News | CT Angiography (CTA) | August 06, 2019

Artificial Intelligence Improves Heart Attack Risk Assessment

Machine learning model trained on coronary CT angiography images predicts risk of cardiovascular event better than CAD-RADS alone

Artificial Intelligence Improves Heart Attack Risk Assessment

August 6, 2019 — When used with a common heart scan, machine learning, a type of artificial intelligence (AI), does better than conventional risk models at predicting heart attacks and other cardiac events, according to a study published in the journal Radiology.

Heart disease is the leading cause of death for both men and women in the United States. Accurate risk assessment is crucial for early interventions including diet, exercise and drugs like cholesterol-lowering statins. However, risk determination is an imperfect science, and popular existing models like the Framingham Risk Score have limitations, as they do not directly consider the condition of the coronary arteries.

Coronary computed tomography arteriography (CCTA), a kind of CT that gives highly detailed images of the heart vessels, is a promising tool for refining risk assessment — so promising that a multidisciplinary working group recently introduced a scoring system for summarizing CCTA results. The decision-making tool, known as the Coronary Artery Disease Reporting and Data System (CAD-RADS), emphasizes stenoses, or blockages and narrowing in the coronary arteries. While CAD-RADS is an important and useful development in the management of cardiac patients, its focus on stenoses may leave out important information about the arteries, according to study lead author Kevin M. Johnson, M.D., associate professor of radiology and biomedical imaging at the Yale School of Medicine in New Haven, Conn.

Read the article "Multi-Society Group Releases CAD-RADS for Standardized Coronary CT Angiography Reporting"

Noting that CCTA shows more than just stenoses, Johnson recently investigated a machine learning (ML) system capable of mining the myriad details in these images for a more comprehensive prognostic picture.

“Starting from the ground up, I took imaging features from the coronary CT,” he said. “Each patient had 64 of these features and I fed them into a machine learning algorithm. The algorithm is able to pull out the patterns in the data and predict that patients with certain patterns are more likely to have an adverse event like a heart attack than patients with other patterns.”

For the study, Johnson and colleagues compared the ML approach with CAD-RADS and other vessel scoring systems in 6,892 patients. They followed the patients for an average of nine years after CCTA. There were 380 deaths from all causes, including 70 from coronary artery disease. In addition, 43 patients reported heart attacks.

Compared to CAD-RADS and other scores, the ML approach better discriminated which patients would have a cardiac event from those who would not. When deciding whether to start statins, the ML score ensured that 93 percent of patients with events would receive the drug, compared with only 69 percent if CAD-RADS were relied on.

“The risk estimate that you get from doing the machine learning version of the model is more accurate than the risk estimate you’re going to get if you rely on CAD-RADS,” Johnson said. “Both methods perform better than just using the Framingham risk estimate. This shows the value of looking at the coronary arteries to better estimate people’s risk.”

If machine learning can improve vessel scoring, it would enhance the contribution of noninvasive imaging to cardiovascular risk assessment. Additionally, the ML-derived vessel scores could be combined with non-imaging risk factors such as age, gender, hypertension and smoking to develop more comprehensive risk models. This would benefit both physicians and patients.

“Once you use a tool like this to help see that someone’s at risk, then you can get the person on statins or get their glucose under control, get them off smoking, get their hypertension controlled, because those are the big, modifiable risk factors,” he said.

Johnson is currently working on a paper that takes results from this study and folds them into the bigger picture with non-imaging risk factors.

“If you add people’s ages and particulars like smoking, diabetes and hypertension, that should increase the overall power of the method and improve the overall results,” he said.

For more information: www.pubs.rsna.org/journal/radiology

Related Content

VIDEO: The Introduction of CAD-RADS

Reference

Johnson K.M., Johnson H.E., Zhao Y., et al. Scoring of Coronary Artery Disease Characteristics on Coronary CT Angiograms by Using Machine Learning. Radiology, June 25, 2019. https://doi.org/10.1148/radiol.2019182061

Related Content

In the light of the coronavirus outbreak, MILabs has enhanced its line of high-performance CT scanners to even better detect the disease #COVID19 #Coronavirus #2019nCoV #Wuhanvirus #SARScov2
News | Computed Tomography (CT) | March 27, 2020
March 27, 2020 — Based on recent scientific research, diagnostic X-ray...
CoronaCare is designed to help healthcare providers track COVID-19 (coronavirus) related symptoms of potentially infected patients. The platform enables communication with patients outside of facility walls and the ability to request the return of high-risk patients for more in-depth care. #COVID19 #Coronavirus #2019nCoV #Wuhanvirus #SARScov2
News | Coronavirus (COVID-19) | March 27, 2020
March 27, 2020 — PaxeraHealth has spent years building and be
AI vendor Infervision's InferRead CT Pneumonia software uses artificial intelligence-assisted diagnosis to improve the overall efficiency of the radiology department. It is being developed in China as a high sensitivity detection aid for novel coronavirus pneumonia (COVID-19). #COVID19 #coronavirus #SARScov2

AI vendor Infervision's InferRead CT Pneumonia software uses artificial intelligence-assisted diagnosis to improve the overall efficiency of the radiology department. It is being developed in China as a high sensitivity detection aid for novel coronavirus pneumonia (COVID-19).

Feature | Coronavirus (COVID-19) | March 27, 2020 | Jilian Liu, M.D., HIMSS Greater China
An older couple walked into the Hubei Provincial Hospital of Integrated Chinese and Western Medicine near their neigh
#COVID19 #Coronavirus #2019nCoV #Wuhanvirus #SARScov2

Typical CT imaging features for COVID-19. Unenhanced, thin-section axial images of the lungs in a 52-year-old man with a positive RT-PCR (A-D) show bilateral, multifocal rounded (asterisks) and peripheral GGO (arrows) with superimposed interlobular septal thickening and visible intralobular lines (“crazy-paving”). Routine screening CT for diagnosis or exclusion of COVID-19 is currently not recommended by most professional organizations or the US Centers for Disease Control and Prevention. Image courtesy of RSNA

News | Coronavirus (COVID-19) | March 26, 2020
March 26, 2020 — The Radiological Society of North America (RSNA
#COVID19 #Coronavirus #2019nCoV #Wuhanvirus #SARScov2
News | Artificial Intelligence | March 24, 2020
March 24, 2020 — Qure.ai, a leading healthcare...