Novel application of approaches to predicting medication adherence using medical claims data.

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.

Department

Description

Provenance

Citation

Published Version (Please cite this version)

10.1111/1475-6773.13200

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.

Scholars@Duke

Zullig

Leah L Zullig

Professor in Population Health Sciences

Leah L. Zullig, PhD, MPH is a health services researcher and an implementation scientist. She is a Professor in the Duke 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’s overarching research interests address three domains: improving cancer care delivery and quality; promoting cancer survivorship and chronic disease management; and improving medication adherence. Throughout these three area of foci Dr. Zullig uses an implementation science lens with the goal of providing equitable care for all by implementing evidence-based practices in a variety of health care environments. She has authored over 150 peer-reviewed publications. 

Dr. Zullig completed her BS in Health Promotion, her MPH in Public Health Administration, and her PhD in Health Policy.

Areas of expertise: Implementation Science, Health Measurement, Health Policy, Health Behavior, Telehealth, and Health Services Research

Thomas

Laine Elliott Thomas

Professor of Biostatistics & Bioinformatics

Laine Thomas, PhD, joined the Department of Biostatistics and Bioinformatics and DCRI in 2009.  She serves as Associate Chair for Equity, Diversity and Inclusion within the Department of Biostatistics and Bioinformatics and Deputy 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.      

Bosworth

Hayden Barry Bosworth

Professor in Population Health Sciences

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.