Machine learning achieves 79% accuracy in identifying long QT syndrome

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.