Prediction of the development of contrast‑induced nephropathy following percutaneous coronary artery intervention by machine learning

Ma, Xuhui; Mo, Changhua; Li, Yujuan; Chen, Xinyuan; Gui, Chun

doi:10.1080/00015385.2023.2198937

Cited by 3 publications

(3 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a more recent publication, the support vector machine (SVM) model showed the most outstanding AUC of 0.784 in terms of identifying the risk of contrast-induced nephropathy in elective PCI patients. The SVM model also outperformed logistic regression models [ 28 ]. Therefore, although currently available evidence suggests the potential efficacy of ML models for AKI risk prediction after PCI, selecting the optimal model has remained controversial.…”

Section: Discussionmentioning

confidence: 99%

“…In a study, Lasso and SHAP methods in ML selected that ST-elevation MI, eGFR, age, preprocedural hemoglobin, non-ST-elevation MI/unstable angina, heart failure at admission, and cardiogenic shock as the pertinent predictor for AKI risk after PCI [ 8 ]. On the other hand, Ma et al reported 11 important predictors of CI-nephropathy after PCI, including uric acid, peripheral vascular disease, cystatin C, creatine kinase-MB, hemoglobin, N-terminal pro-brain natriuretic peptide, age, diabetes, systemic immune-inflammatory index, total protein, and low-density lipoprotein, using SHAP method [ 28 ]. Also, age, serum creatinine level, and LVEF were among the top 20 ranked important variables concerning CI-AKI risk stratification after acute MI, using the Boruta ML algorithm [ 1 ].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

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

Behnoush,

Shariatnia,

Khalaji

et al. 2024

Eur J Med Res

View full text Add to dashboard Cite

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. Graphical Abstract

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

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

Behnoush,

Shariatnia,

Khalaji

et al. 2024

Eur J Med Res

View full text Add to dashboard Cite

show abstract

“…For example, many primary care practitioners are uncomfortable interpreting the results of these tests and request additional clinical input from specialists. Furthermore, many of these tests have medically significant side effects including damage from ionizing radiation and renal damage from contrast dye [ 10 – 13 ]. Finally, clinicians will often conduct multiple modes of testing on the same patient and add additional testing options, such as the use of third-party software vendors, to analyze already obtained imaging data.…”

Section: Introductionmentioning

confidence: 99%

The Use of Precision Epigenetic Methods for the Diagnosis and Care of Stable Coronary Heart Disease Reduces Healthcare Costs

Frisvold,

Dogan,

Dogan

et al. 2024

Adv Ther

View full text Add to dashboard Cite

Introduction The cost of secondary prevention of coronary heart disease (CHD) is continuing to increase, with a substantial portion of this acceleration being driven by the expense of confirmatory diagnostic testing. Conceivably, newly developed precision epigenetic technologies could drive down these costs. However, at the current time, their impact on overall expense for CHD care is poorly understood. We hypothesized that the use of a newly developed, highly sensitive, and specific epigenetic test, PrecisionCHD, could decrease the costs of secondary prevention. Methods To test this hypothesis, we constructed a budget impact analysis using a cost calculation model that examined the effects of substituting PrecisionCHD for conventional CHD diagnostic tests on the expenses of the initial evaluation and first year of care of stable CHD using a 1-year time horizon with no discounting. Results The model projected that for a commercial insurer with one million members, full adoption of PrecisionCHD as the primary method of initial CHD assessment would save approximately $113.6 million dollars in the initial year. Conclusion These analyses support the use of precision epigenetic methods as part of the initial diagnosis and care of stable CHD and can meaningfully reduce cost. Real-world pilots to test the reliability of these analyses are indicated. Supplementary Information The online version contains supplementary material available at 10.1007/s12325-024-02860-7.

show abstract

Special issue on ischaemic heart disease

Lancellotti

2023

Acta Cardiologica

View full text Add to dashboard Cite

Prediction of the development of contrast‑induced nephropathy following percutaneous coronary artery intervention by machine learning

Cited by 3 publications

References 30 publications

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

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

The Use of Precision Epigenetic Methods for the Diagnosis and Care of Stable Coronary Heart Disease Reduces Healthcare Costs

Special issue on ischaemic heart disease

Contact Info

Product

Resources

About