PCI Risk Calculator

This app predicts an individual’s risk of major complications after stent placement/PCI to support shared decision-making between care providers and patients, using statistical models developed with machine learning. When a person has one or more blocked arteries, physicians may choose to conduct a minimally invasive procedure called a percutaneous coronary intervention, or PCI. By inflating a balloon and potentially placing a stent, blood can flow more freely from the heart. While this carries fewer risks than open surgery, stenting and balloon angioplasty can result in complications like bleeding and kidney injury. The risks for patients undergoing PCI vary greatly depending on the individual patient, and both patients and clinicians have historically both over and underestimated the harms associated with PCI. Precise risk prediction is critical to treatment selection and the shared decision-making process. Researchers at Michigan Medicine, with support from the Pulse Heart Institute and Multicare Health System in Tacoma Washington and The Foundation for Health Care Quality and Department of Health Systems and Population Health in Seattle, developed an AI-driven algorithm that accurately predicts death and complications after PCI. This algorithm has been developed into an interactive tool for clinicians and patients as they determine treatment for blocked heart arteries. The data for this tool was sourced from the Blue Cross Blue Shield of Michigan Cardiovascular Consortium (BMC2) and patients from BMC2’s PCI Patient Advisory Council provided input toward the app’s creation. The risk prediction model was developed using the machine learning software “XGBoost”. Physicians and patients work together to enter the patient’s personal health history and receive individualized information about risk of mortality, transfusion, stroke, acute kidney injury, new dialysis, or major bleeding. The app’s data visualization will help patients better understand their risks.