Key result
AKE machine learning model improves post-PCI restenosis prediction over CoxPH with ~0.73 C-index.
Why the study?
In-stent restenosis remains a significant adverse event after PCI, and machine learning offers advantages in integrating multi-dimensional features like quantitative flow ratio and radial wall strain to improve risk stratification accuracy.
Does a machine learning-based survival model integrating quantitative flow ratio and radial wall strain improve the prediction of angiographically confirmed in-stent restenosis compared to a conventional Cox proportional hazards model in adult patients undergoing percutaneous coronary intervention?
Cohort (n=363)
Does a machine learning-based survival model integrating quantitative flow ratio and radial wall strain improve the prediction of angiographically confirmed in-stent restenosis compared to a conventional Cox proportional hazards model in adult patients undergoing percutaneous coronary intervention?
An AKE machine learning survival model integrating quantitative flow ratio and radial wall strain parameters outperforms conventional Cox regression in predicting in-stent restenosis after PCI.
ISR incidence signals ongoing post-PCI risk; ML models with QFR and RWS extend prediction but leave open prospective validation.
Background In-stent restenosis (ISR) remains a significant adverse event following percutaneous coronary intervention (PCI). Quantitative flow ratio (QFR) and radial wall strain (RWS) provide functional and mechanical assessments of coronary lesions. Machine learning (ML) offers advantages in integrating multi-dimensional features to improve the accuracy of ISR risk stratification. Purpose To develop and validate ML-based survival models for predicting the risk of ISR following PCI, and to compare their performance. Methods Consecutive adult patients who underwent PCI were enrolled. The primary endpoint was angiographically confirmed ISR during follow-up. Clinical, laboratory, lesion characteristics, and procedural variables were recorded. Key variables included pre-stent and post-stent QFR measurements (e.g., QFR, △QFR, △QFR/stent length (mm), maximum percentage diameter stenosis (Max%DS)), the Lu-index (residual QFR/residual length), and QFR and RWS measurements (e.g., distal △QFR, distal Max%DS, distal RWS, distal RWS%) within 5 mm from the stent edges. Eleven machine learning algorithms (including AKE, random survival forest, XGBoost, LightGBM, and DeepSurv) and a Cox proportional hazards (CoxPH) model were employed. The dataset was randomly split into training (70%) and testing (30%) sets. Model performance was evaluated using the concordance index (C-index), integrated Brier score, and time-dependent receiver operating characteristic curves (time-ROC). Time-dependent feature importance plots were used to interpret predictor contributions over time. Results A total of 363 patients (mean age 63.5 years, 63.74% male) were included. During a median follow-up of 1.44 years, 131 cases (36.09%) of ISR were observed. Following feature selection, eight key predictors were retained, namely post-stent QFR, △QFR, stent length, Max%DS, distal RWS, distal RWS%, △QFR/stent length (mm), and the Lu-index. In the testing set, the AKE model demonstrated superior discriminative performance (C-index: 0.730, 95% CI: 0.680-0.780) compared to the CoxPH model (C-index: 0.645, 95% CI: 0.595-0.695). The AKE model also achieved a lower integrated Brier score (0.256 vs. 0.274) and a time-dependent AUC of 0.741 (95% CI: 0.639-0.840) at 3 years. Time-dependent analysis identified distal RWS%, stent length, and the Lu-index as the most consistently important predictors for ISR risk. Conclusion The AKE machine learning model effectively predicts the risk of ISR in post-PCI patients and outperforms the conventional Cox regression model. This model shows potential as a precise risk stratification tool to support clinical decision-making.
No takes yet. Share an insight, caveat, or question.
Lu et al. (2026) conducted a cohort in In-stent restenosis after percutaneous coronary intervention (n=363). AKE machine learning survival model integrating QFR and radial wall strain vs. Cox proportional hazards (CoxPH) model was evaluated on Angiographically confirmed in-stent restenosis (ISR) (C-index 0.730, 95% CI 0.680-0.780). The AKE machine learning survival model integrating QFR outperformed the CoxPH model in predicting post-PCI in-stent restenosis (C-index 0.730, 95% CI 0.680-0.780 vs 0.645, 95% CI 0.595-0.695).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: