Julia J. Smith, MS, has a passion for utilizing existing data from electronic health records (EHRs) to illuminate the effectiveness and benefits of treatments and medical modalities, as well as to identify people who may have health care needs that are not being sufficiently addressed.
Ms. Smith came to KPWHRI in 2021, joining projects to validate prediction models, compare suicide risk predictions for those undergoing pharmaceutical treatments, and analyze the impact of an intervention for falls risk. This work is closely aligned with her passion to leverage existing data to identify people who may benefit from intervention or additional awareness and education on health.
Prior to joining KPWHRI, Ms. Smith worked in research at Southcentral Foundation for 13 years with a focus on health care services and mental health research, as well as data management. At SCF, her analyses projects included measuring the impact on quality and health outcomes after a shift to an innovative patient-centered medical home model, assessing patient and provider characteristics associated with completed depression and alcohol screening among primary care patients, performing epidemiologic and biomarker studies of tobacco use, measuring the impact of an intervention developed for people with complex health care needs, creating a registry of fragile pediatric customers for primary care providers, and creating a system to balance primary care provider panels through risk prediction based on EHR data and publicly available social determinants of health (SDoH) variables.
Ms. Smith also spent 2 years with a Pacific Northwest payor in Portland, Oregon, conducting research as well as steering the build of data infrastructure for clinical services and a new technology solution with the goal of creating systems that would easily illuminate clinical effectiveness and quality.
Ms. Smith’s experience in research is built on a foundation in education, teaching, and mentorship that she carries with her through mentoring high school youth in the use of statistics in applied equity research as well as through mentoring professionals in health care services research methods.
Analyses of secondary, observational data; prediction models
Alzheimer’s, dementia, falls risk
Identifying variables for analysis and prediction modeling from publicly and commercially available SDoH data
Comparative effectiveness analyses, cost benefit analyses, intervention impact of health care delivery programs and products
Depression, substance use, suicide
Coley RY, Smith JJ, Karliner L, Idu AE, Lee SJ, Fuller S, Lam R, Barnes DE, Dublin S. External validation of the eRADAR risk score for detecting undiagnosed dementia in two real-world healthcare systems. J Gen Intern Med. 2022 Jul 29. doi: 10.1007/s11606-022-07736-6. Online ahead of print. PubMed
Shaw JL, Beans JA, Noonan C, Smith JJ, Mosley M, Lillie KM, Avey JP, Ziebell R, Simon G. Validating a predictive algorithm for suicide risk with Alaska Native populations. Suicide Life Threat Behav. 2022 Aug;52(4):696-704. doi: 10.1111/sltb.12853. Epub 2022 Mar 15. PubMed
Schaefer KR, Muller CJ, Smith JJ, Avey JP, Shaw JL Using the electronic health record to identify suicide risk factors in an Alaska Native health system. Psychol Serv. 2020 Aug 27. doi: 10.1037/ser0000492. Online ahead of print. PubMed
Smith JJ, Qiu Y, Lam SV, Lockwood CM, Pegus C, Gleason PP. Medical costs and health care utilization among self-insured members with carve-in versus carve-out pharmacy benefits. J Manag Care Spec Pharm. 2020 Jun;26(6):766-774. doi: 10.18553/jmcp.2020.19411. Epub 2020 Mar 10. PubMed
Schaefer KR, Noonan C, Mosley M, Smith JJ, Galbreath D, Fenn D, Robinson RF, Manson SM Differences in service utilization at an urban tribal health organization before and after Alzheimer's disease or related dementia diagnosis: a cohort study. Alzheimers Dement. 2019 Nov;15(11):1412-1419. doi: 10.1016/j.jalz.2019.06.4945. Epub 2019 Sep 25. PubMed
In a new study, a tool to help discover undiagnosed dementia performed well in 2 separate health systems.
NIMH funding will enable the MHRN to conduct larger studies in integrated health systems on topics that matter most.
Researchers find a relationship between prescribed central nervous system-active medications and increased risk of falling among older people with dementia.