Key result
CT-FFR ≤0.80 is linked to ~8.2-fold higher odds of major cardiovascular events.
Why the study?
The predictive value of AI-based FAI combined with CT-FFR for MACE in hyperuricemia patients with concomitant coronary artery stenosis required evaluation.
Does combining AI-based pericoronary fat attenuation index (MAX-FAI) with CT fractional flow reserve (CT-FFR) improve the prediction of major adverse cardiovascular events (MACE) in patients with hyperuricemia and concomitant coronary artery stenosis?
Cohort (n=201)
No
Does combining AI-based pericoronary fat attenuation index (MAX-FAI) with CT fractional flow reserve (CT-FFR) improve the prediction of major adverse cardiovascular events (MACE) in patients with hyperuricemia and concomitant coronary artery stenosis?
Combining AI-derived pericoronary fat attenuation index (MAX-FAI) and CT-FFR from routine CCTA significantly improves MACE risk prediction (AUC 0.950) in patients with hyperuricemia and coronary artery stenosis compared to individual imaging markers.
Answers are grounded in this paper and cite their sources.
May aid MACE stratification in hyperuricemia with stenosis; leaves open prospective validation before clinical adoption.
Background This study explores the evaluation and predictive value of AI based FAI combined with CT-FFR for adverse cardiovascular events (MACE) in hyperuricemia patients with concomitant coronary artery stenosis. Methods A retrospective collection was conducted on 201 patients with hyperuricemia who were proposed diagnosis with coronary heart disease and had coronary artery stenosis detected by coronary CTA (CCTA) in our hospital from January 2021 to October 2025. According to the occurrence of MACE, they were divided into MACE group (n = 52) and non MACE group (n = 149). Measure, record, and compare the differences in relevant clinical baseline data between two groups. Use univariate and multivariate logistic regression analysis to identify the risk factors for MACE in patients with coronary artery stenosis and hyperuricemia. Compare the levels of coronary FAI and CT-FFR in hyperuricemia patients with different grades of coronary artery stenosis and plaque properties. Using receiver operating characteristic (ROC) curves to evaluate the diagnostic predictive value of various indicators and joint models, constructing nomogram, and analyzing and evaluating the predictive performance of the model using calibration curves and decision curves (DCA). Results The grading of coronary artery stenosis, plaque properties, CT-FFR, and MAX-FAI were identified as risk factors for MACE in patients with coronary artery stenosis combine hyperuricemia (P < 0.05); The overall differences in MAX-FAI and CT-FFR between hyperuricemia patients with different grades of coronary artery stenosis were statistically significant (P < 0.05). The more severe the vascular stenosis, the higher the MAX-FAI level and the lower the CT-FFR level; The overall difference in MAX-FAI among hyperuricemia patients with different plaque properties was statistically significant (P < 0.05), with mixed plaque patients having the highest MAX-FAI, while CT-FFR showed no significant difference among different plaque properties. The ROC curve analysis of various indicators and combined models showed that the AUC of coronary artery stenosis grading, plaque properties, CT-FFR, MAX-FAI, and CT-FFR combined with MAX-FAI for predicting MACE were 0.852, 0.836, 0.736, 0.924, and 0.950, respectively. The diagnostic efficacy of CT-FFR combined with MAX-FAI for MACE was better than using any indicator alone. The constructed nomogram model can intuitively and individualize the assessment of MACE risk in patients, and the decision curve shows that the model can provide higher clinical net benefits within a threshold probability range of about 0% -60%. Conclusion The grading of coronary artery stenosis, plaque characteristics, CT-FFR, and MAX-FAI represent risk factors for major adverse cardiovascular events (MACE) in patients suffering from both coronary artery stenosis and hyperuricemia. The integration of CT-FFR and MAX-FAI significantly enhances the predictive capacity for MACE. The nomogram model, constructed based on the aforementioned imaging features, demonstrates reliable calibration and offers a stable clinical net benefit, thereby serving as a noninvasive imaging tool for prognostic evaluation in this high-risk cohort and providing a valuable reference for precise prevention and treatment strategies.
No takes yet. Share an insight, caveat, or question.
Li et al. (2026) conducted a cohort in Hyperuricemia with concomitant coronary artery stenosis (n=201). AI-based MAX-FAI combined with CT-FFR vs. Single imaging indicators (CT-FFR or MAX-FAI alone) / non-MACE group was evaluated on Major adverse cardiovascular events (MACE: cardiac death, non-fatal myocardial infarction, unstable angina requiring coronary revascularization, or recurrent hospitalization due to unstable angina) (OR 8.170, 95% CI 1.750-49.930, p=0.012). AI-based CT-FFR combined with MAX-FAI predicted major cardiovascular events with an AUC of 0.950, with both CT-FFR ≤0.80 and MAX-FAI serving as independent risk factors.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: