Dataset Information

Application of Machine Learning Classification to Improve the Performance of Vancomycin Therapeutic Drug Monitoring.

ABSTRACT: Bayesian therapeutic drug monitoring (TDM) software uses a reported pharmacokinetic (PK) model as prior information. Since its estimation is based on the Bayesian method, the estimation performance of TDM software can be improved using a PK model with characteristics similar to those of a patient. Therefore, we aimed to develop a classifier using machine learning (ML) to select a more suitable vancomycin PK model for TDM in a patient. In our study, nine vancomycin PK studies were selected, and a classifier was created to choose suitable models among them for patients. The classifier was trained using 900,000 virtual patients, and its performance was evaluated using 9000 and 4000 virtual patients for internal and external validation, respectively. The accuracy of the classifier ranged from 20.8% to 71.6% in the simulation scenarios. TDM using the ML classifier showed stable results compared with that using single models without the ML classifier. Based on these results, we have discussed further development of TDM using ML. In conclusion, we developed and evaluated a new method for selecting a PK model for TDM using ML. With more information, such as on additional PK model reporting and ML model improvement, this method can be further enhanced.

SUBMITTER: Lee S

PROVIDER: S-EPMC9144093 | biostudies-literature | 2022 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Application of Machine Learning Classification to Improve the Performance of Vancomycin Therapeutic Drug Monitoring.

Lee Sooyoung S Song Moonsik M Han Jongdae J Lee Donghwan D Kim Bo-Hyung BH Kim Bo-Hyung BH

Pharmaceutics 20220509 5

Bayesian therapeutic drug monitoring (TDM) software uses a reported pharmacokinetic (PK) model as prior information. Since its estimation is based on the Bayesian method, the estimation performance of TDM software can be improved using a PK model with characteristics similar to those of a patient. Therefore, we aimed to develop a classifier using machine learning (ML) to select a more suitable vancomycin PK model for TDM in a patient. In our study, nine vancomycin PK studies were selected, and a ...[more]

PMID: 35631610

Similar Datasets

Project description:Background and objectiveThe necessity of therapeutic drug monitoring (TDM) for vancomycin is controversial. The objective of the current review was to evaluate the available evidence for the necessity of TDM in patients given vancomycin to treat Gram-positive infections.MethodsMedline, Embase, Web of Sciences, the Cochrane Library and two Chinese literature databases (CNKI, CBM) were searched. Randomized controlled studies and observational studies that compared the clinical outcomes of TDM groups vs. non-TDM groups were included. Two reviewers independently extracted the data. The primary outcome was clinical efficacy of therapy. Secondary outcomes included vancomycin associated nephrotoxicity, duration of vancomycin therapy, length of hospital stay, and mortality. Meta-analysis was performed using the Mantel-Haenszel fixed effect method (FEM). Odds ratios (ORs) or weighted mean differences (WMD) with 95% confidence intervals (95%CIs) were calculated for categorical and continuous outcomes, respectively.ResultsOne randomized controlled trial (RCT) and five cohort studies were included in the meta-analysis. Compared with non-TDM groups, TDM groups had significantly higher rates of clinical efficacy (OR = 2.62, 95%CI 1.34-5.11 P = 0.005) and decreased rates of nephrotoxicity (OR = 0.25, 95%CI 0.13-0.48 P<0.0001). Subgroup analyses showed that TDM group had significantly higher rates of clinical efficacy in both cohort studies subgroup (OR = 3.04, 95%CI 1.34-6.90) and in Asian population subgroup (OR = 3.04, 95%CI 1.34-6.90). TDM group had significantly decreased rates of nephrotoxicity in all subgroup. There was no significant difference in duration of vancomycin therapy (WMD = -0.40, 95%CI -2.83-2.02 P = 0.74) or length of stay (WMD = -1.01, 95%CI -7.51-5.49 P = 0.76) between TDM and non-TDM groups. Subgroup analyses showed there were no differences in duration of vancomycin therapy. Only one study reported mortality rates.ConclusionsStudies to date show that TDM significantly increases the rate of clinical efficacy and decreases the rate of nephrotoxicity in patients treated with vancomycin.

Dataset Information

Application of Machine Learning Classification to Improve the Performance of Vancomycin Therapeutic Drug Monitoring.

Publications

Application of Machine Learning Classification to Improve the Performance of Vancomycin Therapeutic Drug Monitoring.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets