From the Department of Anesthesiology.
Division of Biomedical Informatics, Department of Medicine, University of California, San Diego School of Medicine, La Jolla, California.
Anesth Analg. 2020 Nov;131(5):1500-1509. doi: 10.1213/ANE.0000000000004897.
Induction of anesthesia is a phase characterized by rapid changes in both drug concentration and drug effect. Conventional mammillary compartmental models are limited in their ability to accurately describe the early drug distribution kinetics. Recirculatory models have been used to account for intravascular mixing after drug administration. However, these models themselves may be prone to misspecification. Artificial neural networks offer an advantage in that they are flexible and not limited to a specific structure and, therefore, may be superior in modeling complex nonlinear systems. They have been used successfully in the past to model steady-state or near steady-state kinetics, but never have they been used to model induction-phase kinetics using a high-resolution pharmacokinetic dataset. This study is the first to use an artificial neural network to model early- and late-phase kinetics of a drug.
Twenty morbidly obese and 10 lean subjects were each administered propofol for induction of anesthesia at a rate of 100 mg/kg/h based on lean body weight and total body weight for obese and lean subjects, respectively. High-resolution plasma samples were collected during the induction phase of anesthesia, with the last sample taken at 16 hours after propofol administration for a total of 47 samples per subject. Traditional mammillary compartment models, recirculatory models, and a gated recurrent unit neural network were constructed to model the propofol pharmacokinetics. Model performance was compared.
A 4-compartment model, a recirculatory model, and a gated recurrent unit neural network were assessed. The final recirculatory model (mean prediction error: 0.348; mean square error: 23.92) and gated recurrent unit neural network that incorporated ensemble learning (mean prediction error: 0.161; mean square error: 20.83) had similar performance. Each of these models overpredicted propofol concentrations during the induction and elimination phases. Both models had superior performance compared to the 4-compartment model (mean prediction error: 0.108; mean square error: 31.61), which suffered from overprediction bias during the first 5 minutes followed by under-prediction bias after 5 minutes.
A recirculatory model and gated recurrent unit artificial neural network that incorporated ensemble learning both had similar performance and were both superior to a compartmental model in describing our high-resolution pharmacokinetic data of propofol. The potential of neural networks in pharmacokinetic modeling is encouraging but may be limited by the amount of training data available for these models.
麻醉诱导期是一个药物浓度和药物效应迅速变化的阶段。传统的乳突室 compartmental 模型在准确描述早期药物分布动力学方面能力有限。再循环模型已被用于解释药物给药后血管内混合。然而，这些模型本身可能容易出现指定错误。人工神经网络具有灵活性的优势，不受特定结构的限制，因此在建模复杂的非线性系统方面可能更具优势。它们过去曾成功用于建模稳态或近稳态动力学，但从未用于使用高分辨率药代动力学数据集来模拟诱导期动力学。这项研究首次使用人工神经网络来模拟药物的早期和晚期动力学。
20 名病态肥胖和 10 名瘦受试者分别根据瘦体重和肥胖受试者的总体重以 100mg/kg/h 的速度给予异丙酚进行麻醉诱导。在麻醉诱导期采集高分辨率血浆样本，最后一次样本采集在异丙酚给药后 16 小时，每个受试者共采集 47 个样本。构建了传统的乳突室 compartmental 模型、再循环模型和门控循环单元神经网络来模拟异丙酚的药代动力学。比较了模型性能。
评估了 4 compartment 模型、再循环模型和门控循环单元神经网络。最终的再循环模型（平均预测误差：0.348；均方误差：23.92）和纳入集成学习的门控循环单元神经网络（平均预测误差：0.161；均方误差：20.83）具有相似的性能。在诱导和消除阶段，这两个模型都高估了异丙酚的浓度。与 4 compartment 模型（平均预测误差：0.108；均方误差：31.61）相比，这两种模型的性能都有所提高，4 compartment 模型在最初 5 分钟内存在高估偏差，之后 5 分钟内存在低估偏差。
再循环模型和纳入集成学习的门控循环单元人工神经网络的性能相似，在描述我们的异丙酚高分辨率药代动力学数据方面均优于 compartmental 模型。神经网络在药代动力学建模中的潜力令人鼓舞，但可能受到这些模型可用训练数据量的限制。
