PR Newswire05.11.18
AliveCor, the developer of artificial intelligence and FDA-cleared personal electrocardiogram (ECG) technology, today an important milestone in its work with Mayo Clinic on Long QT Syndrome (LQTS).
In an abstract published today at the Heart Rhythm Scientific Sessions conference in Boston, investigators from Mayo Clinic presented research showing that artificial intelligence (AI) using deep neural networks can successfully identify patients with congenital LQTS despite having a normal QTc on their electrocardiogram (ECG). As many as 50 percent of patients with genetically confirmed LQTS have a normal QT interval on the standard ECG, so identifying these patients who are at increased risk of arrhythmias and sudden cardiac death is crucial for correct diagnosis and treatment. This is especially critical when patients are exposed to medications with known QT prolonging potential. The deep neural network employed in the study generated an area under the curve of 0.83, with a specificity of 81 percent, sensitivity of 73 percent, and an overall accuracy of 79 percent.
Importantly, the results were achieved by applying AI to data from lead I of a 12-lead ECG, which suggests that AliveCor's KardiaMobile and KardiaBand devices may be useful in the mobile detection of patients with concealed LQTS.
Long QT Syndrome is both a congenital and acquired disorder. The inherited form affects 160,000 people in the U.S., and causes 3,000 to 4,000 sudden deaths in children and young adults annually. The acquired form of LQTS can be caused by nearly 100 FDA-approved medications, such as antibiotics and antidepressants.
"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.
AliveCor and Mayo Clinic formed a partnership in October of 2016, and announced a joint effort to detect LQTS using AI in July of 2017.
"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.
In an abstract published today at the Heart Rhythm Scientific Sessions conference in Boston, investigators from Mayo Clinic presented research showing that artificial intelligence (AI) using deep neural networks can successfully identify patients with congenital LQTS despite having a normal QTc on their electrocardiogram (ECG). As many as 50 percent of patients with genetically confirmed LQTS have a normal QT interval on the standard ECG, so identifying these patients who are at increased risk of arrhythmias and sudden cardiac death is crucial for correct diagnosis and treatment. This is especially critical when patients are exposed to medications with known QT prolonging potential. The deep neural network employed in the study generated an area under the curve of 0.83, with a specificity of 81 percent, sensitivity of 73 percent, and an overall accuracy of 79 percent.
Importantly, the results were achieved by applying AI to data from lead I of a 12-lead ECG, which suggests that AliveCor's KardiaMobile and KardiaBand devices may be useful in the mobile detection of patients with concealed LQTS.
Long QT Syndrome is both a congenital and acquired disorder. The inherited form affects 160,000 people in the U.S., and causes 3,000 to 4,000 sudden deaths in children and young adults annually. The acquired form of LQTS can be caused by nearly 100 FDA-approved medications, such as antibiotics and antidepressants.
"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.
AliveCor and Mayo Clinic formed a partnership in October of 2016, and announced a joint effort to detect LQTS using AI in July of 2017.
"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.
