Deep Learning AI Algorithm Predicts Severe Aortic Stenosis | Technology

Deep Learning AI Algorithm Predicts Severe Aortic Stenosis | Technology
Deep Learning AI Algorithm Predicts Severe Aortic Stenosis 

Deep Learning Artificial Intelligence Algorithm Accurately Predicts Severe Aortic Stenosis 

A machine learning algorithm detected severe aortic stenosis using audio files from a set of patients with similar accuracy to that of board-certified cardiologists, according to findings from a proof-of-concept study.

"Artificial intelligence will be the next technology to help clinicians with standard techniques like auscultation in clinical routine," Heinrich Wieneke, MD, professor and head of the department of cardiology at Elisabeth-Krankenhaus Essen, Germany, told Healio. "The present study demonstrates the concept that AI-assisted auscultation can provide high-level expert results in the detection of aortic stenosis."

Wieneke and colleagues trained a deep neural network on preprocessed audio files from 100 patients with significant aortic stenosis and 100 controls without aortic stenosis and then evaluated its performance on a test data set of 40 patients. The primary outcome measures were sensitivity, specificity, and F1 score. The researchers compared the results of the deep neural network with the performance of 10 cardiologists, 10 residents, and 10 medical students.

READ MORE: Why Artificial Intelligence will usher in a new era of extraordinary potential in the near future | Technology

The findings were published in Clinical Cardiology.

The researchers found that 18% of patients without aortic stenosis and 22% of patients with aortic stenosis had additional moderate or severe mitral regurgitation. The deep neural network showed a sensitivity of 0.9 (95% CI, 0.81-0.99), a specificity of 1, and an F1 score of 0.95 (95% CI, 0.89-1) for the detection of aortic stenosis. 

The investigators calculated an F1 score of 0.94 for cardiologists (95% CI, 0.86-1), 0.88 for residents (95% CI, 0.78-0.98), and 0.88 for students (95% CI, 0.78-0.98). 

READ MORE: Machine Learning helps Rubrik increase Data Security | Technology

"Integrating this technology into an electronic stethoscope could be the next step in upgrading this system for everyday clinical use," Wieneke told Healio. "A stethoscope that indicates a warning in the event of certain valve defects would be conceivable in the foreseeable future."

The researchers noted that few patients with moderate aortic stenosis were included as the study was conducted with data from patients admitted to a tertiary teaching hospital for specialized valve therapy. Patients with other valvular diseases such as hypertrophic obstructive cardiomyopathy were also not included, and few patients with pure mitral regurgitation participated.

READ MORE: Virtual Reality Meditation: Wonder, Avatars, and Psychedelic Designs | Technology

"Thus, the presented algorithm is far from perfect, and this study can only be the first step in introducing artificial intelligence for valvular heart disease into daily clinical practice," the researchers wrote. "On the other hand, it also shows that artificial intelligence can, in principle, be useful in ausculting heart sounds."

Source: Healio News, Direct News 99