Designing a more efficient, effective and safe Medical Emergency Team (MET) service using data analysis

Area of Science:

• Medical Emergency Response
• Clinical Algorithm Development
• Health Informatics

Background:

• Hospitals are experiencing an increase in Medical Emergency Team (MET) reviews.
• Common MET calls often lead to similar treatment protocols.
• There is a need for proactive management strategies to improve patient outcomes and reduce MET activation.

Purpose of the Study:

• To design a pre-emptive management algorithm for direct treatment of common MET call causes.
• To model the potential impact of this algorithm on MET call incidence and patient outcomes.
• To enable earlier treatment initiation for patients without MET team attendance.

Main Methods:

• Extracted data from hospital databases for all MET calls over a 34-month period.
• Utilized association rule data mining to identify common MET call causes, outcomes, and therapies.
• Modeled the effect of a pre-emptive management algorithm on a subsequent 24-month period.

Main Results:

• Hypotension was the most common MET call (31%), strongly associated with immediate intra-venous fluid administration.
• A pre-emptive management algorithm could reduce MET calls for hypotension by 68.7% and total MET calls by 19.6%.
• The modeled algorithm showed no adverse effects on patient outcomes.

Conclusions:

• Routinely collected data and analytical techniques can create effective pre-emptive management algorithms.
• A pre-emptive algorithm for intravenous fluid therapy in hypotensive patients can reduce MET calls.
• This approach facilitates earlier patient treatment and decreases overall MET activations.