Comparison of clinico-physiologic and CT imaging risk factors for COPD exacerbation

Automatically Explaining Machine Learning Predictions on Severe Chronic Obstructive Pulmonary Disease Exacerbations: Retrospective Cohort Study

Background

Chronic obstructive pulmonary disease (COPD) is a major cause of death and places a heavy burden on health care. To optimize the allocation of precious preventive care management resources and improve the outcomes for high-risk patients with COPD, we recently built the most accurate model to date to predict severe COPD exacerbations, which need inpatient stays or emergency department visits, in the following 12 months. Our model is a machine learning model. As is the case with most machine learning models, our model does not explain its predictions, forming a barrier for clinical use. Previously, we designed a method to automatically provide rule-type explanations for machine learning predictions and suggest tailored interventions with no loss of model performance. This method has been tested before for asthma outcome prediction but not for COPD outcome prediction.

Objective

This study aims to assess the generalizability of our automatic explanation method for predicting severe COPD exacerbations.

Methods

The patient cohort included all patients with COPD who visited the University of Washington Medicine facilities between 2011 and 2019. In a secondary analysis of 43,576 data instances, we used our formerly developed automatic explanation method to automatically explain our model’s predictions and suggest tailored interventions.

Results

Our method explained the predictions for 97.1% (100/103) of the patients with COPD whom our model correctly predicted to have severe COPD exacerbations in the following 12 months and the predictions for 73.6% (134/182) of the patients with COPD who had ≥1 severe COPD exacerbation in the following 12 months.

Conclusions

Our automatic explanation method worked well for predicting severe COPD exacerbations. After further improving our method, we hope to use it to facilitate future clinical use of our model.

International Registered Report Identifier (IRRID)

RR2-10.2196/13783

Developing a Machine Learning Model to Predict Severe Chronic Obstructive Pulmonary Disease Exacerbations: Retrospective Cohort Study

Background

Chronic obstructive pulmonary disease (COPD) poses a large burden on health care. Severe COPD exacerbations require emergency department visits or inpatient stays, often cause an irreversible decline in lung function and health status, and account for 90.3% of the total medical cost related to COPD. Many severe COPD exacerbations are deemed preventable with appropriate outpatient care. Current models for predicting severe COPD exacerbations lack accuracy, making it difficult to effectively target patients at high risk for preventive care management to reduce severe COPD exacerbations and improve outcomes.

Objective

The aim of this study is to develop a more accurate model to predict severe COPD exacerbations.

Methods

We examined all patients with COPD who visited the University of Washington Medicine facilities between 2011 and 2019 and identified 278 candidate features. By performing secondary analysis on 43,576 University of Washington Medicine data instances from 2011 to 2019, we created a machine learning model to predict severe COPD exacerbations in the next year for patients with COPD.

Results

The final model had an area under the receiver operating characteristic curve of 0.866. When using the top 9.99% (752/7529) of the patients with the largest predicted risk to set the cutoff threshold for binary classification, the model gained an accuracy of 90.33% (6801/7529), a sensitivity of 56.6% (103/182), and a specificity of 91.17% (6698/7347).

Conclusions

Our model provided a more accurate prediction of severe COPD exacerbations in the next year compared with prior published models. After further improvement of its performance measures (eg, by adding features extracted from clinical notes), our model could be used in a decision support tool to guide the identification of patients with COPD and at high risk for care management to improve outcomes.

International Registered Report Identifier (IRRID)

RR2-10.2196/13783

Deep radiomics-based survival prediction in patients with chronic obstructive pulmonary disease

Heterogeneous clinical manifestations and progression of chronic obstructive pulmonary disease (COPD) affect patient health risk assessment, stratification, and management. Pulmonary function tests are used to diagnose and classify the severity of COPD, but they cannot fully represent the type or range of pathophysiologic abnormalities of the disease. To evaluate whether deep radiomics from chest computed tomography (CT) images can predict mortality in patients with COPD, we designed a convolutional neural network (CNN) model for extracting representative features from CT images and then performed random survival forest to predict survival in COPD patients. We trained CNN-based binary classifier based on six-minute walk distance results (> 440 m or not) and extracted high-throughput image features (i.e., deep radiomics) directly from the last fully connected layer of it. The various sizes of fully connected layers and combinations of deep features were experimented using a discovery cohort with 344 patients from the Korean Obstructive Lung Disease cohort and an external validation cohort with 102 patients from Penang General Hospital in Malaysia. In the integrative analysis of discovery and external validation cohorts, with combining 256 deep features from the coronal slice of the vertebral body and two sagittal slices of the left/right lung, deep radiomics for survival prediction achieved concordance indices of 0.8008 (95% CI, 0.7642–0.8373) and 0.7156 (95% CI, 0.7024–0.7288), respectively. Deep radiomics from CT images could be used to predict mortality in COPD patients.

Using Computational Methods to Improve Integrated Disease Management for Asthma and Chronic Obstructive Pulmonary Disease: Protocol for a Secondary Analysis

Background

Asthma and chronic obstructive pulmonary disease (COPD) impose a heavy burden on health care. Approximately one-fourth of patients with asthma and patients with COPD are prone to exacerbations, which can be greatly reduced by preventive care via integrated disease management that has a limited service capacity. To do this well, a predictive model for proneness to exacerbation is required, but no such model exists. It would be suboptimal to build such models using the current model building approach for asthma and COPD, which has 2 gaps due to rarely factoring in temporal features showing early health changes and general directions. First, existing models for other asthma and COPD outcomes rarely use more advanced temporal features, such as the slope of the number of days to albuterol refill, and are inaccurate. Second, existing models seldom show the reason a patient is deemed high risk and the potential interventions to reduce the risk, making already occupied clinicians expend more time on chart review and overlook suitable interventions. Regular automatic explanation methods cannot deal with temporal data and address this issue well.

Objective

To enable more patients with asthma and patients with COPD to obtain suitable and timely care to avoid exacerbations, we aim to implement comprehensible computational methods to accurately predict proneness to exacerbation and recommend customized interventions.

Methods

We will use temporal features to accurately predict proneness to exacerbation, automatically find modifiable temporal risk factors for every high-risk patient, and assess the impact of actionable warnings on clinicians’ decisions to use integrated disease management to prevent proneness to exacerbation.

Results

We have obtained most of the clinical and administrative data of patients with asthma from 3 prominent American health care systems. We are retrieving other clinical and administrative data, mostly of patients with COPD, needed for the study. We intend to complete the study in 6 years.

Conclusions

Our results will help make asthma and COPD care more proactive, effective, and efficient, improving outcomes and saving resources.

International Registered Report Identifier (IRRID)

PRR1-10.2196/27065

Relationship between current smoking, visual CT findings and emphysema index in cigarette smokers

PURPOSE

To evaluate whether visual CT findings could account for the effect of current smoking.

METHODS

500 CT scans were visually evaluated within each lobe. A multivariate model for emphysema index was constructed containing previously described confounders in addition to the visual components associated with smoking status.

RESULTS

Current smokers displayed 23% less visual emphysema, 19% more airway wall thickening, and 188% more centrilogular nodule than former smokers (all p < 0.001). The effect of current smoking on the emphysema index decreased after adjustment with confounders and visual parameters.

CONCLUSIONS

Visual CT findings could partially account for the effect of current smoking.

A novel CT-emphysema index/FEV1 approach of phenotyping COPD to predict mortality

Background

COPD-associated mortality was examined using a novel approach of phenotyping COPD based on computed tomography (CT)-emphysema index from quantitative CT (QCT) and post-bronchodilator (BD) forced expiratory volume in 1 second (FEV₁) in a local Malaysian cohort.

Patients and methods

Prospectively collected data of 112 eligible COPD subjects (mean age, 67 years; male, 93%; mean post-BD FEV₁, 45.7%) was available for mortality analysis. Median follow-up time was 1,000 days (range, 60–1,400). QCT and clinicodemographic data were collected at study entry. Based on CT-emphysema index and post-BD FEV₁% predicted, subjects were categorized into “emphysema-dominant,” “airway-dominant,” “mild mixed airway-emphysema,” and “severe mixed airway-emphysema” diseases.

Results

Sixteen patients (14.2%) died of COPD-associated causes. There were 29 (25.9%) “mild mixed,” 23 (20.5%) “airway-dominant,” 15 (13.4%) “emphysema-dominant,” and 45 (40.2%) “severe mixed” cases. “Mild mixed” disease was proportionately more in Global Initiative for Chronic Obstructive Lung Disease (GOLD) Group A, while “severe mixed” disease was proportionately more in GOLD Groups B and D. Kaplan–Meier survival estimates showed increased mortality risk with “severe mixed” disease (log rank test, p=0.03) but not with GOLD groups (p=0.08). Univariate Cox proportionate hazard analysis showed that age, body mass index, long-term oxygen therapy, FEV₁, forced volume capacity, COPD Assessment Test score, modified Medical Research Council score, St Georges’ Respiratory Questionnaire score, CT-emphysema index, and “severe mixed” disease (vs “mild mixed” disease) were associated with mortality. Multivariate Cox analysis showed that age, body mass index, and COPD Assessment Test score remain independently associated with mortality.

Conclusion

“Severe mixed airway-emphysema” disease may predict COPD-associated mortality. Age, body mass index, and COPD Assessment Test score remain as key mortality risk factors in our cohort.

Clinical and pulmonary functions profiling of patients with chronic obstructive pulmonary disease experiencing frequent acute exacerbations

Purpose:

The present study aimed at clinical and pulmonary functions profiling of patients with chronic obstructive pulmonary disease (COPD) to anticipate future exacerbations.

Methods:

The study included 80 COPD patients; 40 patients had ≥2 acute exacerbations during preceding 1 year (frequent exacerbation [FECOPD] group) and 40 patients had <2 acute exacerbations during preceding 1 year (infrequent exacerbation [I-FECOPD] group). Clinical profile, sputum microbiology, blood gas analysis, spirometric indices, and diffusion capacity (transfer test) variables were assessed. Groups’ comparison was performed using an independent t-test for numeric scale parameters and Chi-square test for nominal parameters. Pearson's and Spearman's correlation coefficients were derived for numeric scale parameters and numeric nominal parameters, respectively. Multinomial logistic regression analysis was done using SPSS software.

Results:

FECOPD group contained younger patients than in I-FECOPD group although the difference was not statistically significant. There was no significant difference between two groups regarding smoking pack-years and duration of illness. FECOPD group had significantly more expectoration score and Modified Medical Research Council dyspnea scores. Cough score and wheeze score did not differ significantly between two groups. More patients in FECOPD group (12/40 vs. 4/40) had lower airway bacterial colonization. Arterial blood gas parameters were more deranged in FECOPD group. Spirometric indices (forced expiratory volume during 1^st s) as well as transfer test (both diffusing capacity for carbon monoxide and transfer coefficient of the lung values) were significantly reduced in FECOPD group.

Conclusions:

The patients in FECOPD group had clinical, spirometric, and transfer test profiling suggestive of a severe COPD phenotype, the recognition will help in predicting future exacerbations and a better management.

CT densitometry in emphysema: a systematic review of its clinical utility

BACKGROUND

The aim of the study was to assess the relationship between computed tomography (CT) densitometry and routine clinical markers in patients with chronic obstructive pulmonary disease (COPD) and alpha-1 anti-trypsin deficiency (AATD).

METHODS

Multiple databases were searched using a combination of pertinent terms and those articles relating quantitatively measured CT densitometry to clinical outcomes. Studies that used visual scoring only were excluded, as were those measured in expiration only. A thorough review of abstracts and full manuscripts was conducted by 2 reviewers; data extraction and assessment of bias was conducted by 1 reviewer and the 4 reviewers independently assessed for quality. Pooled correlation coefficients were calculated, and heterogeneity was explored.

RESULTS

A total of 112 studies were identified, 82 being suitable for meta-analysis. The most commonly used density threshold was -950 HU, and a significant association between CT density and all included clinical parameters was demonstrated. There was marked heterogeneity between studies secondary to large variety of disease severity within commonly included cohorts and differences in CT acquisition parameters.

CONCLUSION

CT density shows a good relationship to clinically relevant parameters; however, study heterogeneity and lack of longitudinal data mean that it is difficult to compare studies or derive a minimal clinically important difference. We recommend that international consensus is reached to standardize CT conduct and analysis in future COPD and AATD studies.

Efficacy and Safety of Roflumilast in Korean Patients with COPD

PURPOSE

Roflumilast is the only oral phosphodiesterase 4 inhibitor approved to treat chronic obstructive pulmonary disease (COPD) patients [post-bronchodilator forced expiratory volume in 1 second (FEV₁) <50% predicted] with chronic bronchitis and a history of frequent exacerbations. This study evaluated the efficacy and safety of roflumilast in Korean patients with COPD and compared the efficacy based on the severity of airflow limitation.

MATERIALS AND METHODS

A post-hoc subgroup analysis was performed in Korean COPD patients participating in JADE, a 12-week, double-blinded, placebo-controlled, parallel-group, phase III trial in Asia. The primary efficacy endpoint was the mean [least-squares mean adjusted for covariates (LSMean)] change in post-bronchodilator FEV₁ from baseline to each post-randomization visit. Safety endpoints included adverse events (AEs) and changes in laboratory values, vital signs, and electrocardiograms.

RESULTS

A total of 260 Korean COPD patients were recruited, of which 207 were randomized to roflumilast (n=102) or placebo (n=105) treatment. After 12 weeks, LSMean post-bronchodilator FEV₁ increased by 43 mL for patients receiving roflumilast and decreased by 60 mL for those taking placebo. Adverse events were more common in the roflumilast group than in the placebo group; however, the types and frequency of AEs were comparable to those reported in previous studies.

CONCLUSION

Roflumilast significantly improved lung function with a tolerable safety profile in Korean COPD patients irrespective of the severity of airflow limitation.

Study Design and Outcomes of Korean Obstructive Lung Disease (KOLD) Cohort Study

Background

The Korean Obstructive Lung Disease (KOLD) Cohort Study is a prospective longitudinal study of patients with chronic obstructive pulmonary disease (COPD), asthma, or other unclassified obstructive lung diseases. It was designed to develop new classification models and biomarkers that predict clinically relevant outcomes for patients with obstructive lung diseases.

Methods

Patients over 18 years old who have chronic respiratory symptoms and airflow limitations or bronchial hyper-responsiveness were enrolled at 17 centers in South Korea. After a baseline visit, the subjects were followed up every 3 months for various assessments.

Results

From June 2005 to October 2013, a total of 477 subjects (433 [91%] males; 381 [80%] diagnosed with COPD) were enrolled. Analyses of the KOLD Cohort Study identified distinct phenotypes in patients with COPD, and predictors of therapeutic responses and exacerbations as well as the factors related to pulmonary hypertension in COPD. In addition, several genotypes were associated with radiological phenotypes and therapeutic responses among Korean COPD patients.

Conclusion

The KOLD Cohort Study is one of the leading long-term prospective longitudinal studies investigating heterogeneity of the COPD and is expected to provide new insights for pathogenesis and the long-term progression of COPD.

Comorbidities of chronic obstructive pulmonary disease in Koreans: a population-based study

Chronic obstructive pulmonary disease (COPD) includes pulmonary components with increased comorbidity rates, as well as being a systemic disease. Comorbidities may frequently occur in COPD patients over 40 yr old. We report the comorbidities of patients with COPD, diagnosed by spirometry, in a population-based epidemiologic survey in Korea. Data were derived from the fourth Korean Health and Nutrition Examination Survey in 2008, a stratified multistage clustered probability design survey of a sample representing the entire population of Korea. Results of spirometry and various health-related questionnaires were analyzed in 2,177 subjects aged ≥ 40 yr. The prevalence of COPD (FEV(1)/FVC < 0.7) in subjects ≥ 40 yr of age was 14.1%. Multivariate analysis showed that underweight (odds ratio [OR] 3.07, 95% confidence interval [CI] 1.05-8.98), coronary heart disease (OR, 0.43; 95% CI, 0.20-0.93) and dyslipidemia (OR, 0.61; 95% CI, 0.45-0.82) were significantly associated with COPD, whereas allergic rhinitis, anemia, arthritis, chronic renal failure, depression, diabetes mellitus, hypertension, gastrointestinal ulcer, and osteoporosis were not. Underweight might be more prevalent but coronary heart disease and dyslipidemia are less prevalent in Koreans with than without COPD in population setting.