Author + information
- Zachi Itzhak Attia,
- Suraj Kapa,
- Francisco Lopez-Jimenez,
- Paul McKie,
- Dorothy Ladewig,
- Gaurav Satam,
- Patricia Pellikka,
- Thomas Munger,
- Samuel Asirvatham,
- Serban Dronca,
- Christopher Scott,
- Rickey Carter and
- Paul Friedman
Asymptomatic left ventricular dysfunction (ALVD) is present in 2-9% of the population, is associated with reduced longevity and is treatable when found. Inexpensive, reliable, in office screening is not available. The area under the curve (AUC) for a BNP screening blood test is 0.79 to 0.89. We hypothesized that use of artificial intelligence (AI) would enable the ECG, a ubiquitous, inexpensive test, to identify ALVD.
We trained a convolutional neural network (Fig) using digitally stored 12 lead ECG and echocardiogram pairs from 44,969 patients from the Mayo Clinic data vault to identify patients with an ejection fraction (EF) <= 35%. The network was then tested on 51,979 patients reserved for external validation.
Of the 51,979 patients tested, 4,064 (8%) had an EF< 35%. The AUC of the ROC was 0.93 (Fig). The sensitivity, specificity and accuracy were 85%, 86% and 86%, respectively. In patients with an abnormal AI screen but normal EF (false positives, 1317), 153 had at least one abnormal EF in the future (5 year incidence 10.1%). This five-fold increased risk of developing a future low EF suggests that the network may be detecting early, subclinical, metabolic or structural abnormalities that manifest in the ECG.
Applying artificial intelligence to the ECG - a ubiquitous, low cost test - permits the ECG to serve as a powerful tool to screen for asymptomatic ventricular dysfunction and furthermore to identify individuals at increased risk for its development in the future.
Moderated Poster Contributions
Arrhythmias and Clinical EP Moderated Poster Theater, Poster Hall, Hall A/B
Monday, March 12, 2018, 1:15 p.m.-1:25 p.m.
Session Title: New Developments in Arrhythmias
Abstract Category: 04. Arrhythmias and Clinical EP: Basic
Presentation Number: 1317M-09
- 2018 American College of Cardiology Foundation