ANN ARBOR, Mich. (Michigan News Source) – Researchers at Michigan Medicine in Ann Arbor have developed an artificial intelligence-powered algorithm designed to predict the diverse risk factors associated with percutaneous coronary intervention (PCI).

PCI is a minimally invasive procedure used to address blocked coronary arteries. Michigan Medicine says in their press release about the procedure that when a person has one or more blocked arteries, providers may choose PCI which involves inflating a balloon and potentially placing a stent so blood can flow more freely from the heart.

MORE NEWS: Building for a Cause: Habitat for Humanity of Kent County Announces Housing Project in Grand Rapids

They say that despite carrying less risk than open (conventional) surgery, stenting and balloon angioplasty can still result in complications like bleeding and kidney injury.

How AI can help doctors and patients.

That’s where their AI innovation comes into play. Their new innovative tool provides both doctors and patients with insights into potential outcomes and risks related to undergoing PCI.

David E. Hamilton, a cardiology fellow at Michigan Medicine and a member of the research team behind the AI risk prediction algorithm, explains that the model integrates various patient factors to generate predicted outcomes.

What information goes into the algorithm?

Are grocery prices impacting your spending habits?

By completing the poll, you agree to receive emails from, occasional offers from our partners and that you've read and agree to our privacy policy and legal statement.

The tool analyzes information such as patients’ characteristics (height, weight, smoking history, etc.), blood pressure, medication history, pre-existing conditions, and employs a machine learning algorithm to synthesize this data.

By leveraging AI technology to analyze patient data, doctors can anticipate patient responses post-hospitalization. That, in turn, should lead to better outcomes and save more lives.

Hamilton also emphasizes the importance of continuously collecting data on patients’ outcomes beyond the hospital stay, recognizing that coronary artery disease persists beyond the hospital environment. He also highlights the user-friendly nature of the tool, enabling both doctors and patients to assess the risks associated with the procedure and make informed decisions about their care.

MORE NEWS: Don’t Feed the Scammers! John Ball Zoo Warns of Online Ticket Scams Ahead of 2024 Season.

Hamilton says, “The risks for patients undergoing percutaneous coronary intervention vary greatly depending on the individual patient, and both patients and clinicians have historically both over and underestimated the harms associated with PCI.”

Risk prediction advises treatment selection.

He goes on to say, “Precise risk prediction is critical to treatment selection and the shared decision-making process. Our 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.”

Michigan Medicine says that while other risk stratification tools have been created to identify risk after PCI, researchers say that many have only had modest accuracy and were made without involving a key party: patients.

Where the data used came from.

The Michigan Medicine team collected data from all adult patients who underwent PCI between April 2018 and the end of 2021 using the Blue Cross Blue Shield of Michigan Cardiovascular Consortium, or BMC2, registry. The consortium consists of hospitals throughout Michigan utilizing collected data to guide quality initiatives and enhance both care and patient results.

Utilizing the gathered data, researchers incorporated over 20 pre-procedural factors, including age, blood pressure, and total cholesterol, to develop a risk prediction model using machine learning software called “XGBoost.”

AI model highly accurate – and easy to use.

 Michigan Medicine explains, “The AI-driven model showed high levels of accuracy at predicting death, major bleeding events and the need for blood transfusion. It outperformed other models that used the same pre-procedural characteristics.”

Senior author Hitinder Gurm, MBBS, interim chief medical officer at U-M Health says, “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.”

He adds, “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.”

The innovative technology has been harnessed into a computer and phone application to allow for free and widespread use.

The results are published in European Heart Journal.