Predicting and preventing adverse events such as cardiac arrest is part of daily patient care with machine learning. With the help of Epic’s machine learning platform and optional integration with Microsoft Azure, Ochsner Health System calculates patients’ risk of deterioration in real time and sends notifications directly to physicians’ mobile devices so they can intervene sooner.
Behind the scenes, Epic’s machine learning platform analyzes hundreds of data elements in a patient’s chart, such as medications, medical history, and real-time vital monitor data. Meanwhile, Ochsner’s physicians focus on proactively providing at-the-bedside attention to lower those patients’ risk. In Ochsner’s 90-day pilot of their deterioration model, a rapid response team acted on predictions sent to their mobile devices through Epic and managed to significantly reduce adverse events outside the ICU.
Ochsner plans to give clinicians across their health system help from Epic’s machine learning platform, starting with acute care. The platform supports Epic’s own machine learning library, as well as machine learning models created by community members like Ochsner. “You have both humans and artificial intelligence looking after you while you’re here,” says Jonathan Wilt, CTO of innovationOchsner. “We can detect health patterns, learn from these insights and develop a more aggressive treatment plan as a preventative measure,” says Ochsner’s System VP and CIO Laura Wilt.