Visualizing nationwide variation in Medicare Part D prescribing patterns
Author and article information
Abstract
Objective: To characterize the regional and national variation in prescribing patterns in the Medicare Part D program using machine learning and dimensional reduction visualization methods.
Methods: Using publicly available Medicare Part D claims data, we identified regional and national provider prescribing profile variation with unsupervised clustering and t-distributed stochastic neighbor embedding (t-SNE) dimensional reduction techniques. Additionally, we examined differences between regionally representative prescribing patterns for major metropolitan areas.
Results: Distributions of prescribing volume and medication diversity were highly skewed among over 800,000 Medicare Part D providers, and medical specialties had characteristic prescribing patterns. Although the number of Medicare providers in each state was highly correlated with the number of Medicare Part D enrollees, some states were enriched for providers with >10,000 prescription claims annually. Hierarchical clustering and t-SNE dimension-reduction visualization of drug- or drug-class prescribing patterns revealed that providers cluster strongly based on specialty and sub-specialty, with large regional variations in prescribing patterns. Major metropolitan areas had distinct prescribing patterns that tended to group by major geographical divisions.
Conclusions: There is substantial prescribing variation among providers in Medicare Part D both between and within specialties. Large regional variations in prescribing patterns, particularly among major metropolitan areas, were also seen. Unsupervised clustering and t-SNE dimension-reduction are an effective means to examine variation in provider prescribing patterns, including substantial regional and medical specialty variation.
Cite this as
2017. Visualizing nationwide variation in Medicare Part D prescribing patterns. PeerJ Preprints 5:e3470v1 https://doi.org/10.7287/peerj.preprints.3470v1Author comment
This manuscript was submitted for peer review to BMC Medical Informatics and Decision Making on September 3, 2017.
Sections
Additional Information
Competing Interests
The authors declare that they have no competing interests.
Author Contributions
Alexander Rosenberg conceived and designed the experiments, performed the experiments, analyzed the data, wrote the paper, prepared figures and/or tables, reviewed drafts of the paper.
Christopher Fucile conceived and designed the experiments, performed the experiments, analyzed the data, contributed reagents/materials/analysis tools, prepared figures and/or tables, reviewed drafts of the paper.
Robert J White conceived and designed the experiments, performed the experiments, analyzed the data, wrote the paper, reviewed drafts of the paper.
Melissa Trayhan conceived and designed the experiments, performed the experiments, analyzed the data, contributed reagents/materials/analysis tools, reviewed drafts of the paper.
Samir Farooq performed the experiments, analyzed the data, contributed reagents/materials/analysis tools, reviewed drafts of the paper.
Lisa A Nelson conceived and designed the experiments, analyzed the data, wrote the paper, reviewed drafts of the paper, provided data sets.
Caroline M Quill conceived and designed the experiments, wrote the paper, reviewed drafts of the paper.
Samuel J Weisenthal contributed reagents/materials/analysis tools, wrote the paper, reviewed drafts of the paper.
Kristen Bush conceived and designed the experiments, wrote the paper, reviewed drafts of the paper.
Martin S. Zand conceived and designed the experiments, performed the experiments, analyzed the data, wrote the paper, prepared figures and/or tables, reviewed drafts of the paper.
Data Deposition
The following information was supplied regarding data availability:
The raw data is publicly available from the Center for Medicare Services, and links to the data are provided in the manuscript.
Funding
This work was supported by research grants from National Institute of Health: National Center for Advancing Translation Science UL1 TR000042 and U54 TR001625 (MZ, CQ, RW, and SW), KL2 TR001999 (CQ), TL1 TR002000 (SW, KB), R01AI098112 and R01AI069351 (MZ), from the Philip Templeton Foundation (MZ, RW, SF), and from the University of Rochester Center for Health Informatics (MZ, RW, AR, CF, SF, SW). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.