Long short-term memory recurrent neural network for pharmacokinetic-pharmacodynamic modeling
Xiangyu Liu, Chao Liu, Ruihao Huang, Hao Zhu, Qi Liu, Sunanda Mitra, Yaning Wang
Abstract
OBJECTIVE: Recurrent neural network (RNN) has been demonstrated as a powerful tool for analyzing various types of time series data. There is limited knowledge about the application of the RNN model in the area of pharmacokinetic (PK) and pharmacodynamic (PD) analysis. In this paper, a specific variation of RNN, long short-term memory (LSTM) network, is presented to analyze the simulated PK/PD data of a hypothetical drug. MATERIALS AND METHODS: The plasma concentration and effect level under one dosing regimen were used to train the LSTM model. The developed LSTM model was used to predict the individual PK/PD data under other dosing regimens. RESULTS: The optimized LSTM model captured temporal dependencies and predicted PD profiles accurately for the simulated indirect PK-PD relationship. CONCLUSION: The results demonstrated that the generic LSTM model can approximate the complex underlying mechanistic biological processes.