Machine Learning Models for Predicting Coronary In-Stent Restenosis After Percutaneous Coronary Intervention: A Systematic Review and Meta-Analysis Publisher

Summary: Can AI predict stent narrowing? A review found random forests performed well but varied widely across studies; more external testing is needed before clinical use. #Cardiology #MachineLearning

Alizadehasl A ; Davani D N ; Hosseini Jebelli S F ; Zonooz Y A ; Bahramnejad A ; Bastami E A ; Aliabadi A Y ; Amani Beni R ; Darouei B ; Ghaffari A ; Amini Salehi E ; Hashemi S M ; Golkar S ; Najdaghi S
Source: Heliyon Published:2026

Abstract

Background Machine-learning (ML) models are increasingly used to predict coronary in-stent restenosis (ISR), but evidence combines prognostic, diagnostic-radiomics, and image-reconstruction tasks and often lacks uncertainty around area-under-the-curve (AUC) estimates. We conducted a task-aware systematic review and meta-analysis with study-level auditing of AUC provenance. Methods PubMed, Embase, and Scopus were searched through 3 November 2024. Tabular models predicting subsequent coronary ISR after PCI were pooled within model families using logit-AUC random-effects REML, with one estimate per cohort and family. Missing 95% confidence intervals (CIs) were reconstructed using Hanley–McNeil variance and the logit-delta method when validation/test case and non-case counts were available or transparently approximated. Modified Hartung–Knapp and sensitivity analyses assessed robustness; diagnostic radiomics was analyzed separately. Results Twelve studies represented 16,964 nominal participants/observations. Pooled AUCs for subsequent ISR prediction were 0.84 (95% CI 0.67–0.94; I2 = 98.4%) for random forest (RF), 0.74 (0.71–0.77; I2 = 0%) for logistic regression (LR), 0.59 (0.46–0.71; I2 = 23.1%) for support-vector machines, and 0.73 (0.70–0.76; I2 = 0%) for DNN/MLP. The modified Hartung–Knapp RF interval widened to 0.52–0.96. Restricting analysis to independent patient-level cohorts reporting conventional published 95% CIs yielded AUCs of 0.89 (0.54–0.98) for RF and 0.74 (0.70–0.77) for LR. RF subgroup AUCs were 0.91 (0.70–0.98) for DES-only and 0.72 (0.71–0.73) for mixed BMS/DES cohorts. Age and lipid-related variables appeared in 50% of studies. Conclusions RF showed the highest discrimination but substantial instability, whereas LR was more consistent. Prospective external validation is required before algorithm ranking or clinical deployment. © 2026 The Authors.