Anesthesiologists face significant challenges in monitoring patients in the operating room as they are inundated with data. To help guide anesthesia providers in surgery, a decision support system integrates multiple real-time data streams into a single dashboard providing a ‘live’ schematic view of organs.
The system, called AlertWatch, leverages data extracted from physiologic monitors, electronic health records and laboratory systems, and then displays a patient’s condition in a single user interface, with color-coded icons to indicate normal (green), borderline abnormal (yellow) and abnormal (red) ranges for the data related to each organ system or lab value. The central part of the dashboard includes icons of five organ systems: brain, heart, kidneys, liver and lungs.
According to Sachin Kheterpal, MD, associate professor of anesthesiology at the University of Michigan Medical School, anesthesiologists generally need to be aware of 40 different patient data streams at once during surgery, including blood pressure, ventilation and heart rate.
“It’s not realistic to believe that someone could be doing that consistently during a five-hour operation,” says Kheterpal. “What AlertWatch lets us do is to focus our vigilance on things that are germane, either based on the patient’s past medical history or based on real-time data streams. This really is a way to augment and support human vigilance, as opposed to trying to replace it.”
AlertWatch was cleared by the Food and Drug Administration in early 2014, enabling the University of Michigan startup to sell its patient monitoring software to hospitals. Kheterpal notes that in addition to the installation at the University of Michigan, the decision support system is currently being used at three other hospitals across the country.
However, now—four years later—a study of nearly 27,000 patients using AlertWatch has produced mixed results published in the February issue of Anesthesiology.
While use of the decision support system by anesthesiologists was demonstrated in the study to meaningfully improve management of lung ventilation in patients during surgery, it was not associated with improvements in postoperative outcomes, such as complications or length of hospital stay.
Asked about the study’s mixed results, Kheterpal—who is lead author—says he isn’t disappointed. “If we can demonstrate, as we did, that a decision support system actually alters provider decision-making in a positive way—that’s a huge win in 2018 for the role of technology,” he says, adding that “it’s the beginning of the process,” and “now, we’re going to continue pushing into the postoperative area as well.”
Nonetheless, a potential drawback of the system is the number of alerts that it generates. According to the study, there are more than 47 alerts originating from the 250 pieces of information continuously being extracted from the medical records. Further, the authors note that the display also has 48 digital text alerts and two audible alerts—both related to blood pressure.
“My concern is that decision support systems in development may easily include a hundred or more alerts,” wrote Daniel Sessler, MD, chair of the Department of Outcomes Research at the Cleveland Clinic, in an editorial accompanying the study. “Presumably many will be helpful, but others may not. It would, therefore, seem reasonable to expect most decision support systems and alerts to undergo formal testing, just as we would expect any drug or other device to be properly validated.”
Kheterpal says that the way AlertWatch is being used at the University of Michigan does not cause alert fatigue. In fact, he contends that the number of alerts that get “fired off” from the decision support system are very low. “There’s an average of one clinical alert per case when using AlertWatch.”
Kevin Tremper, MD, chair of the University of Michigan’s Department of Anesthesiology and founder of AlertWatch, is co-author of the study and has an equity interest in the Ann Arbor, Mich.-based company.
Register or login for access to this item and much more
All Health Data Management content is archived after seven days.
Community members receive:
- All recent and archived articles
- Conference offers and updates
- A full menu of enewsletter options
- Web seminars, white papers, ebooks
Already have an account? Log In
Don't have an account? Register for Free Unlimited Access