Skip to main content
EMERGING INNOVATIONS
New

The generalizability of a medication administration discrepancy detection system: quantitative comparative analysis

Kirkendall E, Huth H, Rauenbuehler B, Moses A, Melton K, Ni Y. The Generalizability of a Medication Administration Discrepancy Detection System: Quantitative Comparative Analysis. JMIR Med Inform. 2020;8(12):e22031

Save

Print

September 29, 2021

Medication administration errors are a common source of patient harm. Considerable effort has been devoted to optimizing methods of detecting and preventing medication errors, particularly through the use of electronic health record (EHR) systems.

Developed at Cincinnati Children’s Hospital Medical Center (CCHMC), MED.Safe is an automated software package designed to monitor high-risk intravenous (IV) medications in neonatal intensive care units (NICUs) and identify medication administration discrepancies. The software analyzes medication administration records (MARs) for eleven IV medications associated with the highest rate of harm in the NICU setting: dobutamine, dopamine, epinephrine, fentanyl, insulin, intravenous fluids, milrinone, morphine, total parenteral nutrition (TPN), and vasopressin. The MED.Safe software extracts four types of data from the EHR (medication orders, order modifications, medication administration records (MARs), and free-text physician-to-nurse communication orders (parsed using natural language processing algorithms)). Using the extracted information, the MED.Safe algorithms identify discrepant doses/rates between MARs and medication orders, order modifications, and free-text communication using logic-based rules. 

Researchers with Wake Forest Baptist Medical Center (WFBMC) explored the generalizability of the MED.Safe software in pediatric and adult intensive care settings (PICU and ICU). Findings indicate that execution of MED.Safe at a second site was feasible and effective in detecting medication discrepancies but identified several areas where the software could be modified and improved. For example, since MED.Safe was developed for the NICU setting, it does not include common adult vasopressors such as norepinephrine, which account for a large proportion of medication orders in adult ICU settings. Results show that medication discrepancy rates at WFBMC aligned well with CCHMC for most medications, but the discrepancy rates for insulin, dobutamine, and dopamine at WFBMC were larger compared to those at CCHMC. The authors note that three factors are likely contributing to these differences: (1) range-based dosing, which is common in adult medicine prescribing, particularly for insulin; (2) order/audit value overwriting by the institutional EHR (resolved via software update); (3) verbal ordering practices, which occur frequently in emergency settings while the electronic orders are documented after the care is delivered.

Related Studies

Ni Y, Lingren T, Hall ES, Leonard M, Melton K, Kirkendall ES. Designing and evaluating an automated system for real-time medication administration error detection in a neonatal intensive care unit. J Am Med Inform Assoc. 2018;25(5):555-563. [Available at]
 
Li Q, Kirkendall ES, Hall ES, et al. Automated detection of medication administration errors in neonatal intensive care. J Biomed Inform. 2015;57:124-133. [Available at]
 
Li Q, Melton K, Lingren T, et al. Phenotyping for patient safety: algorithm development for electronic health record based automated adverse event and medical error detection in neonatal intensive care. J Am Med Inform Assoc. 2014;21(5):776-784. [Available at]

Contact the Innovator

Eric Kirkendell, MD, MBI
Center for Healthcare Innovation
Wake Forest School of Medicine
ekirkend@wakehealth.edu

Kristin Melton, MD
Professor of Pediatrics
Division of Neonatology
Cincinnati Children's Hospital Medical Center and University of Cincinnati School of Medicine
Kristin.melton@cchmc.org

Save

Print

Cite
Citation

Kirkendall E, Huth H, Rauenbuehler B, Moses A, Melton K, Ni Y. The Generalizability of a Medication Administration Discrepancy Detection System: Quantitative Comparative Analysis. JMIR Med Inform. 2020;8(12):e22031