Key result
Multimodal machine learning predicts rapid non-target lesion progression post-PCI with an AUC of ~0.89.
Why the study?
The predictive value of a machine learning method combining coronary CTA plaque features and clinical inflammatory markers for identifying rapid progression of non-target lesions after PCI required investigation.
Does a multimodal fusion machine learning model combining coronary CTA plaque features and clinical inflammatory markers improve the prediction of rapid progression of non-target lesions in post-PCI patients?
Observational (n=331)
Does a multimodal fusion machine learning model combining coronary CTA plaque features and clinical inflammatory markers improve the prediction of rapid progression of non-target lesions in post-PCI patients?
Answers are grounded in this paper and cite their sources.
A multimodal fusion machine learning model integrating coronary CTA plaque features and clinical inflammatory markers predicts rapid progression of non-target lesions after PCI with an AUC of 0.89, significantly outperforming single-modality models.
This study investigates the value of a machine learning method combining coronary computed tomography angiography (CTA plaque features and clinical inflammatory markers for predicting rapid progression of non-target lesions after Percutaneous Coronary Intervention (PCI). A total of 331 post-PCI patients were retrospectively enrolled and divided into rapid progression (n = 78) and non-rapid progression (n = 253) groups based on follow-up CTA. Baseline clinical data, inflammatory markers (hs-CRP, IL-6, neutrophil-to-lymphocyte ratio), and CTA plaque features (low-attenuation plaque, positive remodeling, noncalcified plaque volume) were collected. Patients were randomly split 7:3 into training and validation sets. Least Absolute Shrinkage and Selection Operator regression identified predictors. Logistic regression, inflammation-only, CTA-only, and multimodal fusion models were developed and compared. Least Absolute Shrinkage and Selection Operator regression selected 8 independent predictors: hs-CRP, IL-6, neutrophil-to-lymphocyte ratio, low-attenuation plaque, positive remodeling, noncalcified plaque volume, napkin-ring sign, and diabetes history. In the validation set, the multimodal fusion model achieved an area under the curve of 0.89 (95%CI: 0.83–0.95), outperforming the inflammation-only (0.78), CTA-only (0.83), and Logistic regression (0.72) models (all P < .05). Its accuracy, sensitivity, and specificity were 92.9%, 95.2%, and 92.3%, respectively. The fusion model showed excellent calibration (HL P = .58), the highest net benefit across threshold probabilities of 8% to 35%, and stable performance across subgroups (area under the curve 0.86–0.92). The multimodal fusion machine learning model effectively predicts rapid progression of non-target lesions after PCI, outperforming single-modality models and supporting risk stratification and individualized secondary prevention.
No takes yet. Share an insight, caveat, or question.
Zhangliang Chen (2026) conducted an observational in Rapid progression of non-target lesions after percutaneous coronary intervention (PCI) (n=331). Multimodal fusion machine learning model combining coronary CTA plaque features and clinical inflammatory markers vs. Inflammation-only, CTA-only, and logistic regression models was evaluated on Prediction of rapid progression of non-target lesions after PCI (AUC 0.89, 95% CI 0.83-0.95, p=<0.05). A multimodal fusion machine learning model combining CTA plaque features and inflammatory markers predicted rapid non-target lesion progression post-PCI with an AUC of 0.89.
Synapse has enriched 10 related papers. Consider them for comparative context: