Scalable Identification of Clinically Relevant Chronic Obstructive Pulmonary Disease Documents in Large-Scale Electronic Health Record Datasets With a Lightweight Natural Language Processing Model: Retrospective Cohort Study

Mohammed Al-Garadi   ¹ , PhD ;   Sharon E Davis   ¹ , PhD ;   Michael E Matheny   ^{1, 2, 3, 4} , MD, MS, MPH ;   Dax Westerman   ¹ , MS ;   Adrienne K Conger   ⁵ , MD ;   Bradley W Richmond   ^{4, 5} , MD, PhD ;   Thomas A Lasko   ^{1, 6} , MD, PhD ;   Iben M Ricket   ⁷ , MPH, PhD ;   Laura M Paulin   ⁸ , MD, MHS ;   Jeremiah R Brown   ^{7, 9} , MS, PhD ;   Ruth M Reeves   ^{1, 4} , PhD

¹ Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN, United States

² Department of Medicine, Vanderbilt University Medical Center, Nashville, TN, United States

³ Department of Biostatistics, Vanderbilt University Medical Center, Nashville, TN, United States

⁴ Tennessee Valley Healthcare System, Department of Veterans Affairs, Nashville, TN, United States

⁵ Division of Allergy, Pulmonology, and Critical Care Medicine, Vanderbilt University Medical Center, Nashville, TN, United States

⁶ Department of Computer Science, Vanderbilt University, Nashville, TN, United States

⁷ Department of Epidemiology, Dartmouth Geisel School of Medicine, Lebanon, NH, United States

⁸ Department of Pulmonology, Dartmouth Hitchcock Medical Center, Lebanon, NH, United States

⁹ Center for Implementation Science, Dartmouth Geisel School of Medicine, Lebanon, NH, United States