Sam Brusco, Associate Editor12.09.21
Baxter released new data from its retrospective study, which found machine learning AI might help support clinical decisions during smart infusion pump programming. The study was presented at the American Society of Health-System Pharmacists (ASHP) 2021 Midyear Clinical Meeting.
The study is part of collaboration with MedAware intended to support Baxter’s development of next-gen dose reduction software to integrate into Baxter’s infusion pumps and health enterprise connectivity.
“This study shows promise around the potential to enhance patient safety by using machine learning platforms to build and maintain smart infusion drug libraries that dynamically review infusions and signal possible infusion errors,” Douglas M. Hansell, M.D., MPH, VP of medical affairs for Baxter’s Medication Delivery business told the press. “Baxter is eager to further explore the use of machine learning and other digital health platforms to generate real-time insights that support individualized clinical decisions.”
Smart infusion pumps use dose error reduction systems (DERS) to prevent medication errors by checking programmed doses against preset drug limits. If outside the limits, the pump alerts clinicians, requiring confirmation before delivery (soft limit) or not allowing it at all (hard limit).1
MedAware’s machine learning analyzed 3,823,367 infusions on 20,542 Baxter infusion pumps over 10 months. Algorithms applied to the data set identified outliers: infusions deviating from commonly programed drug doses and rates, uncommon drug concentrations, and patient weight entries outside normal ranges.
44,819 programming entries were found to be outliers to common programming patterns. 23 percent triggered DERS soft limits and 52 percent triggered hard limits. MedAware’s machine learning spotted about a quarter of the outliers. However, this didn’t trigger DERS because parameters were set within DERS soft limits, so clinicians didn’t receive an alert.
This reinforces challenges with maintaining meaningful DERS limits. Investigators concluded machine learning could inform future hospital collaboration on more clinically relevant DERS limits.
“We are thrilled to evaluate our medication safety monitoring technology within Baxter’s smart infusion pumps,” said Dr. Gidi Stein, co-founder and CEO of MedAware. “This study shows the significant potential of an AI-enabled, data-driven approach to mitigate alert fatigue and identify pump programming errors that would be difficult to find using conventional approaches and rule-based systems alone.”
Reference
1 ECRI Institute: ECRI: In Depth – Dose Error Reduction Systems.
The study is part of collaboration with MedAware intended to support Baxter’s development of next-gen dose reduction software to integrate into Baxter’s infusion pumps and health enterprise connectivity.
“This study shows promise around the potential to enhance patient safety by using machine learning platforms to build and maintain smart infusion drug libraries that dynamically review infusions and signal possible infusion errors,” Douglas M. Hansell, M.D., MPH, VP of medical affairs for Baxter’s Medication Delivery business told the press. “Baxter is eager to further explore the use of machine learning and other digital health platforms to generate real-time insights that support individualized clinical decisions.”
Smart infusion pumps use dose error reduction systems (DERS) to prevent medication errors by checking programmed doses against preset drug limits. If outside the limits, the pump alerts clinicians, requiring confirmation before delivery (soft limit) or not allowing it at all (hard limit).1
MedAware’s machine learning analyzed 3,823,367 infusions on 20,542 Baxter infusion pumps over 10 months. Algorithms applied to the data set identified outliers: infusions deviating from commonly programed drug doses and rates, uncommon drug concentrations, and patient weight entries outside normal ranges.
44,819 programming entries were found to be outliers to common programming patterns. 23 percent triggered DERS soft limits and 52 percent triggered hard limits. MedAware’s machine learning spotted about a quarter of the outliers. However, this didn’t trigger DERS because parameters were set within DERS soft limits, so clinicians didn’t receive an alert.
This reinforces challenges with maintaining meaningful DERS limits. Investigators concluded machine learning could inform future hospital collaboration on more clinically relevant DERS limits.
“We are thrilled to evaluate our medication safety monitoring technology within Baxter’s smart infusion pumps,” said Dr. Gidi Stein, co-founder and CEO of MedAware. “This study shows the significant potential of an AI-enabled, data-driven approach to mitigate alert fatigue and identify pump programming errors that would be difficult to find using conventional approaches and rule-based systems alone.”
Reference
1 ECRI Institute: ECRI: In Depth – Dose Error Reduction Systems.