Modeling and Simulation/Clinical Pharmacology, Genentech Inc., South San Francisco, California, USA.
Cancer Immunology, Genentech Inc., South San Francisco, California, USA.
CPT Pharmacometrics Syst Pharmacol. 2024 May;13(5):870-879. doi: 10.1002/psp4.13124. Epub 2024 Mar 11.
Noncompartmental analysis (NCA) is a model-independent approach for assessing pharmacokinetics (PKs). Although the existing NCA algorithms are very well-established and widely utilized, they suffer from low accuracies in the setting of sparse PK samples. In response, we developed Deep-NCA, a deep learning (DL) model to improve the prediction of key noncompartmental PK parameters. Our methodology utilizes synthetic PK data for model training and uses an innovative patient-specific normalization method for data preprocessing. Deep-NCA demonstrated adequate performance across six previously unseen simulated drugs under multiple dosing, showcasing effective generalization. Compared to traditional NCA, Deep-NCA exhibited superior performance for sparse PK data. This study advances the application of DL to PK studies and introduces an effective method for handling sparse PK data. With further validation and refinement, Deep-NCA could significantly enhance the efficiency of drug development by providing more accurate NCA estimates while requiring fewer PK samples.
非房室分析（NCA）是一种用于评估药代动力学（PKs）的模型独立方法。尽管现有的 NCA 算法已经非常成熟并得到广泛应用，但在 PK 样本稀疏的情况下，它们的准确性较低。针对这一问题，我们开发了 Deep-NCA，这是一种深度学习（DL）模型，用于提高关键非房室 PK 参数的预测准确性。我们的方法利用合成 PK 数据进行模型训练，并使用创新的患者特异性归一化方法进行数据预处理。Deep-NCA 在多种剂量下对六个以前未见的模拟药物的表现均良好，展示了有效的泛化能力。与传统的 NCA 相比，Deep-NCA 在 PK 数据稀疏的情况下表现出更好的性能。本研究将 DL 应用于 PK 研究，并引入了一种处理稀疏 PK 数据的有效方法。通过提供更准确的 NCA 估计值，同时减少 PK 样本数量，Deep-NCA 可以显著提高药物开发的效率。
