Source: Geralt/Pixabay
The pattern recognition capabilities of deep learning with artificial intelligence (AI) are rapidly developing potential new ways to detect health risks early. A new study by researchers at Massachusetts General Hospital and the AI in Medicine program at Brigham and Women’s Hospital in Boston shows how an AI deep learning model calculates the 10-year risk of death from stroke or a heart attack using a single Chest X can predict -Ray. The researchers presented their findings at the recent 2022 annual meeting of the Radiological Society of North America (RSNA).
According to statistics from the World Health Organization (WHO), cardiovascular diseases (CVDs) are the leading cause of death worldwide, with an estimated 15.2 million deaths from heart attack and stroke in 2019. Early detection of cardiovascular disease offers the opportunity to potentially save lives Interventions and Treatments. According to the WHO, most cardiovascular diseases can be prevented with changes in behavior and lifestyle, such as improved diet, more exercise and eliminating the harmful use of alcohol and tobacco.
Artificial intelligence in healthcare is expected to grow globally from a market value of $15.4 billion in 2022 to $208.2 billion by 2030, according to a report by Grand, at a compound annual growth rate (CAGR) of 38.4 percent grow View research. Factors contributing to this trend include the increasing acceptance of precision medicine, the emerging importance of medical big data, declining hardware costs and the need to reduce healthcare costs, according to the same report.
Using deep learning for radiology as a tool is a natural fit.
Computer-aided diagnostics (CAD), an earlier form of artificial intelligence, has been used in radiology for many years for applications such as detecting breast cancer in mammography and lung nodules in chest CT scans. Previous CAD software was coded based on domain knowledge. With the advent of AI image processing and large data sets, the latest approach is to use deep learning to learn latent features in image data without hardcoding.
For this study, researchers trained an AI deep learning algorithm called CXR-CVD risk model using over 147,400 chest X-rays from over 40,600 patients at multiple centers for a controlled study of early detection of prostate, lung, colon and and Ovarian Cancer sponsored by the National Cancer Institute.
The algorithm was then evaluated using chest X-rays of a second independent cohort of over 11,400 Mass General Brigham outpatients potentially eligible for statin therapy, with approximately 9.6 percent having a major cardiac event over the mean follow-up of 10.3 years suffered. The researchers compared the predictive values of the AI algorithm with the established clinical standard for deciding on the suitability of statins.
The scientists reported in a statement that their AI deep learning algorithm was able to predict future major adverse cardiovascular events from a single chest X-ray “with similar performance and incremental value to the established clinical standard.”
Copyright © 2022 CamiRosso. All rights reserved.
