Newswise — LOS ANGELES (October 27, 2022) — Several recent discoveries show that the accuracy of diagnosing coronary artery disease and predicting patient risk is being improved using artificial intelligence (AI) models developed by scientists in the Department of Artificial Intelligence in Medicine at Cedars-Sinai.
Coronary artery disease affects the arteries that supply the heart muscle with blood. If left untreated, it can lead to a heart attack or other complications such as arrhythmia or heart failure.
The condition, which affects approximately 16.3 million Americans ages 20 and older, is often diagnosed using single photon emission computed tomography (SPECT) and computed tomography (CT) imaging. However, the images generated during the scan are not always easy to read.
“We continue to show that AI can improve the quality of images and reveal more information, allowing for more accurate diagnoses of disease,” said Slomka, who is also a Professor of Medicine and Cardiology and senior author of three studies published recently. published on AI improving cardiac imaging.
Using AI to improve heart imaging
The first study, published in The Journal of Nuclear Medicineuses AI heart imaging technology that helps improve the diagnostic accuracy of SPECT imaging for coronary artery disease through advanced image corrections.
In SPECT imaging, it is important to have attenuation correction, which helps to reduce artifacts in cardiac images, making them easier to read and more accurate. However, it requires an additional CT scan and expensive SPECT/CT hybrid equipment, which is essentially two scanners in one.
While CT attenuation correction has been shown to improve the diagnosis of coronary artery disease, it is currently only performed in a minority of scans due to additional scan time, radiation and limited availability of this expensive technology.
To overcome these obstacles, Slomka and his team developed a deep-learning model called DeepAC to generate corrected SPECT images without the need for expensive hybrid scanners. These images are generated by AI techniques similar to those used to generate ‘deep-fake’ videos and can simulate high-quality images obtained by hybrid SPECT/CT scanners.
The team compared the diagnosis accuracy of coronary artery disease using the uncorrected SPECT images – which are used in most places today – advanced hybrid SPECT/CT images and new AI-corrected images in invisible data from centers never seen in DeepAC. training have been used.
They found that AI created images that were nearly the same quality and offer comparable diagnostic accuracy to those obtained with more expensive scanners.
“This AI model was able to generate split-second DeepAC images on standard computer software and could be easily implemented in clinical workflows as an automatic preprocessing step,” said Slomka.
Predicting Severe Adverse Cardiac Events
In the second study, published in the Journal of American College of Cardiology: Cardiovascular Imagingthe team showed that deep learning AI makes it possible to predict major adverse cardiac events, such as death and heart attacks, directly from SPECT images.
Researchers trained the AI model using a large multinational database spanning five different locations with over 20,000 patient scans. It contained images of cardiac perfusion and movement for each patient.
The AI model includes visual explanations for the doctors, marking the images with the regions that contribute to a high risk of side effects.
“In the first study, we were able to show that AI can be used to make important image corrections without the need for expensive scanners,” says Slomka. “In the second, we show that the existing images can be used in a better way – predicting the patient’s risk of heart attack or death from images, and highlighting the cardiac features that indicate that risk, to better inform clinicians about coronary artery disease.”
“These findings provide principled evidence for how AI can improve clinical diagnostics,” said Sumeet Chugh, MD, director of the Division of Artificial Intelligence in Medicine. “AI-powered improvements to SPECT imaging have the potential to improve the accuracy of coronary artery disease diagnosis while being significantly faster and less expensive than current standards.”
Reducing bias in AI models
The third study, published in the European Journal of Nuclear Medicine and Molecular Imagingdescribes how to train an AI system to perform well in all relevant populations, not just the population that the system was trained to.
Some AI systems are trained using high-risk patient populations, allowing systems to overestimate the likelihood of disease. To ensure that the AI model works accurately for all patients and to reduce any biases, Slomka and his team trained the AI system using simulated variations of patients. This process, called data augmentation, helps to better represent the mix of patients expected to undergo the imaging tests.
They found that the models trained with a balanced mix of patients more accurately predicted the odds of coronary artery disease in women and low-risk patients, potentially leading to less invasive testing and more accurate diagnosis in women.
The models also resulted in fewer false positives, suggesting that the system may be able to reduce the number of tests the patient undergoes to rule out the disease.
“The results suggest that improving training data is critical to ensure that AI predictions better align with the population to which they will be applied in the future,” Slomka said.
The researchers are now evaluating these new AI approaches at Cedars-Sinai and exploring how they can be integrated into clinical software and used in standard patient care.
The research was supported in part by the National Heart, Lung and Blood Institute.
Follow Cedars-Sinai Academic Medicine on Twitter to learn more about Cedars-Sinai’s latest scientific and clinical studies.