Research on health informatics at Kaiser Permanente Washington focuses on developing and using health information technology (IT) to transform health care delivery. By testing new paradigms of care that provide more opportunities to engage patients, this research is supplying valuable evidence that is helping shape federal policy and guiding innovative redesign of health care.
“We’re working to understand how to make health IT practical so patients and care teams find it useful and engaging,” explained Kaiser Permanente Washington Health Research Institute (KPWHRI) Senior Investigator James Ralston, MD, MPH. “We want to find ways to use information technologies to support patients and providers together, both inside and outside the office.”
Integral to this support is designing technologies that are user-friendly and meet the needs of both patients and providers. By applying human-centered methods that focus on needs, use, and usability, KPWHRI researchers inform the design of health IT with direct participation from users.
Groundbreaking methodological work by KPWHRI health informatics researchers includes developing natural language processing (NLP) to analyze text such as notes and written reports in electronic health records (EHRs). Assistant Investigator David Carrell, PhD, leads in the area of using NLP and machine learning to identify patient phenotypes, or specific health characteristics such as possible heart disease, risk of opioid overdose, or suggestion of colon cancer. This information can assist researchers in studying how genetics and other factors influence disease.
Other examples of KPWHRI health informatics research include projects using EHRs and secure electronic communications such as:
Examples of KPWHRI research in mobile health (mHealth) and user-centered design include:
“Our studies on using health IT to improve care are showing that we can achieve better outcomes when we shift care from the doctor’s office to where people live: in their homes—and online,” said Senior Investigator Beverly B. Green, MD, MPH.
Carrell D, Ralston J. Variation in adoption rates of a patient web portal with a shared medical record by age, gender, and morbidity level. AMIA Annu Symp Proc. 2006;871. PubMed
Carrell DS, Cronkite D, Palmer RE, Saunders K, Gross DE, Masters ET, Hylan TR, Von Korff M. Using natural language processing to identify problem usage of prescription opioids. Int J Med Inform. 2015 Dec;84(12):1057-64. doi: 10.1016/j.ijmedinf.2015.09.002. Epub 2015 Sep 25. PubMed
Carrell DS, Cronkite DJ, Li MR, Nyemba S, Malin BA, Aberdeen JS, Hirschman L. The machine giveth and the machine taketh away: a parrot attack on clinical text deidentified with hiding in plain sight. J Am Med Inform Assoc. 2019 Dec 1;26(12):1536-1544. doi: 10.1093/jamia/ocz114. 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
Carrell DS, Gruber S, Floyd JS, Bann MA, Cushing-Haugen KL, Johnson RL, Graham V, Cronkite DJ, Hazlehurst BL, Felcher AH, Bejan CA, Kennedy A, Shinde M, Karami S, Ma Y, Stojanovic D, Zhao Y, Ball R, Nelson J. Improving methods of identifying anaphylaxis for medical product safety surveillance using natural language processing and machine learning. Am J Epidemiol. 2022 Nov 4:kwac182. doi: 10.1093/aje/kwac182. [Epub ahead of print]. PubMed
James D. Ralston, MD, MPHSenior Investigator |
Jennifer B. McClure, PhDDirector, Investigative Science |
Beverly B. Green, MD, MPHSenior Investigator |
Katharine A. Bradley, MD, MPHSenior Investigator |
Paula Lozano, MD, MPHSenior Investigator; Director, ACT Center |
Yates Coley, PhDAssociate Biostatistics Investigator |
Brian D. Williamson, PhDAssistant Biostatistics Investigator |
Annie Hoopes, MD, MPHActing Assistant Investigator |
Claire Allen, MPHManager, Collaborative Science |
Annie Piccorelli, PhDSenior Collaborative Biostatistician |