Over 400,000 deaths per year are the result of preventable harm,1 with medication errors contributing to a large proportion of these errors.2 Specifically, errors at the ordering are particularly at risk for causing serious patient harm.3-5

A novel automated measure of wrong patient ordering errors, using the Retract-and-Reorder (RAR) methodology, has been used to evaluate multiple interventions to prevent wrong patient errors, with the results published in multiple large impact journals (e.g. JAMA).7-9 Further studies, currently in the manuscript stage, have validated new automated measures of ordering errors. Our research team is now developing a database with over 100 million orders and approximately 250,000 RAR events. The database will contain detailed records of clinical encounters, including details around each order placed, as well as patient, clinical, and unit characteristics. Once complete, the database will allow clinical scientists to ask a myriad of questions regarding the association of provider and patient demographics with electronic ordering errors. In addition, the database will allow for the development of machine learning models that aim to predict, and ultimately help prevent, these errors. We aim to recruit data scientists to help to continue to develop this database, which will be the largest known database of electronic ordering errors. The student will also help with the creation of a Python program which will ensure the previously developed measures are easily extrapolated to institutions throughout the United States. Those with specific machine learning skills can also work to identify machine learning algorithms to predict these errors. The data scientist will work with the Dr. Adelman, Chief Patient Safety Officer at CUIMC, and a team of physicians and informaticians. Output of this project will inform clinicians in developing conducting research as it relates to patient safety interventions with the ultimate goal of improving patient care.   References:

  1. James JT. A new, evidence-based estimate of patient harms associated with hospital care. J Patient Saf. 2013;9(3):122-128.
  2. U.S. Department of Health and Human Services Office of Inspector General. Adverse Events in Hospitals: A Quarter of Medicare Patients Experienced Harm in October 2018 . Updated May, 2022. Accessed June 1, 2022. https://oig.hhs.gov/oei/reports/OEI-06-18-00400.pdf.
  3. Nebeker JR, Hoffman JM, Weir CR, Bennett CL, Hurdle JF. High rates of adverse drug events in a highly computerized hospital. Arch Intern Med. 2005;165(10):1111-1116.
  4. Flynn EA, Barker KN, Carnahan BJ. National observational study of prescription dispensing accuracy and safety in 50 pharmacies. J Am Pharm Assoc (Wash). 2003;43(2):191-200.
  5. Aronson JK. Medication errors: what they are, how they happen, and how to avoid them. Qjm. 2009;102(8):513-521.
  6. Hodkinson A, Tyler N, Ashcroft DM, et al. Preventable medication harm across health care settings: a systematic review and meta-analysis. BMC Med. 2020;18(1):313.
  7. Adelman JS KG, Schechter CB, Weiss JM, Berger MA, Reissman SH, Cohen HW, Lorenzen SJ, Burack DA, Southern WN, et al. Effect of Restriction of the Number of Concurrently Open Records in an Electronic Health Record on Wrong-Patient Order Errors. JAMA. 2019;321:18.
  8. Adelman JS, Applebaum JR, Southern WN, et al. Risk of Wrong-Patient Orders Among Multiple vs Singleton Births in the Neonatal Intensive Care Units of 2 Integrated Health Care Systems. JAMA Pediatr. 2019;173(10):979-985.
  9. Adelman JS, Kalkut GE, Schechter CB, et al. Understanding and preventing wrong-patient electronic orders: a randomized controlled trial. J Am Med Inform Assoc. 2013;20(2):305-310.

Selected candidate(s) can receive a stipend directly from the faculty advisor. This is not a guarantee of payment, and the total amount is subject to available funding.

Faculty Advisor

Project Timeline

  • Earliest starting date: 4/2/2023
  • End date: 8/30/2023
  • Number of hours per week of research expected during Spring-Summer 2023: ~0

Candidate requirements

  • Skill sets: Fluency in Python and SQL. Prior experience in machine learning a plus but not required.
  • Student eligibility: freshman, sophomore, junior, senior, master’s
  • International students on F1 or J1 visa: NOT eligible
  • Academic Credit Possible: No