Machine learning-based prediction of 1-year mortality in hypertensive patients undergoing coronary revascularization surgery

Predictive modeling for acute kidney injury after percutaneous coronary intervention in patients with acute coronary syndrome: a machine learning approach

BACKGROUND

Acute kidney injury (AKI) is one of the preventable complications of percutaneous coronary intervention (PCI). This study aimed to develop machine learning (ML) models to predict AKI after PCI in patients with acute coronary syndrome (ACS).

METHODS

This study was conducted at Tehran Heart Center from 2015 to 2020. Several variables were used to design five ML models: Naïve Bayes (NB), Logistic Regression (LR), CatBoost (CB), Multi-layer Perception (MLP), and Random Forest (RF). Feature importance was evaluated with the RF model, CB model, and LR coefficients while SHAP beeswarm plots based on the CB model were also used for deriving the importance of variables in the population using pre-procedural variables and all variables. Sensitivity, specificity, and the area under the receiver operating characteristics curve (ROC-AUC) were used as the evaluation measures.

RESULTS

A total of 4592 patients were included, and 646 (14.1%) experienced AKI. The train data consisted of 3672 and the test data included 920 cases. The patient population had a mean age of 65.6 ± 11.2 years and 73.1% male predominance. Notably, left ventricular ejection fraction (LVEF) and fasting plasma glucose (FPG) had the highest feature importance when training the RF model on only pre-procedural features. SHAP plots for all features demonstrated LVEF and age as the top features. With pre-procedural variables only, CB had the highest AUC for the prediction of AKI (AUC 0.755, 95% CI 0.713 to 0.797), while RF had the highest sensitivity (75.9%) and MLP had the highest specificity (64.35%). However, when considering pre-procedural, procedural, and post-procedural features, RF outperformed other models (AUC: 0.775). In this analysis, CB achieved the highest sensitivity (82.95%) and NB had the highest specificity (82.93%).

CONCLUSION

Our analyses showed that ML models can predict AKI with acceptable performance. This has potential clinical utility for assessing the individualized risk of AKI in ACS patients undergoing PCI. Additionally, the identified features in the models may aid in mitigating these risk factors.

The prognostic role of the low and very low baseline LDL-C level in outcomes of patients with cardiac revascularization; comparative registry-based cohort design

BACKGROUND

Although low-density lipoprotein-cholesterol (LDL-C) level is considered one of the main prognostic factors in patients with coronary artery bypass grafting (CABG), the question about "the lower the better" is still unanswered. We aimed to evaluate and compare the outcomes of patients with CABG and low or very low baseline LDL-C, regardless of statin usage.

METHODS

In this registry-based cohort study, 10,218 patients with low/very low (70-100 and ≤ 70 mg/dL) baseline LDL-C who underwent isolated and the first-time CABG without known previous history of cardio-cerebrovascular events, were included and compared. The median follow-up was 73.33 (72.15-74.51) months. Primary outcomes were all-cause mortality and major adverse cardio-cerebrovascular events (MACCE) (consisted of all-cause mortality, acute coronary syndrome, stroke or transient ischemic attack, and the need for repeat revascularization [percutaneous coronary intervention or redo-CABG]). Cox regression analyses before and after the propensity score matching (PSM) model were applied to evaluate and compare outcomes.

RESULTS

The mean age of the study population was 66.17 ± 9.98 years old and 2506 (24.5%) were women. Diabetes mellitus and a history of cigarette smoking were significantly higher in the very low LDL group (P-value ≤ 0.001). In Cox regression analyses before applying PSM model, both all-cause mortality (14.2% vs. 11.9%, P-value = 0.004 and MACCE (26.0% vs. 23.6%, P-value = 0.006) were significantly higher in the very low LDL group compared to low LDL. However, these results were no longer significant after applying the PSM model (all-cause mortality HR: 1.115 [95% CI: 0.986-1.262], P = 0.083 and MACCE HR: 1.077 [95%CI: 0.984-1.177], P = 0.095). The sensitivity analysis to remove the statin effect demonstrated that very low LDL-C level was correlated to higher risk of all-cause mortality in both unmatched and PSM analyses.

CONCLUSION

Very low serum LDL-C levels (≤ 70 mg/dl) could increase long-term all-cause mortality and cardiovascular events in patients who have undergone isolated CABG.