Lead Investigator: Nan Hu, Florida International University
Title of Proposal Research: Machine learning augmented decision support system for myocardial revascularization treatment plan selection
Vivli Data Request: 9250
Funding Source: None
Potential Conflicts of Interest: None
Summary of the Proposed Research:
Cardiovascular disease (CVD) encompasses a group of conditions that affect the heart and blood vessels, posing a significant health threat worldwide. This category of diseases includes conditions such as coronary artery disease, heart failure, hypertension, and stroke, among others. CVD can lead to serious health complications, disability, and even premature death, making it a critical public health concern. In the United States, CVD remains the leading cause of mortality, contributing to approximately 1 in every 3 deaths. This means that over 800,000 individuals succumb to CVD-related complications annually, highlighting the urgency of effective prevention and treatment strategies.
One of the key treatment options for managing coronary artery disease, a common form of CVD, is coronary revascularization. This procedure aims to improve blood flow to the heart muscle, usually achieved through two main methods. The first is percutaneous coronary intervention (PCI), which is a non-invasive procedure where a thin tube is placed in the blood vessel to open up a blocked section of the arteries. The second is coronary artery bypass grafting (CABG), which is a surgical procedure which takes a blood vessel from another part of the body and attaches it on the artery near the blocked or narrowed area, the blood is then diverted through the new blood vessel.
The selection of the most appropriate revascularization treatment (treatment to improve blood flow) depends on various factors, including the patient’s overall health, the severity and location of coronary artery blockages, which is when an artery is narrowed or blocked and blood cannot flow to the heart as normal, and the presence of comorbidities. Cardiologists and cardiovascular surgeons carefully evaluate these factors to determine whether a patient should undergo PCI, CABG, or a combination of both, tailoring the treatment approach to provide the best possible outcomes for each individual. This decision-making process is crucial in addressing CVD and reducing its impact on the affected population.
The treatment decision making process should adhere to the clinical guidelines (i.e. American College of Cardiology/ American Heart Association/ Society for Cardiovascular Angiography and Interventions for coronary artery revascularization), however, treatment decisions are usually based on factors which are weighed subjectively by the interventional cardiologist and the cardiac surgeon, who may not have the clinical guidelines and patient data readily available. Thus, there is a need for a unified platform containing all the relevant data needed for physicians for efficient data-driven discussions amongst a Heart Team, research studies, or for individual physicians looking to improve patient outcomes. Empowering healthcare providers with both the standard guidelines in addition to precise, AI-based suggestions can support decision making to help select the optimal treatment for every patient, thereby reducing adverse outcomes and saving healthcare utilization costs.
Requested Studies:
Analysis dataset of cardiac catheterization procedures from the Duke Information System for Cardiovascular Care (DISCC) (“ACATHD”)
Data Contributor: Duke University School of Medicine/Duke University Hospital
Study ID: PRO00068333
Sponsor ID: PRO00068333