Risk Scoring System for Vancomycin-Associated Acute Kidney Injury

Prediction of acute kidney injury in patients with liver cirrhosis using machine learning models: evidence from the MIMIC-III and MIMIC-IV

PURPOSE

To develop and validate a machine learning (ML)-based prediction model for acute kidney injury (AKI) in patients with liver cirrhosis.

METHODS

Data on liver cirrhosis patients were extracted from the Medical Information Mart for Intensive Care III (MIMIC-III) and MIMIC-IV databases in this retrospective cohort study. ML algorithms, including random forest (RF), extreme gradient boosting (XGB), light gradient boosting machine (LGBM), and gradient boosting decision tree (GBDT) were applied to construct prediction models. Predictors were screened via univariate logistic regression, and then the models were developed with all data of the included patients. A bootstrap resampling method was adopted to validate the models. The predictive abilities of our final model were compared with those of the sequential organ failure assessment score (SOFA), simplified acute physiology score II (SAPS II), Model for End-stage Liver Disease (MELD), and MELD Na.

RESULTS

This study included 950 patients, of which 429 (45.16%) had AKI. Mechanical ventilation, vasopressor, international normalized ratio (INR), bilirubin, Charlson comorbidity index (CCI), prothrombin time (PT), estimated glomerular filtration rate (EGFR), partial thromboplastin time (PTT), and heart rate served as predictors. In the derivation set, the developed RF [area under curve (AUC) = 0.747], XGB (AUC = 0.832), LGBM (AUC = 0.785), and GBDT (AUC = 0.811) models exhibited significantly greater predictive performance than the logistic regression model (AUC = 0.699) (all P < 0.05). Among the ML-based models, the XGB model had the greatest AUC. In internal validation, the predictive capacity of the XGB model (AUC = 0.833) was significantly superior to that of the logistic regression model (AUC = 0.701) (P = 0.045). Hence, the XGB model was selected as the final model for AKI prediction. In contrast to the XGB model (AUC = 0.832), the SOFA (AUC = 0.609), MELD (AUC = 0.690), MELD Na (AUC = 0.690), and SAPS II (AUC = 0.641) had significantly lower predictive abilities in the derivation set (all P < 0.001). The XGB model was internally validated to have an AUC of 0.833, which was significantly higher than the SOFA (AUC = 0.609), MELD (AUC = 0.690), MELD Na (AUC = 0.688), and SAPS II (AUC = 0.641) (all P < 0.05).

CONCLUSION

The XGB model had a better performance than the logistic regression model, SOFA, MELD, MELD Na, and SAPS II in AKI prediction for cirrhosis patients, which may help identify patients at a risk of AKI, and then provide timely interventions.

Vancomycin associated acute kidney injury in patients with infectious endocarditis: a large retrospective cohort study

Background: Vancomycin remains the cornerstone antibiotic for the treatment of infective endocarditis (IE). Vancomycin has been associated with significant nephrotoxicity. However, vancomycin associated acute kidney injury (AKI) has not been evaluated in patients with IE. We conducted this large retrospective cohort study to reveal the incidence, risk factors, and prognosis of vancomycin-associated acute kidney injury (VA-AKI) in patients with IE. Methods: Adult patients diagnosed with IE and receiving vancomycin were included. The primary outcome was VA-AKI. Results: In total, 435 of the 600 patients were enrolled. Of these, 73.6% were male, and the median age was 52 years. The incidence of VA-AKI was 17.01% (74). Only 37.2% (162) of the patients received therapeutic monitoring of vancomycin, and 30 (18.5%) patients had reached the target vancomycin trough concentration. Multiple logistic regression analysis revealed that body mass index [odds ratio (OR) 1.088, 95% CI 1.004, 1.179], duration of vancomycin therapy (OR 1.030, 95% CI 1.003, 1.058), preexisting chronic kidney disease (OR 2.291, 95% CI 1.018, 5.516), admission to the intensive care unit (OR 2.291, 95% CI 1.289, 3.963) and concomitant radiocontrast agents (OR 2.085, 95% CI 1.093, 3.978) were independent risk factors for VA-AKI. Vancomycin variety (Lai Kexin vs. Wen Kexin, OR 0.498, 95% CI 0.281, 0.885) were determined to be an independent protective factor for VI-AKI. Receiver operator characteristic curve analysis revealed that duration of therapy longer than 10.75 days was associated with a significantly increased risk of VA-AKI (HR 1.927). Kidney function was fully or partially recovered in 73.0% (54) of patients with VA-AKI. Conclusion: The incidence of VA-AKI in patients with IE was slightly higher than in general adult patients. Concomitant contrast agents were the most alarmingly nephrotoxic in patients with IE, adding a 2-fold risk of VA-AKI. In patients with IE, a course of vancomycin therapy longer than 10.75 days was associated with a significantly increased risk of AKI. Thus, closer monitoring of kidney function and vancomycin trough concentrations was recommended in patients with concurrent contrast or courses of vancomycin longer than 10.75 days.

Analysis of a machine learning-based risk stratification scheme for acute kidney injury in vancomycin

Vancomycin-associated acute kidney injury (AKI) continues to pose a major challenge to both patients and healthcare providers. The purpose of this study is to construct a machine learning framework for stratified predicting and interpreting vancomycin-associated AKI. Our study is a retrospective analysis of medical records of 724 patients who have received vancomycin therapy from 1 January 2015 through 30 September 2020. The basic clinical information, vancomycin dosage and days, comorbidities and medication, laboratory indicators of the patients were recorded. Machine learning algorithm of XGBoost was used to construct a series risk prediction model for vancomycin-associated AKI in different underlying diseases. The vast majority of sub-model performed best on the corresponding sub-dataset. Additionally, the aim of this study was to explain each model and to explore the influence of clinical variables on prediction. As the results of the analysis showed that in addition to the common indicators (serum creatinine and creatinine clearance rate), some other underappreciated indicators such as serum cystatin and cumulative days of vancomycin administration, weight and age, neutrophils and hemoglobin were the risk factors for cancer, diabetes mellitus, heptic insufficiency respectively. Stratified analysis of the comorbidities in patients with vancomycin-associated AKI further confirmed the necessity for different patient populations to be studied.

Pharmacokinetic assessment of vancomycin in critically ill patients and nephrotoxicity prediction using individualized pharmacokinetic parameters

Introduction: Therapeutic drug monitoring (TDM) and pharmacokinetic assessments of vancomycin would be essential to avoid vancomycin-associated nephrotoxicity and obtain optimal therapeutic and clinical responses. Different pharmacokinetic parameters, including trough concentration and area under the curve (AUC), have been proposed to assess the safety and efficacy of vancomycin administration.

Methods: Critically ill patients receiving vancomycin at Nemazee Hospital were included in this prospective study. Four blood samples at various time intervals were taken from each participated patient. Vancomycin was extracted from plasma samples and analyzed using a validated HPLC method.

Results: Fifty-three critically ill patients with a total of 212 blood samples from June 2019 to June 2021 were included in this study. There was a significant correlation between baseline GFR, baseline serum creatinine, trough and peak concentrations, AUCτ, AUC_24h, Cl, and V_d values with vancomycin-induced AKI. Based on trough concentration values, 66% of patients were under-dosed (trough concentration <15 μg/ml) and 18.9% were over-dosed (trough concentration ≥20 μg/ml). Also, based on AUC_24h values, about 52.2% were under-dosed (AUC_24h < 400 μg h/ml), and 21.7% were over-dosed (AUC_24h > 600 μg h/ml) that emphasizes on the superiority of AUC-based monitoring approach for TDM purposes to avoid nephrotoxicity occurrence.

Conclusion: The AUC-based monitoring approach would be superior in terms of nephrotoxicity prediction. Also, to avoid vancomycin-induced AKI, trough concentration and AUCτ values should be maintained below the cut-off points.