David Carrell, PhD, is an assistant investigator who develops and applies technology for extracting rich information from unstructured clinical text, such as physician progress notes. This work uses state-of-the-art clinical natural language processing (NLP) technologies in single- and multi-site settings.
An example of this work is an NLP system to identify women who have been diagnosed with recurrent breast cancer. Despite being a common and consequential clinical diagnosis, recurrent breast cancer cannot be tracked reliably using standard medical codes found in a person’s chart. Supported by a grant from the National Cancer Institute, he and his colleagues used information from clinician progress notes, radiology reports, and pathology reports to classify women by breast cancer recurrence.
Working with teams of researchers inside and outside Kaiser Permanente Washington Health Research Institute, Dr. Carrell has applied similar precision phenotyping methods to identify evidence of carotid artery stenosis, colon polyps, problem use of prescription opioids, and colonoscopy quality.
Dr. Carrell’s current research projects are applying NLP and machine learning methods to improve medication safety surveillance (through the Food and Drug Administration Sentinel Initiative) and to evaluate the impact on drug use disorder diagnosis and treatment of Kaiser Permanente Washington patients screened for unhealthy cannabis and other drug use. His ongoing work also includes development and application of automated algorithms based on electronic health record data to identify patients with particular health conditions (called “patient phenotypes”) for use in genetic and epidemiological research.
Surveillance methods for adverse events associated with medication exposure, including problem use of prescription opioids
Methods for using structured and unstructured electronic health record data to identify patients with (or without) specific clinical conditions or phenotypes for large scale epidemiological and genomic studies
Identifying recurrent breast cancer using EHR text; Colonoscopy quality metrics
Recurrent breast cancer; Colonoscopy quality; Extracting information from clinical text; Automated de-identification of clinical text; Methods for applying NLP methods in multi-site research
Prevention and treatment
Almoguera B, Vazquez L, Mentch F, Connolly J, Pacheco JA, Sundaresan AS, Peissig PL, Linneman JG, McCarty CA, Crosslin D, Carrell DS, Lingren T, Namjou-Khales B, Harley JB, Larson E, Jarvik GP, Brilliant M, Williams MS, Kullo IJ, Hysinger EB, Sleiman PM, Hakonarson H. Genome-wide association study identifies four novel loci associated with asthma in European and African American populations. Am J Respir Crit Care Med 2016. [Epub 2016 Sept 9].
Farjah F, Halgrim S, Buist DS, Gould MK, Zeliadt SB, Loggers ET, Carrell DS. An automated method for identifying individuals with a lung nodule can be feasibly implemented across health systems. EGEMS (Wash DC). 2016 Aug 26;4(1):1254. doi: 10.13063/2327-9214.1254. eCollection 2016. PubMed
van 't Hof FN, Ruigrok YM, Lee CH, Ripke S, Anderson G, de Andrade M, Baas AF, Blankensteijn JD, Böttinger EP, Bown MJ, Broderick J, Bijlenga P, Carrell DS, Crawford DC, Crosslin DR, Ebeling C, Eriksson JG, Fornage M, Foroud T, von Und Zu Fraunberg M, Friedrich CM, Gaál EI, Gottesman O, Guo DC, Harrison SC, Hernesniemi J, Hofman A, Inoue I, Jääskeläinen JE, Jones GT, Kiemeney LA, Kivisaari R, Ko N, Koskinen S, Kubo M, Kullo IJ, Kuivaniemi H, Kurki MI, Laakso A, Lai D, Leal SM, Lehto H, LeMaire SA, Low SK, Malinowski J, McCarty CA, Milewicz DM, Mosley TH, Nakamura Y, Nakaoka H, Niemelä M, Pacheco J, Peissig PL, Pera J, Rasmussen-Torvik L, Ritchie MD, Rivadeneira F, van Rij AM, Santos-Cortez RL, Saratzis A, Slowik A, Takahashi A, Tromp G, Uitterlinden AG, Verma SS, Vermeulen SH, Wang GT; Aneurysm Consortium; Vascular Research Consortium of New Zealand, Han B, Rinkel GJ, de Bakker PI. Shared genetic risk factors of intracranial, abdominal, and thoracic aneurysms. J Am Heart Assoc. 2016 Jul 14;5(7). pii: e002603. doi: 10.1161/JAHA.115.002603. PubMed
Carrell DS, Cronkite DJ, Malin BA, Aberdeen JS, Hirschman L. Is the juice worth the squeeze? costs and benefits of multiple human annotators for clinical text de-identification. Methods Inf Med. 2016 Aug 5;55(4):356-64. doi: 10.3414/ME15-01-0122. Epub 2016 Jul 13. PubMed
Kirby JC, Speltz P, Rasmussen LV, Basford M, Gottesman O, Peissig PL, Pacheco JA, Tromp G, Pathak J, Carrell DS, Ellis SB, Lingren T, Thompson WK, Savova G, Haines J, Roden DM, Harris PA, Denny JC. PheKB: a catalog and workflow for creating electronic phenotype algorithms for transportability. J Am Med Inform Assoc. 2016 Mar 28. pii: ocv202. doi: 10.1093/jamia/ocv202. [Epub ahead of print]. PubMed
Li M, Carrell D, Aberdeen J, Hirschman L, Kirby J, Li B, Vorobeychik Y, Malin BA. Optimizing annotation resources for natural language de-identification via a game theoretic framework. J Biomed Inform. 2016 Jun;61:97-109. doi: 10.1016/j.jbi.2016.03.019. Epub 2016 Mar 25. PubMed
Simonti CN, Vernot B, Bastarache L, Bottinger E, Carrell DS, Chisholm RL, Crosslin DR, Hebbring SJ, Jarvik GP, Kullo IJ, Li R, Pathak J, Ritchie MD, Roden DM, Verma SS, Tromp G, Prato JD, Bush WS, Akey JM, Denny JC, Capra JA. The phenotypic legacy of admixture between modern humans and Neandertals. Science. 2016 Feb 12;351(6274):737-41. doi: 10.1126/science.aad2149. PubMed
A Kaiser Permanente-led BCSC study is among the largest ever to evaluate adding MRI surveillance for breast cancer survivors.
Dr. Paula Lozano explains how a Learning Health System project finds Kaiser Permanente Washington members who could benefit most from preventive services.
In Annals editorial Drs. Sascha Dublin and Michael Von Korff advocate more caution in prescribing these medications.