Louisiana health system detects sepsis onset with Epic EHR tool

Hammond, La.-based North Oaks Health System is using a predictive modeling tool in its Epic EHR to help clinicians identify patients at increased risk for developing sepsis.

The tool, dubbed Clinical Care Advisory, generates a sepsis risk score by monitoring more than 80 data points from a patient's health record after they arrive in the emergency room, looking for early symptoms of sepsis. The tool assesses the patient's health information every 15 minutes, and if a patient's risk score reaches a certain threshold, it alerts clinicians that the patient may be becoming septic.

The CCA tool also recommends potential treatments for sepsis and continues to monitor the patient's care throughout their hospital stay.

"Treatment must begin within the first few hours of onset to offer the greatest chance of survival," said Herbert Robinson, MD, chief health information officer at North Oaks Health System. "That's why from the time patients arrive at our hospitals, we evaluate them carefully and then constantly monitor their clinical course to detect any developing signs or symptoms of sepsis."

Patients at North Oaks Health System with symptoms of sepsis are receiving antibiotics an estimated 30 minutes sooner since implementing the tool. In the past year, the sepsis mortality rate at the health system has dropped by nearly 18 percent, according to Dr. Robinson.

Seth Hain, director of analytics and machine learning at Epic, added: "Our goal is to make this new tool more accessible to community health systems like North Oaks by ensuring the setup and statistical validation are efficient and easy to use."

More articles on clinical leadership & infection control:
42 hospitals make Leapfrog's 'straight-A' list for safety
Machine learning model helps inform sepsis treatment in ER
AI tools to detect infection fall short when analyzing data across health systems

© Copyright ASC COMMUNICATIONS 2020. Interested in LINKING to or REPRINTING this content? View our policies by clicking here.

 

Featured Content

Featured Webinars

Featured Whitepapers