Search

Background and Objective: High variability in vancomycin exposure in neonates requires advanced individualized dosing regimens. Achieving steady-state trough concentration (C0) and steady-state area-under-curve (AUC0–24) targets is important to optimize treatment. The objective was to evaluate whether machine learning (ML) can be used to predict these treatment targets to calculate optimal individual dosing regimens under intermittent administration conditions. Methods: C0 were retrieved from a large neonatal vancomycin dataset. Individual estimates of AUC0–24 were obtained from Bayesian post hoc estimation. Various ML algorithms were used for model building to C0 and AUC0–24. An external dataset was used for predictive performance evaluation. Results: Before starting treatment, C0 can be predicted a priori using the Catboost-based C0-ML model combined with dosing regimen and nine covariates. External validation results showed a 42.5% improvement in prediction accuracy by using the ML model compared with the population pharmacokinetic model. The virtual trial showed that using the ML optimized dose; 80.3% of the virtual neonates achieved the pharmacodynamic target (C0 in the range of 10–20 mg/L), much higher than the international standard dose (37.7–61.5%). Once therapeutic drug monitoring (TDM) measurements (C0) in patients have been obtained, AUC0–24 can be further predicted using the Catboost-based AUC-ML model combined with C0 and nine covariates. External validation results showed that the AUC-ML model can achieve an prediction accuracy of 80.3%. Conclusion: C0-based and AUC0–24-based ML models were developed accurately and precisely. These can be used for individual dose recommendations of vancomycin in neonates before treatment and dose revision after the first TDM result is obtained, respectively. [ABSTRACT FROM AUTHOR]

This single-centre prospective feasibility study (UMIN000030232) evaluated whether zinc supplementation was safe and effective for improving outcomes among patients with acute myocardial infarction (AMI). Within 24 h after successful primary percutaneous coronary intervention, consenting patients with AMI were randomly assigned 1:1 to receive conventional treatment (conventional treatment group) or conventional treatment plus zinc acetate supplementation (zinc supplementation group). The two groups were compared in terms of major adverse cardiovascular events (MACE), and scar size, which was evaluated using cardiac magnetic resonance imaging (CMR) at 4 weeks after discharge. A total of 56 patients underwent randomization (with 26 assigned to the zinc supplementation group and 27 to the conventional treatment group). The two groups had generally similar laboratory findings and clinical characteristics. The two groups also had similar lengths of hospital stay and rates of MACE. Forty of the 53 patients underwent CMR and it revealed that % core zone was numerically lower in the zinc supplementation group than in the conventional treatment group (9.3 ± 6.9% vs. 14.2 ± 9.1%, P = 0.07). This small single-centre study failed to detect a significant reduction in mid-term MACE after AMI among patients who received zinc supplementation. [ABSTRACT FROM AUTHOR]

This study aimed to determine the optimal cut-off value of the early drop in systolic blood pressure (SBP) for worsening renal function (WRF) in hospitalized patients with heart failure (HF) and analyze predictors of WRF and the early drop in SBP at that threshold. We retrospectively enrolled 396 patients with acute decompensated HF. The early drop in SBP was defined as the difference between baseline and SBP measured 24 h after hospitalization. We performed receiver operating characteristic (ROC) analysis to determine the optimal cut-off value of the early drop in SBP for WRF and evaluated the effect of the early drop in SBP on in-hospital mortality by multivariate logistic regression analyses. The mean age of the patients was 73.4 ± 14.7 years, and 61.2% were men. A 14.0% drop in SBP was identified as the optimal cut-off value for WRF from the ROC curve analysis. An early drop in SBP ≥ 14.0% was associated with WRF in multivariate logistic regression analysis (odds ratio 7.84; 95% confidence interval 4.06–15.14; P < 0.0001). The dose of intravenous furosemide within 24 h of admission was one of the predictors of the early drop in SBP ≥ 14.0%, while no early drop in SBP was a predictor of in-hospital mortality in multivariate logistic regression models. In conclusion, the optimal cut-off value for WRF in patients with HF was a 14.0% drop in SBP within 24 h of admission. The early drop in SBP ≥ 14.0% was one of the predictors of WRF in patients with HF. However, no early drop in SBP was associated with in-hospital mortality. This study was registered with the University Hospital Medical Information Network in Japan (UMIN000035989). [ABSTRACT FROM AUTHOR]