Researchers use radiomics to predict heart attacks

Researchers are using a technique known as radiomics to predict future cardiac events such as heart attacks, according to a study published in Radiology, a journal of the Radiological Society of North America (RSNA). Radiomics allows researchers to extract quantitative, or quantifiable, data from CT images, revealing disease traits that would otherwise be invisible in the images.

Coronary artery disease is associated with fatty plaque deposits that form within the artery walls. Large, lipid-rich plaques are easily ruptured. Most heart attacks are caused by the rupture of these plaques. It is, however, difficult to predict which plaques will rupture. Researchers in China created a radiomics model that assesses plaque vulnerability using information from coronary CT angiography images.

The model was tested on 299 patients. The method was then tested on 708 patients with suspected coronary artery disease.
The model detected vulnerable plaques linked to an increased risk of major adverse cardiac events such as heart attacks. Over a three-year median follow-up, a high radiomic signature was independently associated with these events.

“The results of this study are encouraging and exciting,” said study co-lead author Long Jiang Zhang, M.D., PhD, from the Department of Radiology at Jinling Hospital, Medical School of Nanjing University in Nanjing, China. “Radiomics provided a more accurate approach to detect vulnerable plaques compared to conventional coronary CT angiography anatomical parameters.”

According to Dr. Zhang, the radiomic signature would be simple to incorporate into clinical practise. It could be used in the clinic to assess potentially vulnerable plaques and help stratify high-risk patients.

“If the radiomics analysis is embedded into the routine CT angiography workstation, it can automatically identify vulnerable plaques for clinician review,” Dr Zhang said. “Thus, radiomics may significantly improve the accuracy and precision of high-risk plaque detection in routine clinical practice.”

The researchers intend to create a radiomics model using various scanner types and vendors. A larger, multicenter study with 10,000 patients is also in the works.

“With the support of large observational studies and randomized controlled trials, the radiomics approach may help guide clinical decision-making and improve patient care in the future,” Dr Zhang said.