Medication Data Science (MeDS) Lab

Dr. Corey Lester, PharmD, PhD, MS leads the Medication Data Science (MeDS) lab in the College of Pharmacy at the University of Michigan. The MeDS lab studies the effect of artificial intelligence, including machine learning, on provider well-being, health outcomes, patient experience, and costs in medication use systems. This research approach is purposefully composed of engineers, information scientists, statisticians, and clinicians to foster creative and disruptive innovations that improve human health. A data science-supported approach to the quadruple aim of medication use systems, combined with domain knowledge expertise, leads to significant breakthroughs in both theoretical and applied research. Human-machine learning teams need to work interdependently to achieve routine, reliable, and resilient improvements in medication use systems. The MeDS lab is achieving this ambitious goal by partnering with industry and academia to create novel solutions.

The MeDS lab is currently conducting two federally funded research projects examining the use of artificial intelligence in the community pharmacies. Dr. Lester was awarded a 3-year grant that aims to improve medication safety through the strategic use of automation in medication prescribing and dispensing workflows. The overall objective of this study is to determine the effect of implementing just-in-time feedback on the prevention of medication errors during e-prescription transactions between healthcare organizations.

Dr. Lester, along with his colleagues Drs. Raed Al Kontar and Xi Jessie Yang in the College of Engineering, were awarded a prestigious National Library of Medicine grant to study the use of machine intelligence to assist in the pill verification process to help avoid dangerous and costly pharmacy dispensing errors. The goal of this research is to create machine learning that is capable of conveying accurate information that encourages providers to make sound cognitive decisions such that optimal trust is maintained, and temporal and cognitive demand is reduced. Imperative to this goal is to design interpretable machine learning that is conveyed in an effective manner effective manner that appropriately calibrate user’s trust to avoid over-trust or under-trust in the system. By achieving these goals, the MeDS Lab team will ensure that patients get the correct pills in the correct bottle, ultimately creating safer systems that can save lives.

RECENT PUBLICATIONS

Gong J, Zheng Y, Lester CA. Pharmacist Initiated Interventions Using RxChange Message Communication with Prescribers for Electronic Prescriptions: A Retrospective Descriptive Study. J Am Pharm Assoc (2003). 2024 Jul 17:102188. doi: 10.1016/j.japh.2024.102188. Epub ahead of print. PMID: 39029625.

Whitaker M, Lester C, Rowell B. Handing Off Electronic Prescription Data From Prescribers to Community Pharmacies: A Qualitative Analysis of] Pharmacy Staff Perspectives. J Patient Saf. 2024 Sep 1;20(6):397-403. doi: 10.1097/PTS.0000000000001244. Epub 2024 May 15. PMID: 38742931; PMCID: PMC11335435.

Zheng Y, Rowell B, Chen Q, Kim JY, Kontar RA, Yang XJ, Lester CA. Designing Human-Centered AI to Prevent Medication Dispensing Errors: Focus Group Study With Pharmacists. JMIR Form Res. 2023 Dec 25;7:e51921. doi: 10.2196/51921. PMID: 38145475; PMCID: PMC10775023.

Lester CA, Flynn AJ, Marshall VD, Rochowiak S, Bagian JP. Implementation outcomes of the Structured and Codified SIG format in electronic prescription directions. J Am Med Inform Assoc. 2022 Oct 7;29(11):1859-1869. doi: 10.1093/jamia/ocac124. PMID: 35927972; PMCID: PMC9552209.

Lester CA, Flynn AJ, Marshall VD, Rochowiak S, Rowell B, Bagian JP. Comparing the variability of ingredient, strength, and dose form information from electronic prescriptions with RxNorm drug product descriptions. J Am Med Inform Assoc. 2022 Aug 16;29(9):1471-1479. doi: 10.1093/jamia/ocac096. PMID: 35773948; PMCID: PMC9382370.

Lester CA, Li J, Ding Y, Rowell B, Yang J’, Kontar RA. Performance evaluation of a prescription medication image classification model: an observational cohort. NPJ Digit Med. 2021 Jul 27;4(1):118. doi: 10.1038/s41746-021-00483-8. Erratum in: NPJ Digit Med. 2022 Feb 16;5(1):22. doi: 10.1038/s41746-022-00564-2. PMID: 34315995; PMCID: PMC8316316.

Lester CA, Ding Y, Li J, Jiang Y, Rowell B, Vydiswaran VGV. Human versus machine editing of electronic prescription directions. J Am Pharm Assoc (2003). 2021 Jul-Aug;61(4):484-491.e1. doi: 10.1016/j.japh.2021.02.006. Epub 2021 Feb 19. PMID: 33766549.

Lester CA, Coe AB, Dorsch MP, Farris KB, Flynn AJ. A learning pharmacy practice enabled by the pharmacists’ patient care process. J Am Pharm Assoc (2003). 2020 Nov-Dec;60(6):e66-e72. doi: 10.1016/j.japh.2020.05.013. Epub 2020 Jul 1. PMID: 32620363; PMCID: PMC9840881.

Dr. Lester currently teaches CPTS 832 Pharmacy Informatics Research.