Author Affiliations

1. Pulmonary, Critical Care and Sleep Medicine Section, Yale University, New Haven, Connecticut, United States
2. Center for Precision Pulmonary Medicine, Yale University, New Haven, Connecticut, United States

Address correspondence to:

Jose Gomez, MD
Yale University
300 Cedar Street (S419 TAC)
New Haven, CT 06520-8057
Phone: (203) 785-4163
Email: jose.gomez-villalobos@yale.edu

Abstract

Rationale: Acute exacerbations of chronic obstructive pulmonary disease (AECOPDs) are heterogeneous. Machine learning (ML) has previously been used to dissect some of the heterogeneity in COPD. The widespread adoption of electronic health records (EHRs) has led to the rapid accumulation of large amounts of patient data as part of routine clinical care. However, it is unclear whether the implementation of ML in EHR-derived data has the potential to identify subgroups of AECOPD.

Objectives: To determine whether ML implementation using EHR data from severe AECOPDs requiring hospitalization identifies relevant subgroups.

Methods: This study used 2 retrospective cohorts of patients with AECOPDs (non-COVID-19 and COVID-19) treated at Yale-New Haven Hospital. K-means clustering was used to identify patient subgroups.

Measurements and Main Results: We identified 3 subgroups in the non-COVID cohort (n=1736). Each subgroup had distinct clinical characteristics. The reference subgroup was the largest (n=904), followed by cardio-renal (n=548) and eosinophilic (n=284). The eosinophilic subgroup had milder severity of AECOPD, including a shorter hospital stay (p<0.01). The cardio-renal subgroup had the highest mortality during (5%) and in the year after hospitalization (30%). Validation of the severe AECOPD classifier in the COVID-19 cohort recapitulated the characteristics seen in the non-COVID cohort. AECOPD subgroups in the COVID-19 cohort had different interleukin (IL)-1 beta, IL-2R, and IL-8 levels (false discovery rate ≤ 0.05). These specific leukocyte and cytokine profiles resulted in inflammatory differences between the AECOPD subgroups based on C-reactive protein levels.

Conclusions: Incorporating ML with EHR data allows the identification of specific clinical and biological subgroups for severe AECOPD.

Citation

Citation: Li H, Huston J, Zielonka J, Kay S, Sauler M, Gomez J. Identification of severe acute exacerbations of chronic obstructive pulmonary disease subgroups by machine learning implementation in electronic health records. J COPD F. 2024; 11(6): 611-623. doi: http://doi.org/10.15326/jcopdf.11.6.2024.0556

Keywords

acute exacerbations of COPD, machine learning, electronic health records, clusters

Full Text

Click to read Identification of Severe Acute Exacerbations of Chronic Obstructive Pulmonary Disease Subgroups by Machine Learning Implementation in Electronic Health Records

PDF Download

PDF Version (2896KB)

Author Affiliations

1. Makerere University Lung Institute, Kampala, Uganda
2. Department of Medicine, Makerere University College of Health Sciences, Kampala, Uganda
3. Soroti District Local Government, Soroti, Uganda
4. Respiratory Institute, Cleveland Clinic, Cleveland, Ohio, United States
5. Department of Medicine, Johns Hopkins University School of Medicine, Baltimore, Maryland, United States
6. Faculty of Health, University of Plymouth, Plymouth, United Kingdom
7. Respiratory, University College London, London, United Kingdom
8. Division of Pulmonary, Critical Care and Sleep Medicine, University of Miami, Miami, Florida, United States

Address correspondence to:

Patricia Alupo, MBChB, MMed
Makerere University Lung Institute
Phone: +256701124540
Email: alupopat@gmail.com

Abstract

Background: The neutrophil-to-lymphocyte ratio (NLR) is an inexpensive biomarker that potentially predicts acute exacerbations of chronic obstructive pulmonary disease (AECOPDs). We evaluated the association of baseline NLR and respiratory hospitalization risk within one year among chronic obstructive pulmonary disease (COPD) patients in Uganda, a low- and middle-income country.

Methods: A total of 312 COPD patients were followed for one year. Clinical characteristics and exacerbation rates were collected. Poisson regression with robust variance estimators was used to measure the association between NLR and hospital admissions due to COPD exacerbations. Receiver-operator characteristic (ROC) curves and the area under the curve were used to assess the ability of NLR to predict AECOPDs.

Results: The median (Q 1, Q 3) age was 64 years (53, 71). Females comprised 50.96% (n=159) of the cohort, and 71.2% (n=222) of participants had moderate or severe COPD. A total of 9.9% (n=31) of participants experienced a COPD exacerbation during the period of follow-up. At baseline, the median (Q 1, Q 3) NLR ratio among participants who experienced an exacerbation was 1.46 (0.92, 2.33) compared to 1.03 (0.72,1.42) among those who did not experience one during the follow-up period (p=0.002). Using Youden and Liu’s methods, the optimal NLR cutoff for predicting COPD exacerbation was 1.17. This cutoff resulted in a ROC curve area of 0.64 (95% confidence interval: 0.56, 0.73).

Conclusions: The NLR could be used as a risk predictor, in low- and middle-income countries, for hospital admissions due to COPD exacerbations. A cutoff of 1.17 was an independent predictor of hospitalization due to acute exacerbations of COPD within one year.

Citation

Citation: Alupo P, Katagira W, Mukunya D, et al. The neutrophil-to-lymphocyte ratio as a predictor of acute exacerbations among patients with COPD in Uganda. J COPD F. 2024; 11(2): 187-195. doi: http://doi.org/10.15326/jcopdf.11.2.2023.0443

Keywords

COPD, biomarkers, exacerbations, acute exacerbations of COPD, neutrophil-to-lymphocyte ratio

Full Text

Click to read The Neutrophil-to-Lymphocyte Ratio as a Predictor of Acute Exacerbations Among Patients With COPD in Uganda

PDF Download

PDF Version (625KB)

Author Affiliations

1. Division of Pulmonary Sciences and Critical Care Medicine, Colorado Pulmonary Outcomes Research Group, Aurora, Colorado, United States
2. Division of Health Care Policy and Research, Department of Medicine, University of Colorado Denver, Anschutz Medical Campus, Aurora, Colorado, United States
3. Institute for Health Research, Kaiser Permanente Colorado, Denver, Colorado, United States
4. National Jewish Health, Denver, Colorado, United States
5. Denver Veterans Administration Medical Center, Denver, Colorado, United States
6. Department of Family Medicine, High Plains Research Network, University of Colorado Denver, Anschutz Medical Campus, United States

*Authors contributed equally to the study

Address correspondence to:

R. William Vandivier, MD
Professor of Medicine
Department of Medicine
Division of Pulmonary Sciences and Critical Care Medicine
University of Colorado-Denver
Aurora, CO 80045
Phone: (303)724-6068
Email: Bill.Vandivier@cuanschutz.edu

Abstract

Background: Up to 50% of chronic obstructive pulmonary disease (COPD) patients do not receive recommended care for COPD. To address this issue, we developed Proactive Integrated Care (Proactive iCare), a health care delivery model that couples integrated care with remote monitoring.

Methods: We conducted a prospective, quasi-randomized clinical trial in 511 patients with advanced COPD or a recent COPD exacerbation, to test whether Proactive iCare impacts patient-centered outcomes and health care utilization. Patients were allocated to Proactive iCare (n=352) or Usual Care ( =159) and were examined for changes in quality of life using the St George’s Respiratory Questionnaire (SGRQ), symptoms, guideline-based care, and health care utilization.

Findings: Proactive iCare improved total SGRQ by 7–9 units (p < 0.0001), symptom SGRQ by 9 units (p<0.0001), activity SGRQ by 6–7 units (p<0.001) and impact SGRQ by 7–11 units (p<0.0001) at 3, 6 and 9 months compared with Usual Care. Proactive iCare increased the 6-minute walk distance by 40 m (p<0.001), reduced annual COPD-related urgent office visits by 76 visits per 100 participants (p<0.0001), identified unreported exacerbations, and decreased smoking (p=0.01). Proactive iCare also improved symptoms, the body mass index-airway obstruction-dyspnea-exercise tolerance (BODE) index and oxygen titration (p<0.05). Mortality in the Proactive iCare group (1.1%) was not significantly different than mortality in the Usual Care group (3.8%; p=0.08).

Interpretation: Linking integrated care with remote monitoring improves the lives of people with advanced COPD, findings that may have been made more relevant by the coronavirus 2019 (COVID-19) pandemic.

Citation

Citation: Koff KB, Min S, Diaz DLP, et al. Impact of Proactive Integrated Care on chronic obstructive pulmonary disease. J COPD F. 2021; 8(1): 100-116. doi: http://doi.org/10.15326/jcopdf.8.1.2020.0139

Keywords

primary care, disease management, patient education, acute exacerbations of COPD, telemedicine, self-care

Full Text

Click to read Impact of Proactive Integrated Care on Chronic Obstructive Pulmonary Disease

PDF Download

PDF Version (6480KB)

Author Affiliations

1. Department of Pulmonary and Critical Care, Wake Forest School of Medicine, Wake Forest Baptist Medical Center, Winston-Salem, North Carolina
2. Department of Internal Medicine, Wake Forest School of Medicine, Wake Forest Baptist Medical Center, Winston-Salem, North Carolina

Address correspondence to:

Chee Hong Loh, MD
Email: seanchloh@gmail.com
Phone: (336)716-4328

Abstract

Purpose: Objective documentation of airflow obstruction is often lacking inhospitalized patients treated for acute exacerbation of chronic obstructive pulmonary disease (AECOPD). The utility of spirometry performed in hospitalized patients to identify airflow obstruction, and thus a diagnosis of COPD, is unclear. Our aim was to compare inpatient spirometry, performed during an AECOPD, with outpatient spirometry.

Methods: A retrospective analysis of data from patients enrolled in an AECOPD care plan was performed. As part of the plan, patients underwent inpatient spirometry to establish a COPD diagnosis and outpatient clinic spirometry within 4 weeks of hospital discharge to confirm it. Data analyzed included forced expiratory volume in 1 second (FEV₁), forced vital capacity (FVC), slow vital capacity (SVC) and FEV₁/ vital capacity (VC). Obstruction was defined by FEV₁/VC<0.70.

Results: A total of 159 patients (mean age 63.2 +/- 10.5 years) had corresponding in- and outpatient spirometry. The median days between inpatient and outpatient spirometry was 12 (interquartile range [IQR] 9-16). Inpatient spirometry had a sensitivity of 94%, specificity of 24%, positive predictive value of 83% and negative predictive value of 53% for predicting outpatient obstruction. The area under curve for using inpatient spirometry was 0.82. The mean difference between inpatient and outpatient FEV₁ was 0.44 +/- 0.03 liters or 17.3 +/- 1.13 % predicted (p<0.0001) for FEV₁.

Conclusions: Inpatient spirometry accurately predicts outpatient airflow obstruction, thus providing an opportunity to identify patients admitted with suspected AECOPD who have no prior spirometric documentation.

Citation

Citation: Loh CH, Genese FA, Kannan KK, Lovings TM, Peters SP, Ohar JA. Spirometry in hospitalized patients with acute exacerbation of COPD accurately predicts post discharge airflow obstruction. J COPD F. 2018; 5(2): 124-133. doi: http://doi.org/10.15326/jcopdf.5.2.2017.0169

Keywords

COPD, chronic obstructive pulmonary disease, AECOPD, inpatient spirometry, COPD readmissions, acute exacerbations of COPD

Full Text

Click to read Spirometry in Hospitalized Patients with Acute Exacerbation of COPD Accurately Predicts Post Discharge Airflow Obstruction

PDF Download

PDF Version (2079KB)