Mayo Clinic study uses AI to detect heart rhythm disorder

An artificial intelligence algorithm is able to identify patients with congenital Long QT syndrome using limited electrocardiogram data, according to an abstract published May 10 at the Heart Rhythm Scientific Sessions conference in Boston.

LQTS is a heart rhythm disorder that, if left untreated, puts patients at an increased risk for arrhythmias and sudden cardiac death.

For the study, a team of researchers from Rochester, Minn.-based Mayo Clinic and AliveCor sought to determine whether AI could identify patients with congenital LQTS despite patients having a normal QTc on their EKG.

The researchers applied an AI algorithm that used deep neural networks to patient data from lead I of a 12-lead EKG and evaluated whether the algorithm was able to distinguish between patients with concealed LQTS and those without the condition. The researchers found the deep neural network achieved 79 percent accuracy, along with specificity of 81 percent and sensitivity of 73 percent.

"It is stunning that our 'AI brain' is distinguishing one patient who has a potentially life threatening syndrome, LQTS, but a normal QTc, from a normal patient with the same QTc value by just staring at a single lead," senior author Michael J. Ackerman, MD, PhD, director of the Mayo Clinic Genetic Heart Rhythm Clinic and the Mayo Clinic Windland Smith Rice Sudden Death Genomics Laboratory, said in a May 10 statement.

The research builds on a commitment Mayo Clinic and AliveCor made to explore LQTS detection using in July 2017. AliveCor, which received FDA clearance for its EKG Apple Watch accessory in November 2017, develops personal electrocardiogram technologies that apply machine learning to improve traditional EKG analysis.

More articles on artificial intelligence:
Why Google renamed its research division 'Google AI'
TriHealth to implement IBM Watson Health's imaging tools in $10M deal
'The mind of a mathematician with the heart of a doctor': athenahealth CTO Prakash Khot shares 4 thoughts on AI in healthcare

© Copyright ASC COMMUNICATIONS 2020. Interested in LINKING to or REPRINTING this content? View our policies by clicking here.


Featured Webinars

Featured Whitepapers