Health Informatics

“Our goal is to understand how to make health information technology practical in ways that directly engage patients and providers.”

James D. Ralston, MD, MPH
Kaiser Permanente Washington Health Research Institute Associate Investigator
Washington Permanente Medical Group, Internal Medicine

Research overview

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:

using a patient-shared EHR to improve care for chronic illnesses such as depression, diabetes, hypertension, and heart disease;
understanding the effects of technologies such as OpenNotes, which gives patients access to notes that their doctors write during office visits;
understanding and addressing differences in patient use of online health care services that could lead to disparities in care;
testing NLP to target mentions of specific words and phrases in EHRs to supplement or replace skilled chart abstraction—providing faster access to “big data” and actionable information about patients who may need follow up.

Examples of KPWHRI research in mobile health (mHealth) and user-centered design include:

evaluating mHealth smartphone tools: 1) to improve primary care for alcohol use disorders, 2) to support patients after bariatric surgery, and 3) to change smoking behavior;
the VITAL and Seeing Priorities studies to apply user-centered processes to learn how health care providers can elicit and honor what is most important to patients living with multiple chronic health conditions;
the REMIND project applying user-centered methods to redesign clinical reminders and notifications for patients with chronic and preventive health care needs;
the landmark Electronic Communications and Blood Pressure (eBP) study of home blood pressure monitoring and web-based care to increase hypertension control without office visits.

“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.

Recent publications on Health Informatics

Smith-Bindman R, Wang Y, Yellen-Nelson TR, Moghadassi M, Wilson N, Gould R, Seibert A, Boone JM, Krishnam M, Lamba R, Hall DJ, Miglioretti DL. Predictors of CT radiation dose and their effect on patient care: a comprehensive analysis using automated data. Radiology. 2017 Jan;282(1):182-193. doi: 10.1148/radiol.2016151391. Epub 2016 Jul 20. 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

Tieu L, Schillinger D, Sarkar U, Hoskote M, Hahn KJ, Ratanawongsa N, Ralston JD, Lyles CR. Online patient websites for electronic health record access among vulnerable populations: portals to nowhere? J Am Med Inform Assoc. 2017 Apr 1;24(e1):e47-e54. doi: 10.1093/jamia/ocw098. PubMed

Tajuddin SM, Schick UM, Eicher JD, Chami N, Giri A, Brody JA, Hill WD, Kacprowski T, Li J, Lyytikäinen LP, Manichaikul A, Mihailov E, O'Donoghue ML, Pankratz N, Pazoki R, Polfus LM, Smith AV, Schurmann C, Vacchi-Suzzi C, Waterworth DM, Evangelou E, Yanek LR, Burt A, Chen MH, van Rooij FJ, Floyd JS, Greinacher A, Harris TB, Highland HM, Lange LA, Liu Y, Mägi R, Nalls MA, Mathias RA, Nickerson DA, Nikus K, Starr JM, Tardif JC, Tzoulaki I, Velez Edwards DR, Wallentin L, Bartz TM, Becker LC, Denny JC, Raffield LM, Rioux JD, Friedrich N, Fornage M, Gao H, Hirschhorn JN, Liewald DC, Rich SS, Uitterlinden A, Bastarache L, Becker DM, Boerwinkle E, de Denus S, Bottinger EP, Hayward C, Hofman A, Homuth G, Lange E, Launer LJ, Lehtimäki T, Lu Y, Metspalu A, O'Donnell CJ, Quarells RC, Richard M, Torstenson ES, Taylor KD, Vergnaud AC, Zonderman AB, Crosslin DR, Deary IJ, Dörr M, Elliott P, Evans MK, Gudnason V, Kähönen M, Psaty BM, Rotter JI, Slater AJ, Dehghan A, White HD, Ganesh SK, Loos RJ, Esko T, Faraday N, Wilson JG, Cushman M, Johnson AD, Edwards TL, Zakai NA, Lettre G, Reiner AP, Auer PL. Large-scale exome-wide association analysis identifies loci for white blood cell traits and pleiotropy with immune-mediated diseases. Am J Hum Genet. 2016 Jul 7;99(1):22-39. doi: 10.1016/j.ajhg.2016.05.003. Epub 2016 Jun 23. PubMed

Eicher JD, Chami N, Kacprowski T, Nomura A, Chen MH, Yanek LR, Tajuddin SM, Schick UM, Slater AJ, Pankratz N, Polfus L, Schurmann C, Giri A, Brody JA, Lange LA, Manichaikul A, Hill WD, Pazoki R, Elliot P, Evangelou E, Tzoulaki I, Gao H, Vergnaud AC, Mathias RA, Becker DM, Becker LC, Burt A, Crosslin DR, Lyytikäinen LP, Nikus K, Hernesniemi J, Kähönen M, Raitoharju E, Mononen N, Raitakari OT, Lehtimäki T, Cushman M, Zakai NA, Nickerson DA, Raffield LM, Quarells R, Willer CJ, Peloso GM, Abecasis GR, Liu DJ; Global Lipids Genetics Consortium, Deloukas P, Samani NJ, Schunkert H, Erdmann J; CARDIoGRAM Exome Consortium; Myocardial Infarction Genetics Consortium, Fornage M, Richard M, Tardif JC, Rioux JD, Dube MP, de Denus S, Lu Y, Bottinger EP, Loos RJ, Smith AV, Harris TB, Launer LJ, Gudnason V, Velez Edwards DR, Torstenson ES, Liu Y, Tracy RP, Rotter JI, Rich SS, Highland HM, Boerwinkle E, Li J, Lange E, Wilson JG, Mihailov E, Mägi R, Hirschhorn J, Metspalu A, Esko T, Vacchi-Suzzi C, Nalls MA, Zonderman AB, Evans MK, Engström G, Orho-Melander M, Melander O, O'Donoghue ML, Waterworth DM, Wallentin L, White HD, Floyd JS, Bartz TM, Rice KM, Psaty BM, Starr JM, Liewald DC, Hayward C, Deary IJ, Greinacher A, Völker U, Thiele T, Völzke H, van Rooij FJ, Uitterlinden AG, Franco OH, Dehghan A, Edwards TL, Ganesh SK, Kathiresan S, Faraday N, Auer PL, Reiner AP, Lettre G, Johnson AD. Platelet-related variants identified by exomechip meta-analysis in 157,293 individuals. Am J Hum Genet. 2016 Jul 7;99(1):40-55. doi: 10.1016/j.ajhg.2016.05.005. Epub 2016 Jun 23. PubMed