Machine learning achieves 79% accuracy in identifying long QT syndrome
AliveCor and Mayo Clinic have utilized machine learning to identify long QT syndrome (LQTS), with findings presented at the Heart Rhythm Scientific Sessions in Boston.
LQTS, which can be a congenital or acquired disorder, causes around 4,000 deaths in children and young adults annually. Identifying patients with LQTS is difficult due to some patients showing normal QTc on in their electrocardiograms (ECGs). In this study, researchers aimed to provide clinicians with a tool in diagnosing the disorder using AI and deep neural networks.
"There can be no better illustration of the importance of our AI to medical science than using it to detect that which is otherwise invisible," said Vic Gundotra, CEO of AliveCor.
By applying AI to data from lead I of a 12-lead ECG, researchers were able to use machine learning to achieve a specificity of 81 percent, sensitivity of 73 percent and an overall accuracy of 79 percent in identifying LQTS patients. Additionally, researchers noted a potential benefit in using AliveCor's KardiaMobile and KardiaBand devices as a mobile detection tool in identifying LQTS.
"Building on our previous work using Mayo Clinic's proprietary T wave fingerprint software, 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," said senior author Michael J. Ackerman, MD, PhD, director of Mayo Clinic's Genetic Heart Rhythm Clinic and the Windland Smith Rice Sudden Death Genomics Laboratory at Mayo Clinic.
Cara joined TriMed Media in 2016 and is currently a Senior Writer for Clinical Innovation & Technology. Originating from Detroit, Michigan, she holds a Bachelors in Health Communications from Grand Valley State University.