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
Bann MA, Carrell DS, Gruber S, Shinde M, Ball R, Nelson JC, Floyd JS. Identification and validation of anaphylaxis using electronic health data in a population-based setting. Epidemiology. 2021 Feb 2. doi: 10.1097/EDE.0000000000001330. [Epub ahead of print]. PubMed
Li R, Duan R, Zhang X, Lumley T, Pendergrass S, Bauer C, Hakonarson H, Carrell DS, Smoller JW, Wei WQ, Carroll R, Velez Edwards DR, Wiesner G, Sleiman P, Denny JC, Mosley JD, Ritchie MD, Chen Y, Moore JH. Lossless integration of multiple electronic health records for identifying pleiotropy using summary statistics. Nat Commun. 2021 Jan 8;12(1):168. doi: 10.1038/s41467-020-20211-2. PubMed
Klarin D, Verma SS, Judy R, Dikilitas O, Wolford BN, Paranjpe I, Levin MG, Pan C, Tcheandjieu C, Spin JM, Lynch J, Assimes TL, Nyrønning LÅ, Mattsson E, Edwards TL, Denny J, Larson E, Lee MTM, Carrell D, Zhang Y, Jarvik GP, Gharavi AG, Harley J, Mentch F, Pacheco JA, Hakonarson H, Skogholt AH, Thomas L, Gabrielsen ME, Hveem K, Nielsen JB, Zhou W, Fritsche L, Huang J, Natarajan P, Sun YV, DuVall SL, Rader DJ, Cho K, Chang KM, Wilson PWF, O'Donnell CJ, Kathiresan S, Scali ST, Berceli SA, Willer C, Jones GT, Bown MJ, Nadkarni G, Kullo IJ, Ritchie M, Damrauer SM, Tsao PS. Genetic architecture of abdominal aortic aneurysm in the Million Veteran program. Circulation. 2020 Sep 28. doi: 10.1161/CIRCULATIONAHA.120.047544. [Epub ahead of print]. PubMed
Palmer MR, Kim DS, Crosslin DR, Stanaway IB, Rosenthal EA, Carrell DS, Cronkite DJ, Gordon A, Du X, Li YK, Williams MS, Weng C, Feng Q, Li R, Pendergrass SA, Hakonarson H, Fasel D, Sohn S, Sleiman P, Handelman SK, Speliotes E, Kullo IJ, Larson EB, Ja+++. Loci identified by a genome-wide association study of carotid artery stenosis in the eMERGE network. Genet Epidemiol. 2021 Feb;45(1):4-15. doi: 10.1002/gepi.22360. Epub 2020 Sep 22. PubMed
Carrell DS, Malin BA, Cronkite DJ, Aberdeen JS, Clark C, Li MR, Bastakoty D, Nyemba S, Hirschman L. Resilience of clinical text de-identified with "hiding in plain sight" to hostile reidentification attacks by human readers. J Am Med Inform Assoc. 2020 Jul 1;27(9):1374-1382. doi: 10.1093/jamia/ocaa095. PubMed
Gordon AS, Zouk H, Venner E, Eng CM, Funke BH, Amendola LM, Carrell DS, Chisholm RL, Chung WK, Denny JC, Fedotov A, Hakonarson H, Kullo IJ, Larson EB, Leduc MS, Leppig KA, Lennon NJ, Linder JE, Muzny DM, Prows CA, Rasmussen-Torvik LJ, Rasouly HM, Roden DM, Rosenthal EA, Smith ME, Stanaway IB, Van Dreist SL, Walker K, Wiesner GL, Williams MS, Witkowski L, Crosslin DR, Gibbs RA, Rehm HL, Jarvik GP. Frequency of genomic secondary findings among 21,915 eMERGE network participants. Genet Med. 2020 Jun 17. doi: 10.1038/s41436-020-0810-9. Online ahead of print. PubMed
D Sullivan M, Boudreau D, Ichikawa L, Cronkite D, Albertson-Junkans L, Salgado G, VonKorff M, Carrell DS. Primary care opioid taper plans are associated with sustained opioid dose reduction. J Gen Intern Med. 2020 Mar;35(3):687-695. doi: 10.1007/s11606-019-05445-1. Epub 2020 Jan 6. PubMed
KPWHRI researchers are contributing to better mental health care for people nationwide.
Using doctor's notes to learn about drug reactions, dementia, and cannabis use.
Dr. Jennifer Nelson explains how KP scientists are helping the CDC and FDA keep an eye out for rare adverse events.
A Kaiser Permanente-led BCSC study is among the largest ever to evaluate adding MRI surveillance for breast cancer survivors.