New AI tool predicts death and complications after heart surgery

If you have a clogged artery, you might need a procedure called percutaneous coronary intervention, or PCI, to clear it up. It involves inserting a tiny balloon or a metal mesh tube called a stent into your blood vessel to improve blood flow to your heart. But PCI is not without risks. Sometimes, it can cause bleeding, kidney damage, or even death.

How can you and your doctor weigh the pros and cons of this treatment? A team of researchers from Michigan Medicine has developed an that can help. It can predict the chances of dying or having complications after PCI with high accuracy. The tool, which is based on a machine learning algorithm called XGBoost, uses data from more than 20 factors, such as your age, blood pressure, and cholesterol levels, to calculate your risk score.

The researchers tested the tool on data from over 100,000 patients who underwent PCI in Michigan between 2018 and 2021. They found that the tool was better than other existing models at predicting outcomes such as death, major bleeding, and blood transfusion. The results were published in the . The tool is not only smart but also patient friendly.

The researchers collaborated with the PCI Patient Advisory Council, a group of patients who have undergone PCI, to design the tool in a way that is easy to understand and use. The tool is available as a and a mobile app, so you can access it anytime, anywhere. “We combined the predictive model with patient feedback from the PCI Patient Advisory Council to transform machine learning into this patient centered, individualized risk prediction tool,” said senior author Hitinder Gurm, MBBS, interim chief medical officer at U M Health.

The tool can help you and your doctor make informed decisions about your treatment. It can also educate you about the potential risks and benefits of PCI. By using the tool, you can have more confidence and control over your health. The researchers hope that the tool will improve the quality and safety of PCI, and ultimately, save lives.

"This AI tool can recognize a wide array of outcomes after PCI and can be used by care providers and patients together to decide the best course of treatment," said David E. Hamilton, M.D., the lead author of the study and a cardiology critical care fellow at Michigan Medicine. "In the age of widespread smartphones and electronic medical records, this computerized risk score could be integrated into electronic health systems and made easy to use at the bedside.

It would not only help relay complex information to the provider quickly but it could also be used to enhance patient education on the risks related to PCI.".