EHR-driven PCI risk assessments could make a world of difference
Electronic health record (EHR) data can be used to deliver automated, real-time risk assessments for patients undergoing percutaneous coronary intervention (PCI), according to new findings published in JACC: Advances.[1]
The study’s authors highlighted the many benefits of such a practice. It can promote shared decision-making, for example, and saves cardiologists valuable time.
“PCI facilitates symptom relief among patients presenting with stable ischemic heart disease and improves survival in those presenting with acute coronary syndrome,” wrote first author Mandeep Singh, MD, an interventional cardiologist with Mayo Clinic, and colleagues. “These putative benefits must be weighed against known procedural complications which are largely determined by older age, acute clinical presentation, hemodynamic instability, cardiovascular risk factors, laboratory, and coronary anatomical variables. Risk estimation and its stratification remain the cornerstone to individualize risk estimates and risk models facilitate shared decision-making for patients and clinicians to comprehend risks from medical therapy as compared to revascularization.”
Singh et al. emphasized that risk calculators for PCI are nothing new. However, the use of these resources among heart teams considering PCI remains quite low. The group’s goal was to develop an automated, real-time risk prediction tool that turns existing EHR data into helpful information—all without any extra work from the cardiologists.
Singh and colleagues explored the Mayo Clinic PCI registry, focusing on data from nearly 9,000 PCI procedures. All PCIs were performed from 2016 to 2024, the median age was 70.4 years old and 28.3% were women. The reported rates of in-hospital mortality, bleeding events, acute kidney injury and stroke were 1.8%, 1.8%, 7.6% and 0.5%, respectively. While 70% of the data were used to train the team’s risk prediction model, another 30% were used to test its effectiveness.
Overall, the group found that their real-time risk assessments were both objective and helpful, identifying patients who may face an increased risk if treated with PCI.
“This study demonstrates that electronic tools can be deployed to EHRs to create automated real-time risk calculators to predict complications following PCI,” the authors wrote. “These models may be translated to patient care as an automated and individualized real-time risk calculator obviating the need of manual data entry.”
As an example, the authors detailed the case of a 73-year-old female patient who has experienced an ST-segment elevation myocardial infarction (STEMI). This patient presents with a history of cerebrovascular disease, cardiac arrest and congestive heart failure. EHR data helped the risk prediction model share a real-time assessment with the care team, and then that assessment helped guide the treatment of the patient. Radial access was recommended, for example, and certain medications were avoided to reduce the risk of bleeding.
Click here to read the full study.
Michael has more than 19 years of experience as a professional writer and editor. He has written at length about cardiology, radiology, artificial intelligence and other key healthcare topics.