%0 Journal Article
%T Chronic obstructive pulmonary disease phenotypes using cluster analysis of electronic medical records
%A Gary Iwamoto
%A Oleg Ursu
%A Pope L Moseley
%A Rodrigo Vazquez Guillamet
%A Tudor Oprea
%J Health Informatics Journal
%@ 1741-2811
%D 2018
%R 10.1177/1460458216675661
%X 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 >40ˋyears 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: 46ˋpercent were >65ˋyears and 52ˋpercent were males. The median Charlson score was 2 (interquartile range: 1每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每chronic obstructive pulmonary disease, coronary artery disease每chronic obstructive pulmonary disease, cerebrovascular disease每chronic obstructive pulmonary disease, malignancy每chronic obstructive pulmonary disease, advanced malignancy每chronic obstructive pulmonary disease, diabetes mellitus每chronic kidney disease每chronic obstructive pulmonary disease, young age每few comorbidities每high readmission rates每chronic obstructive pulmonary disease, atopy每chronic obstructive pulmonary disease, and advanced disease每chronic obstructive pulmonary disease. These clusters will need to be validated prospectively
%K asthma
%K comorbidity
%K chronic obstructive pulmonary disease
%K epidemiology
%K factor analysis
%K phenotype
%U https://journals.sagepub.com/doi/full/10.1177/1460458216675661