PK-RNN-V E: A Deep Learning Model Approach to Vancomycin Therapeutic Drug Monitoring Using Electronic Health Record Data
Authors:
- Hong Thoai Nga TranHTHong Thoai Nga Tran
- Laila RasmyLRLaila Rasmy
- Degui ZhiDZDegui Zhi
Preprint
Abstract
Vancomycin is a commonly used antimicrobial in hospitals, and therapeutic drug monitoring (TDM) is required to optimize its efficacy and avoid toxicities. Bayesian models are currently recommended to predict the antibiotic levels. These models, however, although using carefully designed lab observations, were often developed in limited patient populations. The increasing availability of electronic health record (EHR) data offers an opportunity to develop TDM models for real-world patient populations. Here, we present a deep learning-based pharmacokinetic prediction model for vancomycin (PK-RNN-V E) using a large EHR dataset of 5,483 patients with 55,336 vancomycin administrations. PK-RNN-V E takes the patient’s real-time sparse and irregular observations and offers dynamic predictions. Our results show that RNN-PK-V E offers a root mean squared error (RMSE) of 5.39 and outperforms the traditional Bayesian model (VTDM model) with an RMSE of 6.29. We believe that PK-RNN-V E can provide a pharmacokinetic model for vancomycin and other antimicrobials that require TDM. Statement of Significance: Problem: Current traditional Bayesian models for vancomycin levels were tested in only a limited patient population and take limited patient-specific features. Hence, a more flexible and powerful model, such as deep-learning models, may provide significant advantages. What is Already Known: The Bayesian models do not predict the vancomycin levels well in patient populations with unstable hemodynamic status and fluctuating kidney functions. What this Paper Adds: Deep-learning based pharmacokinetic model for vancomycin (PK-RNN-V E) provided better prediction accuracy with integrating multiple patient-specific features from time sequence electronic health record data. This study proved the concept of model.Keywords
All Related Versions
- Published version: Journal of Biomedical Informatics, 133, 104166.
This publication has 20 references indexed in Scilit:
- Exploration of optimal dosing regimens of vancomycin in patients infected with methicillin-resistant Staphylococcus aureus by modeling and simulationJournal of Clinical Pharmacy and Therapeutics, 2014
- Vancomycin: Over 50 Years Later and Still a Work in ProgressPharmacotherapy: The Journal of Human Pharmacology and Drug Therapy, 2013
- Predictive performance of reported population pharmacokinetic models of vancomycin in Chinese adult patientsJournal of Clinical Pharmacy and Therapeutics, 2013
- Vancomycin therapeutics and monitoring: a contemporary approachInternal Medicine Journal, 2013
- Waves of resistance: Staphylococcus aureus in the antibiotic eraNature Reviews Microbiology, 2009
- Predictability of vancomycin trough concentrations using seven approaches for estimating pharmacokinetic parametersAmerican Journal of Health-System Pharmacy, 2006
- The Pharmacokinetic and Pharmacodynamic Properties of VancomycinClinical Infectious Diseases, 2006
- Population Pharmacokinetic Analysis of Vancomycin in Patients with Hematological MalignanciesAntimicrobial Agents and Chemotherapy, 2005
- A rise in plasma creatinine that is not a sign of renal failure: which drugs can be responsible?Journal of Internal Medicine, 1999
- Studies in the concentration of indifferent narcotics in blood and tissuesActa Medica Scandinavica, 1919