News | EP Lab | July 29, 2021

Human ECG Monitoring Outperforms AI Dependent Remote Cardiac Monitoring

Results show ECG monitor is more than 200% more effective in detecting arrhythmias

The devices compared in the study were the Bardy Carnation Ambulatory Monitor long-term continuous ECG system (left) and the BioGuardian MCT cardiac event monitor (right).  #HRS21 #HRS2021 #HeartRhythm21

The devices compared in the study were the Bardy Carnation Ambulatory Monitor long-term continuous ECG system (left) and the BioGuardian MCT cardiac event monitor (right). 

July 29, 2021 – Results from a new clinical trial found human-oversight dependent continuous electrocardiography (ECG) monitors to more accurately detect significant arrhythmias than artificial intelligence (AI) algorithm-dependent mobile cardiac telemetry (MCT). The study showed there was a 209% increase in detection when humans evaluated the monitoring as compared to algorithmic monitoring to flag events. Findings from this clinical trial were presented today as late-breaking science during Heart Rhythm 2021, the annual meeting for the Heart Rhythm Society (HRS).

The devices compared were the Preventice BioGuardian MCT cardiac event monitor and the Bardy Carnation Ambulatory Monitor long-term continuous ECG system. The BioGuardian uses real-time transmission of data and uses an algorithmic-based detection system to capture arrhythmias and human interpretation of these captured arrhythmias. The Bardy system uses a human-based detection and interpretation system, and has supplemental algorithmic review. 

“Reports received from cardiac monitors greatly impact and influence clinical decisions, so accurate readings are crucial," said lead author Mark Willcox, M.D., Alaska Heart and Vascular Institute. "Because every cardiac monitor employs different reporting methods to process recorded rhythms, it can be challenging for the physicians receiving and interpreting the final report. Our study set out to better understand the accuracy between two common options. We found technology, paired with key human oversight and input, proved to be the most accurate in detecting critical arrhythmias and, ultimately, helping to improve patient outcomes.”

Cardiac arrhythmias occur when the electrical impulses that coordinate heartbeats do not work properly, which can lead to serious health issues like stroke and sudden cardiac death. In order to better identify and diagnose arrhythmias, ECG monitors and MCT allow physicians to evaluate cardiac rhythm for an extended period of time in outpatient settings.[1] 

Today, a variety of FDA-approved cardiac monitors are available, yet each differ in how the data is reviewed. Initial patient data from these monitors are interpreted by the manufacturers and third-party independent diagnostic and testing facilities before they are shared with the ordering physician for review. This study compares the accuracy of human-oversight dependent continuous ECG monitoring with algorithm-dependent MCT.

This study was conducted in an outpatient arrhythmia clinic and enrolled 50 sequential patients who simultaneously wore both a MCT and a long-term continuous ECG monitor. Of the 50 enrolled patients, four failed to wear both monitors simultaneously and were excluded from the study. Patients wore both monitors simultaneously for at least some time period (range: 1.2 - 14.8 days). Each study and its associated report were reviewed by two electrophysiologists and were categorized based on whether significant clinical arrythmias were identified and correctly diagnosed.

During the simultaneous recording, significant arrhythmias were diagnosed by MCT in 11/46 patients (24%) compared to 23/46 patients by the long-term continuous ECG monitoring, a 209% increase (p=0.018). In addition, in 12 of the 46 patients (26%), a significant arrhythmia finding was missed by MCT, but was captured by long-term ECG. In two patients, AV node re-entrant tachycardia, captured by long-term ECG, was missed by MCT. In three patients, second degree AV block was unreported by MCT, but captured by long-term continuous ECG monitoring. In 7/46 (15%), VT was reported by MCT, compared to 13/46 (28%) patients by long-term continuous ECG monitoring. Atrial fibrillation was documented by both types of monitors in two patients, however, long-term continuous ECG monitoring captured four additional AF episodes missed by MCT.

The authors hope the results of their study will lead to further conversation into the approval process for monitoring devices and how to ensure reporting accuracy among available monitors. 

The presentation took place in the session “Late-Breaking Clinical Trials 2: Innovations: Continuous ECG Monitoring Versus Mobile Telemetry: A Comparison Of Arrhythmia Diagnostics Between Human And Algorithm Dependent Systems.” 

Find additional HRS 2021 late-breaking trials

Find more EP device news

Find more HRS 2021 conference news

 

Reference:

1. Bansal A, Joshi R. Portable out-of-hospital electrocardiography: A review of current technologies. J Arrhythm. 2018;34(2):129-138. Published 2018 Feb 23. doi:10.1002/joa3.12035.

Related Content

An example of artificial intelligence on the GE Healthcare Vivid E95 system shown at ASE 2019 where the AI automatically pulls in an exam, identifies the left ventricle and myocardial boards and then calculates all the strain measurements in less than 10 seconds. While AI automation can greatly speed workflow, there are questions about the accuracy of AI for the next step in making diagnoses.  #ASE #ASE21 #ASE2021 #AI

An example of artificial intelligence on the GE Healthcare Vivid E95 system shown at ASE 2019 where the AI automatically pulls in an exam, identifies the left ventricle and myocardial boards and then calculates all the strain measurements in less than 10 seconds. While AI automation can greatly speed workflow, there are questions about the accuracy of AI for the next step in making diagnoses. 

Feature | Artificial Intelligence | September 08, 2021 | By Dave Fornell, Editor
Artificial intelligence is becoming best practice to support clinical decisions and help standardize echocardiography analysis for practices. AI, trained on millions of outcome-based data, can provide automation for operators to obtain highly accurate and precise measurements, to better detect and predict cardiovascular disease.
Webinar | Artificial Intelligence | August 12, 2021
Artificial intelligence is becoming best practice to support clinical decisions and help standardize echocardiography
An example of Viz.AI's pulmonary embolism AI application and mobile alert to the physician on-call. Viz.AI and Avicenna.AI Partner to Launch Artificial Intelligence Care Coordination for Pulmonary Embolism and Aortic Disease

An example of Viz.AI's pulmonary embolism AI application and mobile alert to the physician on-call.

News | Artificial Intelligence | July 21, 2021
July 21, 2021 — Artificial int...
Circle Cardiovascular Imaging Partners With DiA Imaging Analysis to Deliver AI-Based Cardiovascular Imaging Solutions
News | Artificial Intelligence | June 28, 2021
June 28, 2021 — Circle Cardiovascular Imaging Inc. and DiA Imaging Analysis Ltd.
Point of care ultrasound, POCUS, combined with artificial intelligence, can help improve echo image quality by inexperienced sonographers.

Getty Images

News | Artificial Intelligence | June 25, 2021
June 25, 2021 – COVID-19 changed everything in healthcare, and a benefit from this pandemic was a surge in innovation
GE is integrating artificial intelligence into most of its imaging and information technology software. AI can aid fast critical care decision making. Above left is the vScan Air wireless point-of-care ultrasound system. It integrates AI for immediate, automated assessment of a patient's ejection fraction, right.

GE is integrating artificial intelligence into most of its imaging and information technology software. AI can aid fast critical care decision making. Above left is the vScan Air wireless point-of-care ultrasound system. It integrates AI for immediate, automated assessment of a patient's ejection fraction, right.

Feature | Artificial Intelligence | June 10, 2021
The digital transformation of healthcare is underway, but it will advance further and faster if key stakeholders work
AI Med will present its Virtual Clinical Series: Imaging Built by Clinicians, for Clinicians, June 29-30, 2021.
News | Artificial Intelligence | June 09, 2021
June 9, 2021 — AI Med will present its...