Variation in vancomycin dosing and therapeutic drug monitoring practices in neonatal intensive care units

Optimizing vancomycin dosing in pediatrics: a machine learning approach to predict trough concentrations in children under four years of age

BACKGROUND

Vancomycin trough concentration is closely associated with clinical efficacy and toxicity. Predicting vancomycin trough concentrations in pediatric patients is challenging due to significant inter-individual variability and rapid physiological changes during maturation.

AIM

This study aimed to develop a machine learning model to predict vancomycin trough concentrations and determine optimal dosing regimens for pediatric patients < 4 years of age using ML algorithms.

METHOD

A single-center retrospective observational study was conducted from January 2017 to March 2020. Pediatric patients who received intravenous vancomycin and underwent therapeutic drug monitoring were enrolled. Seven ML models [linear regression, gradient boosted decision trees, support vector machine, decision tree, random forest, Bagging, and extreme gradient boosting (XGBoost)] were developed using 31 variables. Performance metrics including R-squared (R2), mean square error (MSE), root mean square error (RMSE), and mean absolute error (MAE) were compared, and important features were ranked.

RESULTS

The study included 120 eligible trough concentration measurements from 112 patients. Of these, 84 measurements were used for training and 36 for testing. Among the seven algorithms tested, XGBoost showed the best performance, with a low prediction error and high goodness of fit (MAE = 2.55, RMSE = 4.13, MSE = 17.12, and R2 = 0.59). Blood urea nitrogen, serum creatinine, and creatinine clearance rate were identified as the most important predictors of vancomycin trough concentration.

CONCLUSION

An XGBoost ML model was developed to predict vancomycin trough concentrations and aid in drug treatment predictions as a decision-support technology.

Vancomycin Dosing and Its Association With Acute Kidney Injury in Pediatric Cardiac Intensive Care Patients Under 3 Months of Age

BACKGROUND

The standard vancomycin regimen for term neonates is 45 mg/kg/day. However, the optimal starting vancomycin dosing for achieving therapeutic levels in young infants in cardiac intensive care units remains unknown. Moreover, data on the association of supratherapeutic vancomycin levels with acute kidney injury (AKI) are limited.

METHODS

Retrospective study of infants ≤3 months old, receiving vancomycin following congenital heart surgery at postoperative intensive care unit admission. Assessed were vancomycin dosing, achievement of therapeutic trough concentration of 10-20 mg/L and development of AKI, based on the modified Kidney Disease Improving Global Outcomes criteria.

RESULTS

Inclusion criteria were met by 109 patients with a median age of 8 days (IQR: 6-16). The mean (SD) vancomycin dose required for achieving therapeutic concentration was 28.9 (9.1) mg/kg at the first postoperative day. Multivariate logistic regression identified higher preoperative creatinine levels and shorter cardiopulmonary bypass time as predictors of supratherapeutic vancomycin concentrations (c-index 0.788). During the treatment course, 62 (56.9%) developed AKI. Length of stay and mortality were higher in those who developed AKI as compared with those who did not. Multivariate logistic regression identified higher vancomycin concentration as a predictor for postoperative AKI, OR, 3.391 (95% CI: 1.257-9.151), P = 0.016 (c-index 0.896).

CONCLUSION

Our results support a lower starting vancomycin dose of ~30 mg/kg/day followed by an early personalized therapeutic approach, to achieve therapeutic trough concentrations of 10-20 mg/L in cardiac postoperative term infants. Supratherapeutic concentrations are associated with an increased risk for AKI, which is prevalent in this population and associated with adverse outcomes.

Discrepancy between perceptions and acceptance of clinical decision support Systems: implementation of artificial intelligence for vancomycin dosing

BACKGROUND

Artificial intelligence (AI) tools are more effective if accepted by clinicians. We developed an AI-based clinical decision support system (CDSS) to facilitate vancomycin dosing. This qualitative study assesses clinicians' perceptions regarding CDSS implementation.

METHODS

Thirteen semi-structured interviews were conducted with critical care pharmacists, at Mayo Clinic (Rochester, MN), from March through April 2020. Eight clinical cases were discussed with each pharmacist (N = 104). Following initial responses, we revealed the CDSS recommendations to assess participants' reactions and feedback. Interviews were audio-recorded, transcribed, and summarized.

RESULTS

The participants reported considerable time and effort invested daily in individualizing vancomycin therapy for hospitalized patients. Most pharmacists agreed that such a CDSS could favorably affect (N = 8, 62%) or enhance (9, 69%) their ability to make vancomycin dosing decisions. In case-based evaluations, pharmacists' empiric doses differed from the CDSS recommendation in most cases (88/104, 85%). Following revealing the CDSS recommendations, we noted 78% (69/88) discrepant doses. In discrepant cases, pharmacists indicated they would not alter their recommendations. The reasons for declining the CDSS recommendation were general distrust of CDSS, lack of dynamic evaluation and in-depth analysis, inability to integrate all clinical data, and lack of a risk index.

CONCLUSION

While pharmacists acknowledged enthusiasm about the advantages of AI-based models to improve drug dosing, they were reluctant to integrate the tool into clinical practice. Additional research is necessary to determine the optimal approach to implementing CDSS at the point of care acceptable to clinicians and effective at improving patient outcomes.

The Use of Antibiotics for Ventilator-Associated Pneumonia in the MIMIC-IV Database

Purpose: By analyzing the clinical characteristics, etiological characteristics and commonly used antibiotics of patients with ventilator-associated pneumonia (VAP) in intensive care units (ICUs) in the intensive care database. This study aims to provide guidance information for the clinical rational use of drugs for patients with VAP.

Method: Patients with VAP information were collected from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database, including their sociodemographic characteristics, vital signs, laboratory measurements, complications, microbiology, and antibiotic use. After data processing, the characteristics of the medications used by patients with VAP in ICUs were described using statistical graphs and tables, and experiences were summarized and the reasons were analyzed.

Results: This study included 2,068 patients with VAP. Forty-eight patient characteristics, including demographic indicators, vital signs, biochemical indicators, scores, and comorbidities, were compared between the survival and death groups of VAP patients. Cephalosporins and vancomycin were the most commonly used. Among them, fourth-generation cephalosporin (ForGC) combined with vancomycin was used the most, by 540 patients. First-generati49n cephalosporin (FirGC) combined with vancomycin was associated with the highest survival rate (86.7%). More than 55% of patients were infected with Gram-negative bacteria. However, patients with VAP had fewer resistant strains (&lt;25%). FirGC or ForGC combined with vancomycin had many inflammation-related features that differed significantly from those in patients who did not receive medication.

Conclusion: Understanding antibiotic use, pathogenic bacteria compositions, and the drug resistance rates of patients with VAP can help prevent the occurrence of diseases, contain infections as soon as possible, and promote the recovery of patients.