Chronic obstructive pulmonary disease phenotypes using cluster analysis of electronic medical records
Open accessAbstract
Chronic obstructive pulmonary disease is a heterogeneous disease. In this retrospective study, we hypothesize that it is possible to identify clinically relevant phenotypes by applying clustering methods to electronic medical records. We included all the patients >40 years with a diagnosis of chronic obstructive pulmonary disease admitted to the University of New Mexico Hospital between 1 January 2011 and 1 May 2014. We collected admissions, demographics, comorbidities, severity markers and treatments. A total of 3144 patients met the inclusion criteria: 46 percent were >65 years and 52 percent were males. The median Charlson score was 2 (interquartile range: 1–4) and the most frequent comorbidities were depression (36%), congestive heart failure (25%), obesity (19%), cancer (19%) and mild liver disease (18%). Using the sphere exclusion method, nine clusters were obtained: depression–chronic obstructive pulmonary disease, coronary artery disease–chronic obstructive pulmonary disease, cerebrovascular disease–chronic obstructive pulmonary disease, malignancy–chronic obstructive pulmonary disease, advanced malignancy–chronic obstructive pulmonary disease, diabetes mellitus–chronic kidney disease–chronic obstructive pulmonary disease, young age–few comorbidities–high readmission rates–chronic obstructive pulmonary disease, atopy–chronic obstructive pulmonary disease, and advanced disease–chronic obstructive pulmonary disease. These clusters will need to be validated prospectively.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
COPD cluster 9 has frequent readmissions, severe disease, and a high number of anticholinergic prescriptions.
“whereas cluster 9 has frequent readmissions, severe disease and high number of anticholinergic prescriptions.”
From QSAR without borders (2020) · cites this paper as [283]
COPD cluster 4, comprising young patients with few comorbidities, has the highest number of prescriptions for bronchodilators.
“Cluster 4 (young patients, few comorbidities) has the highest number of prescriptions for bronchodilators;”
From QSAR without borders (2020) · cites this paper as [283]
Two COPD clusters (2 and 5) are associated with malignancy, with cluster 2 having few readmissions and cluster 5 having signs of advanced COPD and frequent readmissions.
“two clusters (2 and 5) are associated with malignancy, although the first one has few readmissions whereas the second one has signs of advanced COPD and frequent readmissions.”
From QSAR without borders (2020) · cites this paper as [283]
The largest COPD cluster is characterized by a large proportion of patients over age 65 and depression.
“The largest cluster is characterized by a large proportion of patients over age 65 and depression;”
From QSAR without borders (2020) · cites this paper as [283]
For the COPD dataset, the optimal balance between the number of clusters and clustering overlap was found at a similarity threshold of 0.62.
“For this dataset, the optimal balance between the number of clusters and clustering overlap was found at similarity threshold 0.62.”
From QSAR without borders (2020) · cites this paper as [283]
After leaving 189 patients (6%) as outliers, nine COPD clusters (phenotypes) were identified with the following patient counts: 1 Depression-COPD (1748); 2 Malignancy-COPD (312); 3 Coronary artery disease-COPD (291); 4 Young age-low comorbidity-high readmission-COPD (152); 5 Advanced malignancy-COPD (144); 6 Cerebrovascular disease-COPD (120); 7 Atopy-COPD (81); 8 Diabetes mellitus - Chronic Kidn
“After leaving 189 patients (6%) as outliers, the following nine COPD clusters (phenotypes) were identified, with the number of patients given in brackets: 1: Depression–COPD (1748); 2: Malignancy–COPD (312); 3: Coronary artery disease–COPD (291); 4: Young age–low comorbidity–high readmission–COPD (152); 5: Advanced malignancy–COPD (144);”
From QSAR without borders (2020) · cites this paper as [283]
COPD cluster 3 is associated with heart disease in patients over age 65.
“Cluster 3 is associated with heart disease (patients over age 65),”
From QSAR without borders (2020) · cites this paper as [283]
COPD cluster 8 is associated with chronic kidney disease and type 2 diabetes in patients aged 40-65.
“cluster 8 is associated with chronic kidney disease (CKD) and type 2 diabetes in patients aged 40-65,”
From QSAR without borders (2020) · cites this paper as [283]
The analysis revealed five previously unreported COPD phenotypes: two malignancy-COPD clusters (2 and 5), the COPD-CKD-diabetes cluster (8), the advanced disease cluster (9), and the high readmission phenotype (4).
“Our analysis revealed five previously unreported COPD phenotypes: two malignancy-COPD clusters (2 and 5), the COPD – CKD – diabetes cluster (8), the “advanced disease” cluster (9) and the high readmission phenotype (4).”
From QSAR without borders (2020) · cites this paper as [283]
COPD cluster 6 is associated with predominantly cerebrovascular disease and younger patients under age 65.
“whereas cluster 6 is associated with predominantly cerebrovascular disease and younger (under 65) patients.”
From QSAR without borders (2020) · cites this paper as [283]
COPD cluster 7 is comprised of patients below age 65 but with asthma/atopy and higher numbers of readmissions.
“cluster 7 is also comprised of patients below age 65, but with asthma/atopy and higher numbers of readmissions;”
From QSAR without borders (2020) · cites this paper as [283]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Adherence to inhaled therapy, mortality and hospital admission in COPD
Vestbo, J., Anderson, J. A., Calverley, P. M. A., Celli, B., Ferguson, G. T., Jenkins, C., Knobil, K., Willits, L. R., Yates, J. C., & Jones, P. W. (2009) · Thorax · doi:10.1136/thx.2009.113662 · Cited by 516 · see citing works
Cully, J. A., Graham, D. P., Stanley, M. A., Ferguson, C. J., Sharafkhaneh, A., Souchek, J., & Kunik, M. E. (2006) · Psychosomatics · doi:10.1176/appi.psy.47.4.312 · Cited by 254 · see citing works
The effects of depressed mood on smoking cessation: Mediation by postcessation self-efficacy.
Cinciripini, P. M., Wetter, D. W., Fouladi, R. T., Blalock, J. A., Carter, B. L., Cinciripini, L. G., & Baile, W. F. (2003) · Journal of Consulting and Clinical Psychology · doi:10.1037/0022-006x.71.2.292 · Cited by 181 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Muratov, E. N., Bajorath, J., Sheridan, R. P., Tetko, I. V., Filimonov, D., Poroikov, V., Oprea, T. I., Baskin, I. I., Varnek, A., Roitberg, A., et al. (2020) · Chemical Society Reviews · doi:10.1039/d0cs00098a · Cited by 913 · see citing works
Self-citation
- Authors
- Vazquez Guillamet, R., Ursu, O., Iwamoto, G., Moseley, P. L., & Oprea, T.
- Affiliations
- University of New Mexico School of Medicine, USA
- University of New Mexico (US)
- Venue
- Health Informatics Journal
- Publisher
- SAGE Publications
- Published
- 2016-11-17
- Volume
- 24
- Issue
- 4
- Pages
- 394-409
- ISSN
- 1355-4743 (ISSN-L)
- 1460-4582
- 1741-2811
- OpenAlex
- W2550642549
- Cited by
- 30
- References
- 3
- Citations by year
- 2026: 2 · 2025: 3 · 2023: 2 · 2022: 3 · 2021: 9 · 2020: 6 · 2019: 4 · 2018: 1
- FWCI
- 1.49
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Health Informatics Journal (publishedVersion)
- PubMed (publishedVersion)
- Funders
- School of Medicine, University of New Mexico
- Topics
- Health Sciences › Medicine › Pulmonary and Respiratory Medicine › Chronic Obstructive Pulmonary Disease (COPD) Research
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Health Sciences › Medicine › Epidemiology › Chronic Disease Management Strategies
- Keywords
- chronic obstructive pulmonary disease, disease phenotypes, patient clustering, electronic health records, comorbidities, depression, congestive heart failure, cancer, diabetes mellitus, chronic kidney disease, atopy, hospital readmission, disease severity
- MeSH terms
- Aged, Female, Humans, Male, Middle Aged, Phenotype, Retrospective Studies, Risk Factors, Models, Statistical, Comorbidity, Pulmonary Disease, Chronic Obstructive, Electronic Health Records
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
