Deep Learning Based Pharmacokinetic Model for Vancomycin

摘要：（30行） 万古霉素是住院患者最常用的抗菌药物之一。国家指导方针 我推荐贝叶斯模型来监测万古霉素的治疗药物浓度，特别是对于 耐甲氧西林金黄色葡萄球菌（MRSA），以尽量减少药物毒性，同时保持其疗效。 现有的贝叶斯模型，尽管被称为患者特异性药代动力学（PK）模型，使用简单的 患者特征，并在有限的患者人群中研究基于人群的PK参数（ 贝叶斯先验）。越来越多的真实世界电子健康记录（EHR）提供了广泛的 患者特异性数据，包括万古霉素剂量和血清水平数据。然而，有限的灵活性 贝叶斯模型结构阻碍了对这些丰富数据的充分利用。深度学习模型，如循环 与贝叶斯模型相比，神经网络（RNN）对EHR中万古霉素的PK特别有吸引力 和其他传统的机器学习模型，因为深度学习模型可以使患者更灵活地 具体的投入，并具有较高的潜力。因此，它们可以更好地预测不同的 人口我们的万古霉素深度学习模型（PK-RNN-V）优于公开的贝叶斯模型 模型，但可以在各个方面进行改进。在目标1中，我们将改进PK-RNN-V模型架构， 添加更多患者特定数据和更精细的时间步长。我们将构建两室PK-RNN模型， 增加对不稳定状态患者的预测能力。我们将用Med-BERT增强PK-RNN-V， 改进分类数据的嵌入。我们还将开发多轨常微分方程 同时预测血清肌酐和万古霉素水平的模型。在目标2中，我们将使用 不同的来源来验证我们的PK-RNN-V模型，并改进数据提取流程和预处理， 协调医疗保健系统的数据。我们将使用休斯顿卫理公会医院和纪念医院的EHR 赫尔曼医院系统/德克萨斯州休斯顿的德克萨斯大学健康科学中心， Arizona in Phoenix，AZ，和公开可用的MIMIC-IV数据库（Boston，MA）。这些数据库包含 数据来自超过121，007例接受至少一剂静脉万古霉素的患者。在目标3中， 我将添加基于PK-RNN-V模型预测的剂量建议作为一个功能，并验证我们的模型 在具有挑战性万古霉素PK的特定亚组中预测PK水平。该项目将提供大量 模型的改进，直接导致万古霉素在医院的使用优化，增加了患者 通过最大限度地减少不良事件和降低医疗费用来提高安全性，这与NIH的研究使命一致。

Abstract: (30 lines) Vancomycin is one of the most commonly used antimicrobial drugs in inpatient settings. National guidelines recommend Bayesian models to monitor the therapeutic drug concentration of vancomycin, especially for methicillin-resistant Staphylococcus aureus (MRSA), to minimize drug toxicity while maintaining its efficacy. Existing Bayesian models, despite being claimed as patient-specific pharmacokinetic (PK) models, use simple patient features and are studied in limited patient populations for the population-based PK parameters (the Bayesian prior). Increasingly available real-world electronic health records (EHR) provide a wide range of patient-specific data, including data on vancomycin dosage and serum levels. However, the limited flexibility of the Bayesian model structure prohibits the full use of these rich data. Deep-learning models, such as recurrent neural network (RNN), are particularly attractive for PK of vancomycin in EHR, compared to Bayesian models and other traditional machine learning models, because deep-learning models enable more flexible patient- specific inputs and possess a higher latent capacity. Thus, they deliver better predictions for a diverse population. Our deep-learning model for vancomycin (PK-RNN-V) outperforms publicly available Bayesian models but can be improved on various aspects. In Aim 1, we will improve PK-RNN-V model architectures and add more patient-specific data and a finer timestep. We will construct two-compartment PK-RNN models to increase predictive power in patients with unsteady states. We will augment PK-RNN-V with Med-BERT to improve the embedding of categorical data. We will also develop multi-track ordinary differential equations models for simultaneous prediction of serum creatinine and vancomycin levels. In Aim 2, we will use EHR from different sources to validate our PK-RNN-V model and improve the data-extraction flow and pre-processing to harmonize data from healthcare systems. We will use EHR from Houston Methodist Hospital and Memorial Hermann Hospital System/The University of Texas Health Science Center in Houston, TX, the University of Arizona in Phoenix, AZ, and the publicly available MIMIC-IV database (Boston, MA). These databases contain data from more than 121,007 patients who received at least one dose of intravenous vancomycin. In Aim 3, we will add dosing recommendations based on PK-RNN-V model predictions as a feature and validate our model in specific subgroups with challenging vancomycin PK to predict PK levels. This project will deliver substantial model improvements, leading directly to the optimization of vancomycin use in hospitals, increased in patient safety by minimizing adverse events, and reduced healthcare costs, which align with NIH’s research mission.