A machine learning approach to personalized dose adjustment of lamotrigine using noninvasive clinical parameters

Abstract

The pharmacokinetic variability of lamotrigine (LTG) plays a significant role in its dosing requirements. Our goal here was to use noninvasive clinical parameters to predict the dose-adjusted concentrations (C/D ratio) of LTG based on machine learning (ML) algorithms. A total of 1141 therapeutic drug-monitoring measurements were used, 80% of which were randomly selected as the "derivation cohort" to develop the prediction algorithm, and the remaining 20% constituted the "validation cohort" to test the finally selected model. Fifteen ML models were optimized and evaluated by tenfold cross-validation on the "derivation cohort,” and were filtered by the mean absolute error (MAE). On the whole, the nonlinear models outperformed the linear models. The extra-trees’ regression algorithm delivered good performance, and was chosen to establish the predictive model. The important features were then analyzed and parameters of the model adjusted to develop the best prediction model, which accurately described the C/D ratio of LTG, especially in the intermediate-to-high range (≥ 22.1 μg mL−1 g−1 day), as illustrated by a minimal bias (mean relative error (%) = + 3%), good precision (MAE = 8.7 μg mL−1 g−1 day), and a high percentage of predictions within ± 20% of the empirical values (60.47%). This is the first study, to the best of our knowledge, to use ML algorithms to predict the C/D ratio of LTG. The results here can help clinicians adjust doses of LTG administered to patients to minimize adverse reactions.

Combining Metabolomics and Interpretable Machine Learning to Reveal Plasma Metabolic Profiling and Biological Correlates of Alcohol-Dependent Inpatients: What About Tryptophan Metabolism Regulation?

“…Gamma-amino butyric acid (GABA) and NMDA receptors are two major receptors involved in AD, which are also believed to be important targets of alcohol (Peoples and Weight, 1999;Banerjee, 2014). Besides L-aspartic acid, glycine, glutamate, and D-serine can act as cofactors regulating the activity of the NMDA receptor (Zorumski and Izumi, 2012). The exact contributions of these amino acid cofactors to the activity of the NMDA receptor modulated by alcohol remain unclear (Ron and Wang, 2009).…”

“…Decision tree-based machine learning has been an emerging approach in metabolomics for disease discrimination and biomarker detection ( Allalou et al, 2016 ; Shao et al, 2017 ; Murata et al, 2019 ). In addition, comparing with linear regression and logistic regression models, decision trees are more successful in processing nonlinear relationships between input features and outcomes, particularly suitable for these situations existing in metabolomics due to the nonlinear and dynamic disease states ( Zhu et al, 2021c ).…”

Construction and Interpretation of Prediction Model of Teicoplanin Trough Concentration via Machine Learning

“…Its main ability is to gather and interpret any relevant data even on a large scale and thus, transforms medicine to a data-driven approach. Precision treatment is one of the top applications of machine learning, where a patient receives tailored medical care, such as personalized dose adjustment, plasma concentration prediction, and adverse drug events prediction (19)(20)(21)(22). Ensemble learning, one of the key features of machine learning, comes from a combination of various models that is capable of producing a final prediction.…”

Case Report: Predicting the Range of Lamotrigine Concentration Using Pharmacokinetic Models Based on Monte Carlo Simulation: A Case Study of Antiepileptic Drug-Related Leukopenia

“…Lamotrigine (LTG) is a new-generation antiepileptic drug, the pharmacokinetic (PK) variability of which plays a key role in dosing requirements for it ( Johannessen and Tomson, 2006 ). Multiple factors, such as the co-medication, concurrent diseases, age, body weight, pregnancy, and genetic polymorphisms, have been shown to affect its PK variability ( Wang et al, 2019 ; Methaneethorn and Leelakanok, 2020 ; Zhu et al, 2021 ). An increase in toxicity has been noted in definite relation to an increase in LTG concentration ( Hirsch et al, 2004 ), and the prevalence of toxicity increases significantly with LTG serum concentrations >15 mg/L ( Søndergaard Khinchi et al, 2008 ; Jacob and Nair, 2016 ).…”