A new web-based tool predicts the risk of post-surgery complications

Heart attack, kidney failure, stroke. These are just a few of the life-threatening complications of patients undergoing surgery. Jefferson researchers now have an easy-to-use web-based tool that predicts the risk of post-surgery complications such as kidney failure and stroke. The medical professional model may help to implement protective measures before emergency intervention is required.

“We need to be able to assess the risk from life-threatening postoperative complications so that we can then come up with ways to reduce those complications,” says Sang Woo, MD, senior. clinical professor of medicine at Thomas Jefferson University led the new research.

The need for better risk prediction models became clear to Dr. Woo after a patient fails in kidney after surgery and needs medical intervention like dialysis. Another patient suffered a stroke after surgery to treat a broken hip and suddenly needed emergency brain surgery.

“Seeing how much these patients had gone through, I wanted to find out what we could have done differently to prevent the complications. that life, “says Dr. Woo.

Risk calculator that doctors are currently heavily assessing for heart risks, such as a heart attack or heart attack. They do not provide risk assessment for other major complications such as stroke, and doctors have paid little attention to risk assessment for renal failure, Dr. Woo says.

“We wanted to help doctors to be able to assess the risk of stroke, as well as traditional risks,” he says.

To develop a prediction model that was accurate and easy for clinicians to use, Dr. Woo drew on experience in big data set analysis and machine learning, and collaborated with a multi- Jefferson disciplines include surgeon, cardiologist, nephrologists and hospitals.

“We often do the research and publish research research that is too complex to translate to the bedside,” Dr. Woo says. “My goal from the beginning was create a new model that is very practical and useful and can be integrated into routine patient care. “

Now, in two recent studies, Dr. Woo and colleagues show that the model effectively predicts the risk of life-threatening, postoperative complications.

In a study published online December 29, 2020 in the research journal Kidney360, Dr. Woo and colleagues developed a model to assess a patient’s risk of developing severe renal injury (AKI) after surgery. AKI is a serious medical issue. More than a third of patients who required dialysis died after heart surgery for example.

“Identifying patients at high risk for AKI and implementing protective measures could reduce that risk of death,” Dr. Woo says.

He and colleagues analyzed data from more than 2.2 million surgical patients, about 7,000 of whom developed AKI that required dialysis. The analysis showed that patients requiring dialysis were older and more likely to have congestive heart failure and diabetes.

The researchers then trained the model with data from more than 1.4 million patients using these and eight other predictors before testing data from another set of more than 800,000 surgical patients. The model accurately predicted which patients would develop AKI.

In a second study published online in the Journal of the American Heart Association on January 30, 2021, Dr. Woo and colleagues used the model to predict the risk of stroke, heart event, or death within 30 days after surgery.

For this version of the model, the researchers analyzed data from more than 1.1 million surgical patients. They used predictors such as age, stroke history, type of surgery and other health factors that could be measured before surgery to construct the model.

They found that the model predicted which patients would suffer a stroke, heart event or die within 30 days of surgery with high accuracy. The predictive power of the model was exceptional, with sub-curve width (AUC) – a standard method of assessing model performance – measuring 0.87 for stroke and 0.92 for mortality. The model also predicts heart risk (AUC 0.87) similar to or better than the widely used heart risk models.

As a web-based tool, the model is easy to use as well. Doctors who perform preoperative assessments can use the device at the patient’s bedside.

The new risk assessment models will benefit clinicians and patients. With the models, clinicians will be able to better inform surgeons about the risks and better consult patients, both of which translate into improved patient care.

“Now that we have a tool to reasonably assess the risk of stroke and renal failure, we are exploring new ways to reduce that risk,” says Dr. Woo.