– Getty Images for Unsplash +
Artificial intelligence has brought about a revolution in medical screening practices, with the technology able to make detections across hundreds of scans in seconds which can be forwarded to trained pairs of human eyes.
Now from the UK comes another example in the form of heart disease diagnostics. Trained on millions of patients, a new AI tool has been designed to detect minute abnormalities in traditional electrocardiogram (ECG) readings.
Though the ECG, which measures the natural electrical activity in the heart, has been a key part of diagnosing heart attack risk and heart arrhythmia for decades, it isn’t able to detect heart disease.
For heart disease risk, an echocardiogram, or ultrasound reading of the heart is ordered, but appointments are often months later. Now, however, an AI tool has been designed specifically to detect early signs of 2 of the most common forms of heart disease from ECG readings.
Details of the breakthrough, which could boost early diagnosis of heart disease, were presented at the European Society of Cardiology’s annual congress in Munich, the Guardian reports.
“When it comes to the heart, earlier diagnosis and treatment saves and improves lives,” said Dr. Sonya Babu-Narayan, a consultant cardiologist and clinical director of the British Heart Foundation (BHF), which funded the trial.
“Technology like the AI ECG in this research, which has the potential to identify high-risk patients early, will not detect everyone with a heart condition. But it could be a solution to help fast-track the patients who are most likely to have a heart abnormality.”
Heart valve diseases and heart failure are the 2 conditions the AI is capable of detecting in the blink of an eye. Unless one is an experienced cardiologist, the first outwardly visible symptom of heart failure is cardiac arrest or sudden cardiac death.
In a clinical trial for the AI’s potential inclusion in cardiology departments and beyond, 67,000 patients in the US had ECGs they’d received analyzed. The model detected 81% of heart failure cases, and 90% of heart valve disease cases.
AI IN HEALTH: Teens Developed App That Identifies Mouth Cancer–Making Early Diagnosis Easy and Winning $50k for Their School
The ECG is one of the most common tests conducted in cardiology, with approximately a billion ordered every year worldwide. Though a potential case flagged by the AI wouldn’t be proof the patient is about to sustain a heart attack, it’s imagined they’d use the AI-analyzed ECG to receive priority access to echocardiogram appointments.
“Patients can often wait several months for a heart ultrasound scan after being referred for one by their doctor,” said Professor Fu Siong Ng, a professor of cardiology at Imperial College London who was involved in the study.
AI IN WOMEN’S HEALTH: Signs of Breast Cancer Could Be Spotted 3-6 Years Before Diagnosis Using AI Screening, Shows Massive Study
“This makes it exciting that our technology could identify patients most at risk of heart failure and heart valve disease, so they could be prioritized for scans faster and more urgently.”
People may have undergone ECG tests for other reasons, Professor Ng said, and a major benefit of having the AI tool there will be that it can just as easily include potential heart disease checks into any list of diagnostic markers for other conditions, revealing potential heart disease when none was thought to exist.
PUMP This Great News Out Into The Veins Of The Internet…
