TCT-332 Machine Learning Methods in Prediction of Acute Kidney Injury: Application of the US National Cardiovascular Data Registry Model on Japanese Percutaneous Coronary Intervention Patients

AbstractAcute kidney injury (AKI) after percutaneous coronary intervention (PCI) is associated with a significant risk of morbidity and mortality. The traditional risk model provided by the National Cardiovascular Data Registry (NCDR) is useful for predicting the preprocedural risk of AKI, although the scoring system requires a number of clinical contents. We sought to examine whether machine learning (ML) techniques could predict AKI with fewer NCDR-AKI risk model variables within a comparable PCI database in Japan. We evaluated 19,222 consecutive patients undergoing PCI between 2008 and 2019 in a Japanese multicenter registry. AKI was defined as an absolute or a relative increase in serum creatinine of 0.3 mg/dL or 50%. The data were split into training (N = 16,644; 2008–2017) and testing datasets (N = 2578; 2017–2019). The area under the curve (AUC) was calculated using the light gradient boosting model (GBM) with selected variables by Lasso and SHapley Additive exPlanations (SHAP) methods among 12 traditional variables, excluding the use of an intra-aortic balloon pump, since its use was considered operator-dependent. The incidence of AKI was 9.4% in the cohort. Lasso and SHAP methods demonstrated that seven variables (age, eGFR, preprocedural hemoglobin, ST-elevation myocardial infarction, non-ST-elevation myocardial infarction/unstable angina, heart failure symptoms, and cardiogenic shock) were pertinent. AUC calculated by the light GBM with seven variables had a performance similar to that of the conventional logistic regression prediction model that included 12 variables (light GBM, AUC [training/testing datasets]: 0.779/0.772; logistic regression, AUC [training/testing datasets]: 0.797/0.755). The AKI risk model after PCI using ML enabled adequate risk quantification with fewer variables. ML techniques may aid in enhancing the international use of validated risk models.

Download Full-text

Contrast-induced acute kidney injury and nitric oxide depletion in patients undergoing primary percutaneous coronary intervention

Journal of Cardiovascular Medicine ◽

10.2459/jcm.0000000000001154 ◽

2021 ◽

Vol Publish Ahead of Print ◽

Author(s):

Alessio Arrivi ◽

Giacomo Pucci ◽

Marcello Dominici ◽

Enrico Mangieri ◽

Gaetano Tanzilli

Keyword(s):

Nitric Oxide ◽

Acute Kidney Injury ◽

Percutaneous Coronary Intervention ◽

Primary Percutaneous Coronary Intervention ◽

Kidney Injury ◽

Coronary Intervention ◽

Percutaneous Coronary

Download Full-text

Faculty Opinions recommendation of Effect of access site choice on acute kidney injury after percutaneous coronary intervention.

Faculty Opinions – Post-Publication Peer Review of the Biomedical Literature ◽

10.3410/f.732085796.793560628 ◽

2019 ◽

Author(s):

Eric Hoste

Keyword(s):

Acute Kidney Injury ◽

Percutaneous Coronary Intervention ◽

Kidney Injury ◽

Coronary Intervention ◽

Access Site ◽

Percutaneous Coronary

Download Full-text

Nutritional status and risk of contrast-associated acute kidney injury in elderly patients undergoing percutaneous coronary intervention

Clinical and Experimental Nephrology ◽

10.1007/s10157-021-02061-4 ◽

2021 ◽

Author(s):

Xiaoqi Wei ◽

Hanchuan Chen ◽

Zhebin You ◽

Jie Yang ◽

Haoming He ◽

...

Keyword(s):

Risk Factors ◽

Acute Kidney Injury ◽

Percutaneous Coronary Intervention ◽

Nutritional Status ◽

Elderly Patients ◽

Kidney Injury ◽

Coronary Intervention ◽

Severe Malnutrition ◽

Percutaneous Coronary ◽

Conut Score

Abstract Background This study aimed to investigate the connection between malnutrition evaluated by the Controlling Nutritional Status (CONUT) score and the risk of contrast-associated acute kidney injury (CA-AKI) in elderly patients who underwent percutaneous coronary intervention (PCI). Methods A total of 1308 patients aged over 75 years undergoing PCI was included. Based on the CONUT score, patients were assigned to normal (0–1), mild malnutrition (2–4), moderate-severe malnutrition group (≥ 5). The primary outcome was CA-AKI (an absolute increase in ≥ 0.3 mg/dL or ≥ 50% relative serum creatinine increase 48 h after contrast medium exposure). Results Overall, the incidence of CA-AKI in normal, mild, moderate-severe malnutrition group was 10.8%, 11.0%, and 27.2%, respectively (p < 0.01). Compared with moderate-severe malnutrition group, the normal group and the mild malnutrition group showed significant lower risk of CA-AKI in models adjusting for risk factors for CA-AKI and variables in univariate analysis (odds ratio [OR] = 0.48, 95% confidence interval [CI]: 0.26–0.89, p = 0.02; OR = 0.46, 95%CI: 0.26–0.82, p = 0.009, respectively). Furthermore, the relationship were consistent across the subgroups classified by risk factors for CA-AKI except anemia. The risk of CA-AKI related with CONUT score was stronger in patients with anemia. (overall interaction p by CONUT score = 0.012). Conclusion Moderate-severe malnutrition is associated with higher risk of CA-AKI in elderly patients undergoing PCI.

Download Full-text