) by a composite of BDR in either forced expiratory volume in 1 second (FEV1) and/or forced vital capacity (FVC) greater than or equal to 12% and 200 ml (ATS-BDR). We hypothesized that ATS-BDR components would be differentially associated with important chronic obstructive pulmonary disease (COPD) outcomes. Objectives: To examine whether ATS-BDR components are differentially associated with clinical, functional, and radiographic features in COPD. Methods: We included subjects with COPD enrolled in the COPDGene study. In the main analysis, we excluded subjects with self-reported asthma. We categorized BDR into the following: 1) No-BDR, no BDR in either FEV1 or FVC; 2) FEV1-BDR, BDR in FEV1 but no BDR in FVC; 3) FVC-BDR, BDR in FVC but no BDR in FEV1; and 4) Combined-BDR, BDR in both FEV1 and FVC. We constructed multivariable logistic, linear, zero-inflated negative binomial, and Cox hazards models to examine the association of BDR categories with symptoms, computed tomography findings, change in FEV1 over time, respiratory exacerbations, and mortality. We also created models using the ATS BDR definition (ATS-BDR) as the main independent variable. Results: Of 3,340 COPD subjects included in the analysis, 1,083 (32.43%) had ATS-BDR, 182 (5.45%) had FEV1-BDR, 522 (15.63%) had FVC-BDR, and 379 (11.34%) had Combined-BDR. All BDR categories were associated with FEV1 decline compared with No-BDR. Compared with No-BDR, both ATS-BDR and Combined-BDR were associated with higher functional residual capacity %predicted, greater internal perimeter of 10 mm, and greater 6-minute-walk distance. In contrast to ATS-BDR, Combined-BDR was independently associated with less emphysema (adjusted beta regression coefficient, -1.67; 95% confidence interval [CI], -2.68 to -0.65; P = 0.001), more frequent respiratory exacerbations (incidence rate ratio, 1.25; 95% CI, 1.03-1.50; P = 0.02) and severe exacerbations (incidence rate ratio, 1.34; 95% CI, 1.05-1.71; P = 0.02), and lower mortality (adjusted hazards ratio, 0.76; 95% CI, 0.58-0.99; P = 0.046). Sensitivity analysis that included subjects with self-reported history of asthma showed similar findings. Conclusions: BDR in both FEV1 and FVC indicates a COPD phenotype with asthma-like characteristics, and provides clinically more meaningful information than current definitions of BDR.

Project description:ObjectivesBecause they are potentially modifiable and may coexist, we evaluated the combined occurrence of a reduced forced expiratory volume in 1 second (FEV1) and peripheral artery disease (PAD), including its association with exertional symptoms, physical inactivity, and impaired mobility, in sedentary elders with functional limitations.DesignCross sectional.SettingLifestyle Interventions and Independence in Elder (LIFE) Study.ParticipantsA total of 1307 sedentary community-dwelling persons, mean age 78.9, with functional limitations (Short Physical Performance Battery [SPPB] <10).MeasurementsA reduced FEV1 was defined by a z-score less than -1.64 (<lower limit of normal), whereas PAD was defined by an ankle-brachial index less than 1.00. Exertional dyspnea was defined as moderate to severe (modified Borg index) immediately after a 400-meter walk test (400MWT). Exertional leg symptoms were established by the San Diego Claudication Questionnaire. Physical inactivity was evaluated by percent of accelerometry wear-time with activity less than 100 counts per minute (top quartile established high sedentary time). Mobility was evaluated by the 400MWT (gait speed <0.8 m/s defined as slow) and SPPB (≤ 7 defined moderate-to-severe mobility impairment).ResultsA combined reduced FEV1 and PAD was established in 6.0% (78/1307) of participants. However, among those who had a reduced FEV1, 34.2% (78/228) also had PAD, whereas 20.8% (78/375) of those who had PAD also had a reduced FEV1. The 2 combined conditions were associated with exertional dyspnea (adjusted odds ratio [adjOR] 2.59 [1.20-5.60]) and slow gait speed (adjOR 3.15 [1.72-5.75]) but not with exertional leg symptoms, high sedentary time, and moderate-to-severe mobility impairment.ConclusionsIn sedentary community-dwelling elders with functional limitations, a reduced FEV1 and PAD frequently coexisted and, in combination, were strongly associated with exertional dyspnea and slow gait speed (a frailty indicator that increases the risk of deleterious outcomes).

Dataset Information

Machine Learning Prediction of Progression in Forced Expiratory Volume in 1 Second in the COPDGene® Study.

Background

Methods

Results

Conclusion

Publications

Machine Learning Prediction of Progression in Forced Expiratory Volume in 1 Second in the COPDGene® Study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets