App predicts hernia risk for abdominal surgery patients
Using electronic health record data, researchers at the University of Pennsylvania’s Perelman School of Medicine have developed an app that generates a real-time risk score for each patient.
The tool, which was validated based on data from nearly 30,000 patients, calculates the likelihood that a patient will develop an incisional hernia—which can occur following abdominal surgery at the site of the surgical wound when the contents of the abdomen can push through the muscle.
“Our tool presents the risk for each case at the point of care, giving surgeons and patients the chance to consider this outcome ahead of time and incorporate data into the decision-making process,” said John P. Fischer, MD, an assistant professor of plastic surgery, who presented the app at last week’s American Surgical Association annual meeting in Dallas.
The app, which generates a real-time risk score for patients, has “proven to be remarkably strong” when it comes to its making accurate predictions, according to Penn.
“Reliability is a measure for which 0.5 is a coin flip and a 1.0 is a certainty,” states Penn’s announcement. “This model scores as high as 0.89.”
By analyzing the electronic health records of 29,739 patients undergoing intra-abdominal, urologic or gynecologic surgery at Penn, Fischer and his team identified risk factors that made a patient more likely to develop an incisional hernia.
According to their analysis, the most common risk to patients was a history of abdominal surgery, which increased the likelihood of hernia to 87.5 percent of cases. It was followed by a history of smoking and a recent infection, for which the likelihood was 75 percent for both.
Fischer’s team also discovered from the EHR data that more than 1,100 of the patients (3.8 percent) subsequently needed a second surgery after the primary operation to repair the incisional hernias.
Not surprisingly, the Penn researchers estimate that care related to incisional hernias costs the U.S. healthcare system about $7.3 billion annually.