Machine Learning to Predict Stent Restenosis Based on Daily Demographic, Clinical, and Angiographic Characteristics

The Rise of Open-Sourced Machine Learning in Small and Imbalanced Datasets: Predicting In-Stent Restenosis

“…Only diabetes has previously been used for ISR risk prediction in the PRESTO-1, PRESTO-2, and EVENT risk models. 2,5 The other predictors highlighted in this study could represent novel predictors of post-STEMI PCIeassociated ISR. 1 It is particularly noteworthy to see that the strongest predictors of ISR in the ERT machine-learning model are supported by literature and consistent with our understanding of ISR pathophysiology, involving both neointimal proliferation and neoatherosclerosis.…”

“…4 In this issue of the Canadian Journal of Cardiology, Sampedro-Gómez et al applied various machine-learning algorithms to develop risk models for the prediction of ISR. 5 The authors sought to predict ISR in patients with ST-segment-elevation myocardial infarction (STEMI) undergoing percutaneous coronary intervention (PCI) within the Grupo de Análisis de la Cardiopatía Isquemica Aguda (GRACIA)-3 study population. 5 The GRACIA-3 trial was a 2Â2 randomized, open-label, multicenter trial that compared the efficacy of the paclitaxel-eluting stent with conventional bare-metal stents in patients with STEMI.…”

“…5 The authors sought to predict ISR in patients with ST-segment-elevation myocardial infarction (STEMI) undergoing percutaneous coronary intervention (PCI) within the Grupo de Análisis de la Cardiopatía Isquemica Aguda (GRACIA)-3 study population. 5 The GRACIA-3 trial was a 2Â2 randomized, open-label, multicenter trial that compared the efficacy of the paclitaxel-eluting stent with conventional bare-metal stents in patients with STEMI. 6 ISR was assessed by core laboratoryevalidated coronary angiography at baseline and at 12-month follow-up in all patients.…”

“…The GRACIA-3 population looked at STEMI patients undergoing PCI, which is inherently different from the population of the PRESTO and EVENT studies, which recruited a majority of non-STEMI cases. 2,5 Several key predictors identified by Sampedro-Gómez et al, such as ! 2 coronary vessel disease, post-PCI Thrombolysis in Myocardial Infarction flow, post-PCI thrombus, abnormal platelets count, and elevated total cholesterol, have not been consistently reported in previous models that looked at non-STEMI cases.…”

“…Furthermore, the feature selection approach used in this study could be valuable in other settings to identify other novel predictors of ISR. 1 Because the strongest predictors in this model are readily available in clinical practice, this model can be easily clinically applied to identify the subset of STEMI patients who are at risk for ISR after PCI, 5 prompting more frequent follow-up to rule out the development of ISR.…”