Michigan Medicine researchers have developed an AI tool that accurately predicts complications and death following heart surgery, significantly enhancing patient safety. The tool utilizes data from various factors such as age, blood pressure, cholesterol levels, and more to calculate an individual’s risk score. The researchers designed the AI tool as a user-friendly web and mobile application, making it easily accessible to patients and healthcare providers.
Scientific and technological advancements in the medical field have led to numerous innovative treatments. However, these treatments often come with unintended effects that can be challenging to anticipate, even for experts. The newly created AI program aims to identify potential risks associated with cardiovascular surgery, enabling doctors to make informed decisions about the safest and most effective treatment options for their patients.
The heart surgery AI developed by Michigan Medicine is based on the XGBoost machine learning algorithm. It analyzes data from 20 factors, including age and cholesterol levels, to estimate the risk of percutaneous coronary intervention (PCI). PCI involves the insertion of a tiny balloon or a stent into a blood vessel to improve blood flow, but it can also lead to complications such as bleeding, kidney damage, or even death.
During testing, the researchers used the AI tool on more than 100,000 patients who underwent PCI between 2018 and 2021. The results showed that the tool outperformed other models in predicting outcomes like bleeding. To ensure the tool is patient-friendly and easy to understand, the researchers collaborated with the PCI Patient Advisory Council during the design process.
The web and mobile application created by the researchers allows patients and doctors to access the AI tool anytime and anywhere. By incorporating patient feedback, the program aims to empower individuals to take an active role in their treatment decisions while providing a comprehensive understanding of the potential benefits and risks associated with PCI.
In addition to the heart surgery AI, other researchers are also developing AI tools to predict the likelihood of heart disease and autism. The QUARTZ program utilizes retinal images to diagnose potential heart disease risks by comparing a patient’s eye scan with a database of images from various studies. Another AI algorithm developed in Korea accurately detects childhood autism using retinal photographs, potentially serving as a valuable biomarker for the disorder.
Artificial intelligence has made significant advancements in cardiovascular health and beyond. These innovations enable the early detection of health risks, improve treatment decision-making, and enhance patient safety. As the age of AI continues to advance rapidly, its future impacts on healthcare are expected to be profound.
To learn more about the potential impacts of AI and its applications in various fields, visit Inquirer Tech. For further information about the heart surgery AI tool, refer to the European Heart Journal.
