Dr. Ershan Abdullayev during his presentation at RSNA
Photo courtesy of Dr. Ershan Abdullaev
In his presentation at RSNA 2025, Dr. Ershan Abdullayev, head of the radiology department at Sahu Hospital in Baku, explained that AI tools cannot replace cardiac CT scans. “Cardiac CT scan detects calcium Although it provides excellent risk stratification through scoring, patients must be selected for this imaging test. However, thousands of patients undergo routine non-cardiac CT examinations that may contain unreported visible coronary artery calcifications. If these are identified and reported, they could provide life-saving cardiovascular risk information without additional radiation exposure or procedural burden.”
Reclassify patient risk
A retrospective study of 8,547 routine chest CT examinations performed at six academic centers to validate the screening tool identified 2,847 patients with previously unclassified risk and reclassified to a higher category. Of the total, 24.3% had their risk reclassified and 18.2% received an intervention.
Dr. Abdullaev reported that the AI tool achieved excellent diagnostic accuracy with a sensitivity of 94.8% and a specificity of 97.2% in automated CAC scoring across all severity categories. The statistical analysis process, including survival analysis, took 12 seconds to run.6
“Early identification of high-risk asymptomatic patients could represent a paradigm shift towards active population health management using existing imaging infrastructure,” Dr. Abdullayev emphasized. “Early intervention allows timely initiation of evidence-based preventive therapies.”
