AUG 13, 2020 10:05 AM PDT

Using Artificial Intelligence to Read Your ECG Results

WRITTEN BY: Jasper Cantrell

An electrocardiogram (ECG) is a tool used to measure the heartbeat using an electrical current. By following the current from 10 electrodes placed around the body, a traditional 12-lead ECG can give a physician an idea about your heart health. However, current analysis methods may not get the most bang for your buck.

The development of machine learning, a form of simple artificial intelligence, has taken many fields by storm. These programs can analyze hard to read or incredibly dense data and identify unique characteristics within those data. For ECGs, the data typically requires expert clinicians using special programs. With machine learning, you could do the same thing, and more, with just the program and an ECG. To this end, a team from the University of Pittsburgh created a machine learning program to analyze ECG results and do it in a way that outperforms trained physicians and produces more expansive results.

Their idea was to not only look at the temporal aspect of the ECG readout (what most programs use) but the spatial as well. Current analytical methods are only reliable in diagnosing ST-elevation myocardial infarction, aka a heart attack. Patients with another condition would continue to lengthy tests and exams before proper diagnosis. This new method can cut out the guesswork, and get a diagnosis with the ECG alone.

Machine learning programs require large datasets, so the team took ECG data from the EMPIRE study between 2013 and 2015. While most other programs used “model” data (aka perfect data) for training and validation, this study focused on using real-world ECG results. The team used three algorithms (logistic regression, gradient boosting machine, and artificial neural network) to train their program. Validation tests showed the resulting model could reliably classify ECG results with more sensitivity than expert clinicians and modern software.

Other groups have developed machine learning programs to analyze ECGs before, but the team is quick to criticize their use of non-real-world data. Their program was developed using real-world ECG readings and had four benefits of note: increased classification strength, integrable into ECG machines, lower expertise requirements, and increased interpretative strength for hard to analyze ECG results.

The study concludes, “In conclusion, using features extracted from only the prehospital 12-lead ECG, we arrived at a generalizable ML model that outperforms both commercial interpretation software and experienced clinician interpretation.”

Sources: Nature Communications, Osmosis

About the Author
  • Hey everyone! My name is Jasper and, considering I am pretty new here to Labroots, I figured I would introduce myself. I received my bachelor’s from the University of California at Riverside back in 2016. I started off my career a few years ago with a job at a University over in New York, before moving over into the industry. I'm happy to be writing content for Labroots, and I hope you enjoy it!
You May Also Like
MAY 20, 2020
Cardiology
Metabolite Responsible for Poor Metabolic Response to Exercise Identified
MAY 20, 2020
Metabolite Responsible for Poor Metabolic Response to Exercise Identified
For some, working out just doesn’t pay off. A recent study published in Cardiovascular Research by the H ...
JUN 04, 2020
Cannabis Sciences
How Does Recent Cannabis Use Affect Your Risk of Stroke?
JUN 04, 2020
How Does Recent Cannabis Use Affect Your Risk of Stroke?
Does cannabis use influence stroke risk? Some research says yes; some says no. These “conflicting results” f ...
JUN 18, 2020
Cardiology
Healthy Eating Habits Lower the Risk of Cardiovascular Disease
JUN 18, 2020
Healthy Eating Habits Lower the Risk of Cardiovascular Disease
The results are in, eat your fruits and vegetables. A truth that society has known for some time, but data now confirms ...
AUG 25, 2020
Cardiology
Doing More with Less: Making the Diagnosis of Heart Damage Easier for Patients
AUG 25, 2020
Doing More with Less: Making the Diagnosis of Heart Damage Easier for Patients
Cardiovascular health can be a tricky thing to diagnose. Sometimes it can be done with simple heart rate and blood press ...
AUG 26, 2020
Technology
Could a Selfie Be The Next Screening Tool for Heart Disease?
AUG 26, 2020
Could a Selfie Be The Next Screening Tool for Heart Disease?
We may soon live in a world where sending a selfie to your doctor can help with diagnosing heart disease—at least ...
SEP 12, 2020
Cardiology
Is Hyperuricemia an Indicator of Aortic Disease?
SEP 12, 2020
Is Hyperuricemia an Indicator of Aortic Disease?
Living in a culture of excess can have its benefits, but also its drawbacks. Diabetes is a common disease that is gettin ...
Loading Comments...