Impact of small and dense low-density lipoprotein (sd-LDL)on contrast-induced acute kidney injury in patients with acute ST-segment elevation myocardial infarction undergoing primary percutaneous coronary intervention

Application of interpretable machine learning algorithms to predict acute kidney injury in patients with cerebral infarction in ICU

BACKGROUND

Acute kidney injury (AKI) is not only a complication but also a serious threat to patients with cerebral infarction (CI). This study aimed to explore the application of interpretable machine learning algorithms in predicting AKI in patients with cerebral infarction.

METHODS

The study included 3920 patients with CI admitted to the Intensive Care Unit and Emergency Medicine of the Central Hospital of Lishui City, Zhejiang Province. Nine machine learning techniques, including XGBoost, logistics, LightGBM, random forest (RF), AdaBoost, GaussianNB (GNB), Multi-Layer Perceptron (MLP), support vector machine (SVM), and k-nearest neighbors (KNN) classification, were used to develop a predictive model for AKI in these patients. SHapley Additive exPlanations (SHAP) analysis provided visual explanations for each patient. Finally, model effectiveness was assessed using metrics such as average precision (AP), sensitivity, specificity, accuracy, F1 score, precision-recall (PR) curve, calibration plot, and decision curve analysis (DCA).

RESULTS

The XGBoost model performed better in the internal validation set and the external validation set, with an AUC of 0.940 and 0.887, respectively. The five most important variables in the model were, in order, glomerular filtration rate, low-density lipoprotein, total cholesterol, hemiplegia and serum kalium.

CONCLUSION

This study demonstrates the potential of interpretable machine learning algorithms in predicting CI patients with AKI.

Prognostic Role of Neutrophil to Lymphocyte Ratio in Contrast-Induced Nephropathy: A Systematic Review and Meta-analysis

This meta-analysis assessed the use of the neutrophil-to-lymphocyte ratio (NLR) as a means of early detection of contrast-induced nephropathy (CIN) following diagnostic or therapeutic procedures. We used Web of Science, PubMed, and Scopus to conduct a systematic search. There was no limitation regarding language or date of publication. We reported standardized mean difference (SMD) with a 95% confidence interval (CI). Due to high heterogeneity, a random-effects model was used, and the Newcastle–Ottawa scale was used for quality assessment. Thirty-one articles were included in the analysis. Patients in the CIN group had elevated levels of NLR compared with those in the non-CIN group (SMD = 0.78, 95% CI = 0.52–1.04, P < .001). Similar results were observed in either prospective (SMD = 1.03, 95% CI = 0.13–1.93, P = .02) or retrospective studies (SMD = 0.70, 95% CI = 0.45–0.96, P < .001). The pooled sensitivity of NLR was 74.02% (95% CI = 66.54%–81.02%), and the pooled specificity was 60.58% (95% CI = 53.94%–66.84%). NLR shows potential as a cost-effective biomarker for predicting CIN associated with contrast-involved treatments. This could help implement timely interventions to mitigate CIN and improve outcomes.

Predictive value of SII and sd-LDL for contrast-induced acute kidney injury in STEMI patients undergoing percutaneous coronary intervention

Aim: To investigate the relationship between the incidence of contrast-induced acute kidney injury (CI-AKI) and the level of small dense low-density lipoprotein (sd-LDL) and systemic immune-inflammation index (SII) in patients with acute ST-segment elevation myocardial infarction (STEMI) undergoing emergency percutaneous coronary intervention (PCI), and to further compare the predictive values of SII, sd-LDL and their combination for CI-AKI. Methods: A total of 674 patients were assigned to a training and a validation cohort according to their chronological sequence. The baseline characteristics of the 450 patients in the training cohort were considered as candidate univariate predictors of CI-AKI. Multivariate logistic regression was then used to identify predictors of CI-AKI and develop a prediction model. The predictive values of SII, sd-LDL and their combination for CI-AKI were also evaluated. Results: Multivariate logistic regression analysis showed that age, left ventricular ejection fraction (LVEF), sd-LDL, uric acid, estimated glomerular filtration rate (eGFR) and SII were predictors of CI-AKI. The area under the curve (AUC) of the prediction model based on the above factors was 0.846 [95% confidence interval (CI) 0.808–0.884], and the Hosmer-Lemeshow test (P = 0.587, χ2 = 6.543) proved the goodness of fit of the model. The AUC combining SII with sd-LDL to predict CI-AKI was 0.785 (95% CI 0.735–0.836), with a sensitivity of 72.8% and a specificity of 79.8%, and was statistically significant when compared with SII and sd-LDL, respectively. The predictive efficiency of combining SII with sd-LDL and SII were evaluated by improved net reclassification improvement (NRI, 0.325, P < 0.001) and integrated discrimination improvement (IDI, 0.07, P < 0.001). Conclusions: Both SII and sd-LDL can be used as predictors of CI-AKI in STEMI patients undergoing emergency PCI, and their combination can provide more useful value for early assessment of CI-AKI.

Preprocedural Lp(a) level and ApoB/ApoA-Ι ratio and the risk for contrast-induced acute kidney injury in patients undergoing emergency PCI

BACKGROUND

High serum Lipoprotein(a) (Lp(a)) level and Apolipoprotein B/Apolipoprotein AΙ (ApoB/ApoA-Ι) ratio are risk factors for cardiovascular disease and kidney disease and have been found to be correlated with the prevalence and prognosis of various kidney diseases. However, it is not clear whether the serum Lp(a) level and ApoB/ApoA-Ι ratio pre-PCI are correlated with the prevalence of contrast-induced acute kidney injury (CI-AKI).

METHODS

A total of 931 participants undergoing emergency PCI from July 2018 to July 2020 were included. According to whether the serum creatinine concentration was higher than the baseline concentration (by ≥25% or ≥ 0.5 mg/dL) 48-72 h after contrast exposure, these participants were divided into a CI-AKI group (n = 174) and a non-CI-AKI group (n = 757). Serum Lp(a), ApoA-Ι and ApoB concentration were detected in the patients when they were admitted to hospital, and the ApoB/ApoA-Ι ratio was calculated. Logistic regression and restricted cubic spline analyses were used to explore the correlation between the Lp(a) concentration or the ApoB/ApoA-Ι ratio and the risk of CI-AKI.

RESULTS

Among the 931 participants undergoing emergency PCI, 174 (18.69%) participants developed CI-AKI. Compared with the non-CI-AKI group, the Lp(a) level and ApoB/ApoA-Ι ratio pre-PCI in the CI-AKI group were significantly higher (P < 0.05). The incidence of CI-AKI was positively associated with the serum Lp(a) level and ApoB/ApoA-Ι ratio pre-PCI in each logistic regression model (P < 0.05). After adjusting for all the risk factors included in this study, restricted cubic spline analyses found that the Lp(a) level and the ApoB/ApoA-Ι ratio before PCI, within certain ranges, were positively associated with the prevalence of CI-AKI.

CONCLUSION

High Lp(a) levels and high ApoB/ApoA-Ι ratios before PCI are potential risk factors for CI-AKI.