A Machine Learning Model to Predict Risperidone Active Moiety Concentration Based on Initial Therapeutic Drug Monitoring

Abstract

Risperidone is an efficacious second-generation antipsychotic (SGA) to treat a wide spectrum of psychiatric diseases, whereas its active moiety (risperidone and 9-hydroxyrisperidone) concentration without a therapeutic reference range may increase the risk of adverse drug reactions. We aimed to establish a prediction model of risperidone active moiety concentration in the next therapeutic drug monitoring (TDM) based on the initial TDM information using machine learning methods. A total of 983 patients treated with risperidone between May 2017 and May 2018 in Beijing Anding Hospital were collected as the data set. Sixteen predictors (the initial TDM value, dosage, age, WBC, PLT, BUN, weight, BMI, prolactin, ALT, MECT, Cr, AST, Ccr, TDM interval, and RBC) were screened from 26 variables through univariate analysis (p < 0.05) and XGBoost (importance score >0). Ten algorithms (XGBoost, LightGBM, CatBoost, AdaBoost, Random Forest, support vector machine, lasso regression, ridge regression, linear regression, and k-nearest neighbor) compared the model performance, and ultimately, XGBoost was chosen to establish the prediction model. A cohort of 210 patients treated with risperidone between March 1, 2019, and May 31, 2019, in Beijing Anding Hospital was used to validate the model. Finally, the prediction model was evaluated, obtaining R2 (0.512 in test cohort; 0.374 in validation cohort), MAE (10.97 in test cohort; 12.07 in validation cohort), MSE (198.55 in test cohort; 324.15 in validation cohort), RMSE (14.09 in test cohort; 18.00 in validation cohort), and accuracy of the predicted TDM within ±30% of the actual TDM (54.82% in test cohort; 60.95% in validation cohort). The prediction model has promising performance to facilitate rational risperidone regimen on an individualized level and provide reference for other antipsychotic drugs' risk prediction.

Machine learning advances the integration of covariates in population pharmacokinetic models: Valproic acid as an example

“…Compared with the initially proposed XGBoost model, the reduced performance of our simplified XGBoost model indicated the important influences of these features, particularly the blood sampling time and ALB, on the model output. Nevertheless, a 60.00% IR of the simplified optimum XGBoost model on our external dataset suggested its good forecasting performance, considering the prediction accuracy of the predicted TDM within ±30% of the actual TDM in many similar studies that utilized XGBoost models, ranging from 40% to 75% (Huang et al, 2021b;Guo et al, 2021;Zheng et al, 2021;Ma et al, 2022). Based on the simplified optimum XGBoost model, we designed an easy-to-use web application by using only CYP2C19 genotypes and some noninvasive clinical parameters as an MIPD tool for personalized dosing adjustments.…”

An interpretable stacking ensemble learning framework based on multi-dimensional data for real-time prediction of drug concentration: The example of olanzapine

“…Unlike previous studies that used only homogeneous ensembles (e.g., XGBoost) or simple weighted average ensembles for ML-assisted TDM ( Zhu et al, 2021a ; Guo et al, 2021 ; Hsu et al, 2021 ; Huang et al, 2021 ; Zheng et al, 2021 ; Lee et al, 2022 ), our is the first study, to the best of our knowledge, to explore the real-time estimation of drug concentrations by using a stacking ensemble framework as an MIPD tool. Our work here shows that stacking a heterogeneous ensemble, overall, is superior to homogeneous ensemble-based methods (e.g., bagging and XGBoost models) on several comparisons of model performance on the TDM-OLZ dataset.…”

“…Aside from the MAE, the following evaluation metrics were used to quantitatively evaluate the performance of the models: R-square ( ), mean squared error (MSE) ( Cesar de Azevedo et al, 2021 ), mean relative error (MRE) (%) ( Zhu et al, 2021a ), and ideal rate (IR) (%) ( Guo et al, 2021 ). These indices were calculated as follows: where , , and are the predicted, measured values, and the mean values, respectively.…”

“…A previous study used the extra trees-based regression algorithm to establish a predictive model for dose-adjusted concentrations of lamotrigine ( Zhu et al, 2021a ). Guo et al (2021) established an eXtreme gradient boosting (XGBoost) model for the prediction of the active moiety of risperidone in the next TDM based on the initial TDM. Both of these studies evaluated a variety of ML models.…”

Development and evaluation of uncertainty quantifying machine learning models to predict piperacillin plasma concentrations in critically ill patients

“…Earlier works already explored the idea of using various ML models, such as support vector machines, gradient boosting trees, XGBoost, and neural networks, to predict drug concentrations for tacrolimus, remifentanil, gentamicin, risperidone, teicoplanin, phenytoin, and warfarin [22][23][24][25][26][27][28][29]. A recent study explained and validated the predictions of teicoplanin trough concentrations using Shapley values while combining the best models into a single ensemble [28,30].…”