- Shortness of breath can be due to many reasons and determining why someone has it can be challenging for the emergency department physicians
- Electrocardiogram results evaluated with artificial intelligence-based (AI) formula is a rapid and effective method to determine if shortness of breath is due to heart failure and will help assess decreased heart function
- AI-based ECG is better than standard blood tests at identifying both severe and less severe left ventricular systolic dysfunction in both men and women alike
A routine electrocardiogram (ECG or EKG) enhanced by artificial intelligence (AI) is better than standard blood tests at determining if the cause is heart failure when people seek emergency care for shortness of breath. The findings are published in Circulation: Arrhythmia and Electrophysiology, an American Heart Association journal.
Around 1.2 billion people visit the emergency department every year due to shortness of breath. Shortness of breath is also a hallmark symptom of COVID-19 infection, and the number of people complaining about shortness of breath is also higher.
According to the lead study author DemiladeAdedinsewo, M.D., M.P.H.,"Determining why someone has shortness of breath is challenging for emergency department physicians, and this AI-enabled ECG provides a rapid and effective method to screen these patients for left ventricular systolic dysfunction."Adedinsewo is also a chief fellow in the division of cardiovascular medicine at Mayo Clinic in Jacksonville, Florida.
When emergency department physicians suspect cardiac abnormalities, an ECG which is a quick, 10-second recording of the heart's electrical activity is performed. "An abnormal ECG raises concern about underlying cardiac abnormalities but are not specific for heart failure,"Adedinsewo said.
Standard blood tests are also done to assess the blood levels of natriuretic peptides. Elevated natriuretic peptides is a biomarker of heart failure. But its levels are also affected by obesity, age, kidney disease, severe infection, high blood pressure in the vessels that bring blood to the lungs (pulmonary hypertension), abnormal heart rhythms, and a specific heart failure medication.
In order to create AI-enhanced ECG, Mayo researchers trained computers to distinguish between ECG patterns of people diagnosed with LVSD and those without LSVD by using data on thousands of patients. Using AI software application, the standard ECG recordings can be analyzed in about ten seconds, to identify LSVD.
The researchers applied AI-enhancement to the ECGs of 1,606 patients who had visited the emergency department following shortness of breath to identify LVSD. The patients had received an ECG and blood testing, followed by definitive testing using an echocardiogram
Benefits of AI-Enhanced ECGAI-enhanced ECG was better than standard blood tests in identifying which patients have severe LVSD;
The AI-enhanced ECG was also good at identifying patients with less severe but abnormally low pumping ability (50% or less of the blood leaving the heart with each contraction);
While blood test results can be influenced by several factors, AI-enhanced ECG performed just as well in men and women across different age groups.
"AI-enhanced ECGs are quicker and outperform current standard-of-care tests. Our results suggest that high-risk cardiac patients can be identified quicker in the emergency department and provides an opportunity to link them early to appropriate cardiovascular care," Adedinsewo said.
More such prospective rather than retrospective studies are required before this becomes an acceptable practice in emergency and other departments.
- Artificial intelligence-enhanced ECGs may speed heart failure diagnosis and treatment - (https://newsroom.heart.org/news/artificial-intelligence-enhanced-ecgs-may-speed-heart-failure-diagnosis-and-treatment?preview=9c49)