AI-driven CAC screening identified high-risk patients with 9.5% high CAC burden; LDL dropped from 90.2 to 72.9 mg/dL over 1 year with no spontaneous MI recorded.
Does AI-driven opportunistic CAC screening on non-gated chest CT identify high-risk patients and facilitate effective preventive medical interventions?
AI-driven opportunistic CAC screening on routine non-gated chest CT effectively identifies high-risk patients and facilitates targeted medical interventions that significantly improve lipid profiles.
Absolute Event Rate: 0% vs 0%
Abstract Introduction Recent advancements in artificial intelligence (AI) led to the development of automatic Coronary artery calcification (CAC) analysis based on chest CT scans . The aim of this study is to present the 1-year follow-up results of patients diagnosed with a high CAC burden. Methods We prospectively collected CAC analysis performed using a novel propriety AI software applied to non-gated, non-contrast chest CT scans. Patients were categorized into three groups: low CAC 0-99 Agatston unit (AU), moderate CAC 100-399AU, and high CAC ≥ 400 AU. Exclusion criteria included age 75y, prior myocardial infarction (MI), percutaneous coronary intervention (PCI), coronary artery bypass graft (CABG), and life expectancy 2 years. Patients with a high CAC burden were initially evaluated in-person at a dedicated clinic, while those with low to intermediate CAC underwent follow-up through virtual visits. During clinic visits, patients underwent risk factor evaluation and clinical assessment, received appropriate medical treatment, and were referred for additional testing as needed. Results A total of 1705 eligible patients were evaluated for inclusion between January 1, 2023, and February 29, 2024. Of these, 687 (40%) were excluded. Among the 1018 enrolled patients, 92 (9.5%) were classified as having a high CAC burden, 336 (32.8%) as moderate, and 590 (57.7%) as low. Statin prescriptions were verified for all patients. Currently, 1-year follow-up data is available for patients categorized with high CAC burden. Among 23 high CAC patients referred for functional imaging due to anginal symptoms, 6 (6.5%) ultimately required revascularization. There were 10 non-cardiac mortality events (10.9%), 1 stroke (1%), and 2 heart failure hospitalizations (2%). Notably, no spontaneous MI events occurred in high CAC patients managed at the dedicated clinic. LDL levels significantly declined over 1 year, from 90.2±33.2 mg/dL before the CT scan to 72.9±31.8 mg/dL at follow-up (p0.001). Conclusion This ongoing study suggests that routine CAC quantification using AI software on chest CT scans effectively identifies patients at risk for cardiovascular events and non-cardiac mortality. Additionally, medical interventions, such as statin therapy, significantly improve the metabolic profile of high-risk patients. Further follow-up is needed to assess and compare outcomes in patients with low and intermediate CAC.
Aviv et al. (Sat,) reported a other. AI-driven CAC screening identified high-risk patients with 9.5% high CAC burden; LDL dropped from 90.2 to 72.9 mg/dL over 1 year with no spontaneous MI recorded.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: