Machine learning in cardiac CT could be useful—if clinicians put aside their skepticism

Machine learning in cardiovascular CT has the potential to improve disease diagnosis and predictive models, according to the authors of a new paper, but limitations with its applications still remain.

Writing in the Journal of Cardiovascular Computed Tomography, James K. Min, MD, and colleagues said machine learning-based algorithms are proficient in quantifying epicardial fat, which they believe could be added to patient risk assessments. In addition, algorithms using data from coronary CT angiography could help to accurately characterize coronary artery plaque, they noted.

However, the authors pointed out machine learning calculations are often difficult for clinicians to decipher, leaving them hesitant to believe in—and act upon—their feedback.

“While ML algorithms are capable of accurately predicting an outcome, computers are not able, or not programmed, to logically and comprehensively translate the complex and often abstract calculations leading to the prediction back to its user,” Min and coauthors wrote. “The use of these complex systems makes it difficult to explain the origin and logic behind the predictions that are made.”

Read more from Health Imaging below:

""

Daniel joined TriMed’s Chicago editorial team in 2017 as a Cardiovascular Business writer. He previously worked as a writer for daily newspapers in North Dakota and Indiana.

Around the web

Eleven medical societies have signed on to a consensus statement aimed at standardizing imaging for suspected cardiovascular infections.

Kate Hanneman, MD, explains why many vendors and hospitals want to lower radiology's impact on the environment. "Taking steps to reduce the carbon footprint in healthcare isn’t just an opportunity," she said. "It’s also a responsibility."

Philips introduced a new CT system at ECR aimed at the rapidly growing cardiac CT market, incorporating numerous AI features to optimize workflow and image quality.

Trimed Popup
Trimed Popup