Machine Learning for Pharmacokinetic/Pharmacodynamic Modeling

A variety of new recurrent neural networks (RNNs) including the ODE-LSTM, Phased LSTM, CTGRU and GRUD, were evaluated on modeling irregularly sampled PK/PD data with 6 or 12 time points/day and predicting PD data of unseen dosing regimens and dosing levels. The one-compartment absorption PK model and the Indirect PK/PD model I was used to simulate the PK/PD with inter-individual variabilities in volume of distribution and residual errors in PD measurement. The four RNNs were able to successfully model daily dose (QD) PK/PD and extrapolate to twice daily (BID) dose PD based on BID PK. The RNNs not only captured the additional fluctuations in the BID regimen but also the return phase to the baseline PD. However, extrapolating to unseen dose levels outside of the dose range for training proved to be challenging for all the RNNs tested. Only the GRUD demonstrated reasonable prediction results when extrapolating to unseen doses that were 3 or 10-fold outside the training doses. Overall, these new RNNs were able to overcome some limitations of previous RNNs evaluated and showed promise of integrating neural networks in PK/PD.(c) 2023 American Pharmacists Association. Published by Elsevier Inc. All rights reserved.

Automated summary

A variety of new recurrent neural networks (RNNs) were evaluated on modeling irregularly sampled PK/PD data and predicting PD data of unseen dosing regimens and dosing levels. The RNNs were able to model daily dose (QD) PK/PD and extrapolate to twice daily (BID) dose PD based on BID PK. However, extrapolating to unseen dose levels outside of the dose range for training proved to be challenging for all the RNNs tested. Only the GRUD demonstrated reasonable prediction results when extrapolating to unseen doses that were 3 or 10-fold outside the training doses. Overall, these new RNNs showed promise of integrating neural networks in PK/PD.