AI model may improve detection of atrial septal defect


AIAn artificial intelligence (AI) model may be more efficient at detecting signatures of atrial septal defect (ASD) in electrocardiograms (ECG) than traditional methods.

This is according to investigators from Brigham and Women’s Hospital (Boston, USA) and Keio University (Tokyo, Japan), who have developed a deep learning AI model to screen ECG for signs of ASD.

“If we can deploy our model on a population-level ECG screening, we would be able to pick up many more of these patients before they have irreversible damage,” says Shinichi Goto (Brigham and Women’s Hospital, Boston, USA), corresponding author on the paper published in EClinicalMedicine.

ASD is a common adult congenital heart disease caused by a hole in the heart’s septum that lets blood flow between the left and right atria. The symptoms of ASD are typically very mild or, in many cases, non-existent until later in life. Symptoms include an inability to do strenuous exercise, affect the rate or rhythm of the heartbeat, heart palpitations, and an increased risk of pneumonia.

Even if ASD is asymptomatic, it can increase the risk of atrial fibrillation (AF), stroke, heart failure, and pulmonary hypertension. If found early, ASD can be corrected with minimally invasive surgery to improve life expectancy and reduce complications.

ASD can be detected in several ways, the largest defects can be found by listening to the heart with a stethoscope, use of an echocardiogram, or screening via ECG.

To see if an AI model could better detect ASD from ECG readouts, the study team fed a deep learning model ECG data from 80,947 patients over 18 who underwent both ECG and echocardiogram to detect ASD. A total of 857 patients were diagnosed with ASD.

The data were collected from three hospitals: two large teaching institutions—Brigham and Women’s Hospital and Keio University, and Dokkyo Medical University (Mibu, Japan), a community hospital. The model was then tested using scans from Dokkyo, which has a more general population and is not specifically screening patients for ASD. The model was more sensitive than using known abnormalities found on ECGs to screen for ASD. The model correctly detected ASD 93.7% of the time, while using known abnormalities found ASD 80.6% of the time.

“It picked up much more than what an expert does using known abnormalities to identify cases of ASD,” Goto says.

One limitation of the study is that the model was trained used samples from academic institutions, which deal more with rare diseases like ASD. All the patients used to train the model were being screened for ASD and received an echocardiogram, so it is not clear how well the model would work on a general population, which is why they tested it in Dokkyo.

“The model’s performance was retained even in the community hospital’s general population, which suggests that the model generalises well,” Goto adds.

The authors also note that even the use of echocardiogram to detect ASD will not find every defect. Some could slip through both the regular screening and the AI model, though these smaller defects are less likely to require surgical closure.

“The problem of machine learning is that it is a black box—we do not really know what features it picked up,” Goto says.

Results suggest that the technology could be used in population-level screening to detect ASD before it leads to irreversible heart damage, the researchers claim. ECG is relatively low cost and currently performed in many contexts. “Perhaps this screening could be integrated into an annual PCP appointment or used to screen ECGs taken for other reasons,” Goto adds.


Please enter your comment!
Please enter your name here