Decision Support Analytics Workgroup
ICU Medication Safety

ICU Medication Safety


Aim 1: R01-funded work to compare NICU medication order and Medication Administration Record (MAR) data in realtime and notify clinicians when there is a discrepancy (possible error)

Aim 2: Studying the portability of the work into other NICUs and adult ICU settings.

Aim 3: Incorporating smart infusion pump data into Med Administration error detection algorithms, so could compare order, med administration record (MAR) and smart pump data.

ICU Medication Safety

Click image to enlarge.

Clinical Rationale/Problem Solved

Aim 1: Medication administration errors are among the most common types of medical errors

Aim 2: Are the algorithms feasible in other environments and settings, and what customization is needed?

Aim 3: Smart infusion pumps are a source for new types of administration errors

Potential Impact

Aim 1: Reduction of administration errors with high-risk medications.

Aim 2: Prove that the algorithms are generalizable depending on workflows and data of the setting.

Aim 3: More robust detection and mitigation of medication administration errors.

DSAW Investigators

Eric Kirkendall (co-PI)


Kristin Melton (co-PI), Yizhao Ni, Todd Lingren, Jareen Meinzen-Derr, Katie Walsh, Matt Leonard,  (UC) Vivek Narendren, (UC) Nishant Gupta, (UC) Dan Schauer


2015-2019 NIH/NLM Grant #1R01LM012230-01 (Peer-reviewed)
“Improving Intensive Care Medication Safety through EHR-based Algorithms.”
Principal Investigator: Eric Kirkendall, MD, MBI, Kristin Melton, MD

NIH/NICHHD Grant #1R21HD072883-01 (Peer-reviewed)
“EHR-based patient safety: Automated error detection in neonatal intensive care unit”
Principal Investigator: Imre Solti, MD, PhD
Role: Principal Investigator


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 May 1;25(5):555-563.

 Li Q, Kirkendall ES, Hall ES, Ni Y, Lingren T, Kaiser M, Lingren N, Zhai H, Solti I, Melton K. Automated detection of medication administration errors in neonatal intensive care.  J Biomed Inform. 2015 Oct;57:124-33.

 Li Q, Melton K, Lingren T, Kirkendall ES, Hall E, Zhai H, Ni Y, Kaiser M, Stoutenborough L, Solti I. 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 Sep-Oct;21(5):776-84.