Key result
A novel machine-learning model predicted target lesion failure in post-stent patients with a true positive rate of 52.76% and true negative rate of 90.23%, outperforming five state-of-the-art models.
Why the study?
Predicting post-intervention target lesion failure months before its onset remains an extremely challenging clinical task.
Does a novel machine-learning model accurately predict target lesion failure in patients after coronary artery stent implantation?
Cohort (n=1,975)
Yes
Does a novel machine-learning model accurately predict target lesion failure in patients after coronary artery stent implantation?
A novel machine-learning model demonstrates improved prediction of target lesion failure up to five years post-stent implantation compared to existing models.
May aid post-stent risk stratification; leaves open prospective validation before clinical use.
The main intervention for coronary artery disease is stent implantation. We aim to predict post-intervention target lesion failure (TLF) months before its onset, an extremely challenging task in clinics. This post-intervention decision support tool helps physicians to identify at-risk patients much earlier and to inform their follow-up care. We developed a novel machine-learning model with three components: a TLF predictor at discharge via a combination of nine conventional models and a super-learner, a risk score predictor for time-to-TLF, and an update function to manage the size of the at-risk cohort. We collected data in a prospective study from 120 medical centers in over 25 countries. All 1975 patients were enrolled during Phase I (2016–2020) and were followed up for five years post-intervention. During Phase I, 151 patients (7.6%) developed TLF, which we used for training. Additionally, 12 patients developed TLF after Phase I (right-censored). Our algorithm successfully classifies 1635 patients as not at risk (TNR = 90.23%) and predicts TLF for 86 patients (TPR = 52.76%), outperforming its training by identifying 33% of the right-censored patients. We also compare our model against five state of the art models, outperforming them all. Our prediction tool is able to optimize for both achieving higher sensitivity and maintaining a reasonable size for the at-risk cohort over time.
No takes yet. Share an insight, caveat, or question.
Pachl et al. (2021) conducted a cohort in Coronary artery disease post-stent implantation (n=1,975). Machine-learning prediction model for target lesion failure vs. Five state-of-the-art models was evaluated on Prediction of target lesion failure (TLF). A novel machine-learning model predicted target lesion failure in post-stent patients with a true positive rate of 52.76% and true negative rate of 90.23%, outperforming five state-of-the-art models.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: