Machine learning in pharmacometrics: Opportunities and challenges

Abstract

The explosive growth in medical devices, imaging and diagnostics, computing, and communication and information technologies in drug development and healthcare has created an ever-expanding data landscape that the pharmacometrics (PMX) research community must now traverse. The tools of machine learning (ML) have emerged as a powerful computational approach in other data-rich disciplines but its effective utilization in the pharmaceutical sciences and PMX modelling is in its infancy. ML-based methods can complement PMX modelling by enabling the information in diverse sources of big data, e.g. population-based public databases and disease-specific clinical registries, to be harnessed because they are capable of efficiently identifying salient variables associated with outcomes and delineating their interdependencies. ML algorithms are computationally efficient, have strong predictive capabilities and can enable learning in the big data setting. ML algorithms can be viewed as providing a computational bridge from big data to complement PMX modelling. This review provides an overview of the strengths and weaknesses of ML approaches vis-à-vis population methods, assesses current research into ML applications in the pharmaceutical sciences and provides perspective for potential opportunities and strategies for the successful integration and utilization of ML in PMX.

A hybrid machine learning/pharmacokinetic approach outperforms maximum a posteriori Bayesian estimation by selectively flattening model priors

“…Applications of ML to MIPD to date have found that ML models are often able to accurately estimate past drug exposure 24,25 , predict future drug exposure 26-28 or select doses [29][30][31][32] . However, the improvement in accuracy from these earlier approaches comes at the expense of pharmacological interpretability and the ability to simulate patient response to alternative dosing regimens 24,33,34 . An advantage of the combination of ML and PK models as described here is that clinical decision making is augmented by ML while maintaining the ability to forecast patient PK and extract mechanistic insight from PK parameter estimates.…”

“… 29 , 30 , 31 , 32 However, the improvement in accuracy from these earlier approaches comes at the expense of pharmacological interpretability and the ability to simulate patient response to alternative dosing regimens. 24 , 33 , 34 An advantage of the combination of ML and PK models as described here is that clinical decision making is augmented by ML while maintaining the ability to forecast patient PKs and extract mechanistic insight from PK parameter estimates. Improving predictive performance for patients with unusual PKs by allowing more flexibility in individual PK parameters has been proposed before.…”

Pediatric Therapeutic Drug Monitoring for Selective Serotonin Reuptake Inhibitors

“…artificial intelligence can serve as a "computational bridge between big data and pharmacometrics," with specific applications towards TDM (e.g., pharmacokinetics/pharmacodynamics and dose optimization) (McComb et al, 2021). Development of tools that allow clinicians to input individual patient characteristics to predict their SSRI concentration comparable to current pharmacokinetic modeling could overcome some barriers of TDM for SSRIs (e.g., the need for phlebotomy, long turnaround times for assays).…”

Introduction of an artificial neural network–based method for concentration‐time predictions

“…They are used for text completion in emails 7 and autonomously driving cars 8 and have even been introduced in the discovery of new antibiotics 9 . Although ANNs have not yet been widely adopted in clinical pharmacology and pharmacometrics, multiple publications point to their potential to become an important tool in these subject areas as well 10–12 …”

“…9 Although ANNs have not yet been widely adopted in clinical pharmacology and pharmacometrics, multiple publications point to their potential to become an important tool in these subject areas as well. [10][11][12] In this article, we introduce the concept of ANNs to pharmacometricians, highlight their capability for concentration-time curve predictions, and discuss their differences and limitations compared with classical methods.…”