Forecasting the Risk of Heart Failure Hospitalization After Acute Coronary Syndromes: the CORALYS HF Score

The present study aimed to identify patients at a higher risk of hospitalization for heart failure (HF) in a population of patients with acute coronary syndrome (ACS) treated with percutaneous coronary revascularization without a history of HF or reduced left ventricular (LV) ejection fraction before the index admission. We performed a Cox regression multivariable analysis with competitive risk and machine learning models on the incideNce and predictOrs of heaRt fAiLure After Acute coronarY Syndrome (CORALYS) registry (NCT04895176), an international and multicenter study including consecutive patients admitted for ACS in 16 European Centers from 2015 to 2020. Of 14,699 patients, 593 (4.0%) were admitted for the development of HF up to 1 year after the index ACS presentation. A total of 2 different data sets were randomly created, 1 for the derivative cohort including 11,626 patients (80%) and 1 for the validation cohort including 3,073 patients (20%). On the Cox regression multivariable analysis, several variables were associated with the risk of HF hospitalization, with reduced renal function, complete revascularization, and LV ejection fraction as the most relevant ones. The area under the curve at 1 year was 0.75 (0.72 to 0.78) in the derivative cohort, whereas on validation, it was 0.72 (0.67 to 0.77). The machine learning analysis showed a slightly inferior performance. In conclusion, in a large cohort of patients with ACS without a history of HF or LV dysfunction before the index event, the CORALYS HF score identified patients at a higher risk of hospitalization for HF using variables easily accessible at discharge. Further approaches to tackle HF development in this high-risk subset of patients are needed.

Impact of Left Ventricular Ejection Fraction on Procedural and Long-Term Outcomes of Bifurcation Percutaneous Coronary Intervention

The association of left ventricular ejection fraction (LVEF) with procedural and long-term outcomes after state-of-the-art percutaneous coronary intervention (PCI) of bifurcation lesions remains unsettled. A total of 5,333 patients who underwent contemporary coronary bifurcation PCI were included in the intercontinental retrospective combined insights from the unified RAIN (veRy thin stents for patients with left mAIn or bifurcatioN in real life) and COBIS (COronary BIfurcation Stenting) III bifurcation registries. Of 5,003 patients (93.8%) with known baseline LVEF, 244 (4.9%) had LVEF <40% (bifurcation with reduced ejection fraction [BIFrEF] group), 430 (8.6%) had LVEF 40% to 49% (bifurcation with mildly reduced ejection fraction [BIFmEF] group) and 4,329 (86.5%) had ejection fraction (EF) ≥50% (bifurcation with preserved ejection fraction [BIFpEF] group). The primary end point was the Kaplan-Meier estimate of major adverse cardiac events (MACEs) (a composite of all-cause death, myocardial infarction, and target vessel revascularization). Patients with BIFrEF had a more complex clinical profile and coronary anatomy. No difference in procedural (30 days) MACE was observed across EF categories, also after adjustment for in-study outcome predictors (BIFrEF vs BIFmEF: adjusted hazard ratio [adj-HR] 1.39, 95% confidence interval [CI] 0.37 to 5.21, p = 0.626; BIFrEF vs BIFpEF: adj-HR 1.11, 95% CI 0.25 to 2.87, p = 0.883; BIFmEF vs BIFpEF: adj-HR 0.81, 95% CI 0.29 to 2.27, p = 0.683). BIFrEF was independently associated with long-term MACE (median follow-up 21 months, interquartile range 10 to 21 months) than both BIFmEF (adj-HR 2.20, 95% CI 1.41 to 3.41, p <0.001) and BIFpEF (adj-HR 1.91, 95% CI 1.41 to 2.60, p <0.001) groups, although no difference was observed between BIFmEF and BIFpEF groups (adj-HR 0.87, 95% CI 0.61 to 1.24, p = 0.449). In conclusion, in patients who underwent PCI of a coronary bifurcation lesion according to contemporary clinical practice, reduced LVEF (<40%), although a strong predictor of long-term MACEs, does not affect procedural outcomes.

A review of machine learning for cardiology

This paper reviews recent cardiology literature and reports how Artificial Intelligence Tools (specifically, Machine Learning techniques) are being used by physicians in the field. Each technique is introduced with enough details to allow the understanding of how it works and its intent, but without delving into details that do not add immediate benefits and require expertise in the field. We specifically focus on the principal Machine Learning based risk scores used in cardiovascular research. After introducing them and summarizing their assumptions and biases, we discuss their merits and shortcomings. We report on how frequently they are adopted in the field and suggest why this is the case based on our expertise in Machine Learning. We complete the analysis by reviewing how corresponding statistical approaches compare with them. Finally, we discuss the main open issues in applying Machine Learning tools to cardiology tasks, also drafting possible future directions. Despite the growing interest in these tools, we argue that there are many still underutilized techniques: while Neural Networks are slowly being incorporated in cardiovascular research, other important techniques such as Semi-Supervised Learning and Federated Learning are still underutilized. The former would allow practitioners to harness the information contained in large datasets that are only partially labeled, while the latter would foster collaboration between institutions allowing building larger and better models.

Machine learning-based prediction of adverse events following an acute coronary syndrome (PRAISE): a modelling study of pooled datasets

BACKGROUND

The accuracy of current prediction tools for ischaemic and bleeding events after an acute coronary syndrome (ACS) remains insufficient for individualised patient management strategies. We developed a machine learning-based risk stratification model to predict all-cause death, recurrent acute myocardial infarction, and major bleeding after ACS.

METHODS

Different machine learning models for the prediction of 1-year post-discharge all-cause death, myocardial infarction, and major bleeding (defined as Bleeding Academic Research Consortium type 3 or 5) were trained on a cohort of 19 826 adult patients with ACS (split into a training cohort [80%] and internal validation cohort [20%]) from the BleeMACS and RENAMI registries, which included patients across several continents. 25 clinical features routinely assessed at discharge were used to inform the models. The best-performing model for each study outcome (the PRAISE score) was tested in an external validation cohort of 3444 patients with ACS pooled from a randomised controlled trial and three prospective registries. Model performance was assessed according to a range of learning metrics including area under the receiver operating characteristic curve (AUC).

FINDINGS

The PRAISE score showed an AUC of 0·82 (95% CI 0·78-0·85) in the internal validation cohort and 0·92 (0·90-0·93) in the external validation cohort for 1-year all-cause death; an AUC of 0·74 (0·70-0·78) in the internal validation cohort and 0·81 (0·76-0·85) in the external validation cohort for 1-year myocardial infarction; and an AUC of 0·70 (0·66-0·75) in the internal validation cohort and 0·86 (0·82-0·89) in the external validation cohort for 1-year major bleeding.

INTERPRETATION

A machine learning-based approach for the identification of predictors of events after an ACS is feasible and effective. The PRAISE score showed accurate discriminative capabilities for the prediction of all-cause death, myocardial infarction, and major bleeding, and might be useful to guide clinical decision making.

FUNDING

None.