Novel application of approaches to predicting medication adherence using medical claims data.
Date
2019-12
Journal Title
Journal ISSN
Volume Title
Repository Usage Stats
views
downloads
Citation Stats
Attention Stats
Abstract
Objective
To compare predictive analytic approaches to characterize medication nonadherence and determine under which circumstances each method may be best applied.Data sources/study setting
Medicare Parts A, B, and D claims from 2007 to 2013.Study design
We evaluated three statistical techniques to predict statin adherence (proportion of days covered [PDC ≥ 80 percent]) in the year following discharge: standard logistic regression with backward selection of covariates, least absolute shrinkage and selection operator (LASSO), and random forest. We used the C-index to assess model discrimination and decile plots comparing predicted values to observed event rates to evaluate model performance.Data extraction
We identified 11 969 beneficiaries with an acute myocardial infarction (MI)-related admission from 2007 to 2012, who filled a statin prescription at, or shortly after, discharge.Principal findings
In all models, prior statin use was the most important predictor of future adherence (OR = 3.65, 95% CI: 3.34-3.98; OR = 3.55). Although the LASSO regression model selected nearly 90 percent of all candidate predictors, all three analytic approaches had moderate discrimination (C-index ranging from 0.664 to 0.673).Conclusions
Although none of the models emerged as clearly superior, predictive analytics could proactively determine which patients are at risk of nonadherence, thus allowing for timely engagement in adherence-improving interventions.Type
Department
Description
Provenance
Subjects
Citation
Permalink
Published Version (Please cite this version)
Publication Info
Zullig, Leah L, Shelley A Jazowski, Tracy Y Wang, Anne Hellkamp, Daniel Wojdyla, Laine Thomas, Lisa Egbuonu-Davis, Anne Beal, et al. (2019). Novel application of approaches to predicting medication adherence using medical claims data. Health services research, 54(6). pp. 1255–1262. 10.1111/1475-6773.13200 Retrieved from https://hdl.handle.net/10161/28703.
This is constructed from limited available data and may be imprecise. To cite this article, please review & use the official citation provided by the journal.
Collections
Scholars@Duke
Leah L Zullig
Leah L. Zullig, PhD, MPH is a health services researcher and implementation scientist whose work focuses on accelerating the adoption of evidence-based practices to improve healthcare delivery and population health. She is a Professor in the Duke University Department of Population Health Sciences and an investigator with the Center of Innovation to Accelerate Discovery and Practice Transformation (ADAPT) at the Durham Veterans Affairs Health Care System.
Dr. Zullig is a recognized leader in implementation science. She directs INTERACT, the Implementation Science Research Collaborative, which fosters interdisciplinary collaborations across Duke University and with external partners to accelerate the translation of research into practice. She also leads the Dissemination and Implementation Catalyst within Duke's Clinical and Translational Science Award (CTSA) program and serves as Co-Leader of the Duke Cancer Institute's Cancer Prevention and Control Research Program.
Dr. Zullig's research spans three interconnected areas: improving the quality and delivery of cancer care; advancing cancer survivorship and chronic disease management; and enhancing medication adherence. Across these domains, she applies implementation science methods to develop, evaluate, and scale evidence-based interventions that promote equitable, high-quality care across diverse healthcare settings. Her research is characterized by strong partnerships with healthcare systems, ensuring that findings extend beyond publication to inform clinical practice, health system transformation, and policy.
Dr. Zullig has authored more than 200 peer-reviewed publications and has established a national reputation for leading pragmatic, health system-embedded research that improves patient outcomes and advances the science of implementation.
Dr. Zullig earned her Bachelor of Science in Health Promotion, Master of Public Health in Public Health Administration, and PhD in Health Policy.
Daniel Wojdyla
Laine Elliott Thomas
Laine Thomas, PhD is a Professor in the Department of Biostatistics and Bioinformatics, co-chair of the Division of Biostistics, and Director of Data Science and Biostatistics at the Duke Clinical Research Institute. She is a leader in study design and development of methods for observational and pragmatic studies, with over 240 peer reviewed clinical and methodological publications arising from scientific collaboration in the therapeutic areas of cardiovascular disease, diabetes, uterine fibroids and SARS-CoV-2 virus. She led the statistical teams on the HERO COVID-19, ORBIT-AF I & II, ACTION-CMS, CHAMP-HF, and COMPARE-UF clinical registries and secondary analyses of the NAVIGATOR and ARISTOTLE clinical trials. She has served as a primary investigator and co-investigator on numerous methodological studies with funding from NIH, AHRQ, PCORI and Burroughs Wellcome Fund, addressing observational treatment comparisons, time-varying treatments, heterogeneity of treatment effects, and randomized trials augmented by synthetic controls from real world data.
Hayden Barry Bosworth
Dr. Bosworth is a health services researcher and Deputy Director of the Center of Innovation to Accelerate Discovery and Practice Transformation (ADAPT) at the Durham VA Medical Center. He is also Vice Chair of Education and Professor of Population Health Sciences. He is also a Professor of Medicine, Psychiatry, and Nursing at Duke University Medical Center and Adjunct Professor in Health Policy and Administration at the School of Public Health at the University of North Carolina at Chapel Hill. His research interests comprise three overarching areas of research: 1) clinical research that provides knowledge for improving patients’ treatment adherence and self-management in chronic care; 2) translation research to improve access to quality of care; and 3) eliminate health care disparities.
Dr. Bosworth is the recipient of an American Heart Association established investigator award, the 2013 VA Undersecretary Award for Outstanding Achievement in Health Services Research (The annual award is the highest honor for VA health services researchers), and a VA Senior Career Scientist Award. In terms of self-management, Dr. Bosworth has expertise developing interventions to improve health behaviors related to hypertension, coronary artery disease, and depression, and has been developing and implementing tailored patient interventions to reduce the burden of other chronic diseases. These trials focus on motivating individuals to initiate health behaviors and sustaining them long term and use members of the healthcare team, particularly pharmacists and nurses. He has been the Principal Investigator of over 30 trials resulting in over 400 peer reviewed publications and four books. This work has been or is being implemented in multiple arenas including Medicaid of North Carolina, private payers, The United Kingdom National Health System Direct, Kaiser Health care system, and the Veterans Affairs.
Areas of Expertise: Health Behavior, Health Services Research, Implementation Science, Health Measurement, and Health Policy
Unless otherwise indicated, scholarly articles published by Duke faculty members are made available here with a CC-BY-NC (Creative Commons Attribution Non-Commercial) license, as enabled by the Duke Open Access Policy. If you wish to use the materials in ways not already permitted under CC-BY-NC, please consult the copyright owner. Other materials are made available here through the author’s grant of a non-exclusive license to make their work openly accessible.