An Ensemble Model for Prediction of Vancomycin Trough Concentrations in Pediatric Patients

Machine Learning: A New Approach for Dose Individualization

The application of machine learning (ML) has shown promising results in precision medicine due to its exceptional performance in dealing with complex multidimensional data. However, using ML for individualized dosing of medicines is still in its early stage, meriting further exploration. A systematic review of study designs and modeling details of using ML for individualized dosing of different drugs was performed. We have summarized the status of the study populations, predictive targets, and data sources for ML modeling, the selection of ML algorithms and features, and the evaluation and validation of their predictive performance. We also used the Prediction model Risk of Bias Assessment Tool (PROBAST) to assess the risk of bias of included studies. Currently, ML can be used for both a priori and a posteriori dose selection and optimization, and it can also assist the implementation of therapeutic drug monitoring. However, studies are mainly focused on drugs with narrow therapeutic windows, predominantly immunosuppressants (N = 23, 35.9%) and anti-infectives (N = 21, 32.8%), and there is currently only very limited attention for special populations, such as children (N = 22, 34.4%). Most studies showed poor methodological quality and a high risk of bias. The lack of external validation and clinical utility evaluation currently limits the further clinical implementation of ML for dose individualization. We therefore have proposed several ways to improve the clinical relevance of the studies and facilitate the translation of ML models into clinical practice.

Machine learning-based prediction of sertraline concentration in patients with depression through therapeutic drug monitoring

Background: Sertraline is a commonly employed antidepressant in clinical practice. In order to control the plasma concentration of sertraline within the therapeutic window to achieve the best effect and avoid adverse reactions, a personalized model to predict sertraline concentration is necessary. Aims: This study aimed to establish a personalized medication model for patients with depression receiving sertraline based on machine learning to provide a reference for clinicians to formulate drug regimens. Methods: A total of 415 patients with 496 samples of sertraline concentration from December 2019 to July 2022 at the First Hospital of Hebei Medical University were collected as the dataset. Nine different algorithms, namely, XGBoost, LightGBM, CatBoost, random forest, GBDT, SVM, lasso regression, ANN, and TabNet, were used for modeling to compare the model abilities to predict sertraline concentration. Results: XGBoost was chosen to establish the personalized medication model with the best performance (R 2 = 0.63). Five important variables, namely, sertraline dose, alanine transaminase, aspartate transaminase, uric acid, and sex, were shown to be correlated with sertraline concentration. The model prediction accuracy of sertraline concentration in the therapeutic window was 62.5%. Conclusion: In conclusion, the personalized medication model of sertraline for patients with depression based on XGBoost had good predictive ability, which provides guidance for clinicians in proposing an optimal medication regimen.

Predicting quetiapine dose in patients with depression using machine learning techniques based on real-world evidence

BACKGROUND

Being one of the most widespread, pervasive, and troublesome illnesses in the world, depression causes dysfunction in various spheres of individual and social life. Regrettably, despite obtaining evidence-based antidepressant medication, up to 70% of people are going to continue to experience troublesome symptoms. Quetiapine, as one of the most commonly prescribed antipsychotic medication worldwide, has been reported as an effective augmentation strategy to antidepressants. The right quetiapine dose and personalized quetiapine treatment are frequently challenging for clinicians. This study aimed to identify important influencing variables for quetiapine dose by maximizing the use of data from real world, and develop a predictive model of quetiapine dose through machine learning techniques to support selections for treatment regimens.

METHODS

The study comprised 308 depressed patients who were medicated with quetiapine and hospitalized in the First Hospital of Hebei Medical University, from November 1, 2019, to August 31, 2022. To identify the important variables influencing the dose of quetiapine, a univariate analysis was applied. The prediction abilities of nine machine learning models (XGBoost, LightGBM, RF, GBDT, SVM, LR, ANN, DT) were compared. Algorithm with the optimal model performance was chosen to develop the prediction model.

RESULTS

Four predictors were selected from 38 variables by the univariate analysis (p < 0.05), including quetiapine TDM value, age, mean corpuscular hemoglobin concentration, and total bile acid. Ultimately, the XGBoost algorithm was used to create a prediction model for quetiapine dose that had the greatest predictive performance (accuracy = 0.69) out of nine models. In the testing cohort (62 cases), a total of 43 cases were correctly predicted of the quetiapine dose regimen. In dose subgroup analysis, AUROC for patients with daily dose of 100 mg, 200 mg, 300 mg and 400 mg were 0.99, 0.75, 0.93 and 0.86, respectively.

CONCLUSIONS

In this work, machine learning techniques are used for the first time to estimate the dose of quetiapine for patients with depression, which is valuable for the clinical drug recommendations.

Prediction of plasma trough concentration of voriconazole in adult patients using machine learning

OBJECTIVE

Plasma trough concentration of voriconazole (VCZ) was associated with its toxicity and efficacy. However, the nonlinear pharmacokinetic characteristics of VCZ make it difficult to determine the relationship between clinical characteristics and its concentration. We intended to present a machine learning (ML)-based method to predict toxic plasma trough concentration of VCZ (>5 μg/mL).

METHODS

A single center retrospective study was conducted. Three ML algorithms were used to estimate the concentration in adult patients, including random forest (RF), gradient boosting (GB), and extreme gradient boosting (XGBoost). The importance of variables was recognized by the SHapley Additive exPlanations (SHAP) method. In addition, an external validation set was used to validate the robustness of models.

RESULTS

A total of 1318 VCZ plasma concentration were included, with 33 variables enrolled in the model. Nine classification models were developed using the RF, GB, and XGBoost algorithms. Most models performed well for both the training set and test set, with an average balanced accuracy (BA) of 0.704 and an average accuracy (ACC) of 0.788. In addition, the average Matthews correlation coefficient value reached 0.484, which indicated the predicted values are meaningful. Based on the average BA and ACC values, the predictive ability of the models can be ranked from best to worst as follows: younger adult models > mixed models > elderly models, and XGBoost models > GBT models > RF models. The SHAP results showed that the top five influencing factors in younger adult patients (<60 years) were albumin, total bile acid (TBA), platelets count, age, and inflammation, while the top five influencing factors in elderly patients were albumin, TBA, aspartate aminotransferase, creatinine, and alanine aminotransferase. Furthermore, the prediction of external validation set for VCZ concentrations verified the high reliability of the models, for the ACC value of 0.822 by the best model.

CONCLUSIONS

The ML models can be reliable tools for predicting toxic concentration exposure of VCZ. The SHAP results may provide useful guidelines for dosage adjustment of VCZ.

A machine learning model for predicting blood concentration of quetiapine in patients with schizophrenia and depression based on real-world data

AIMS

This study aimed to establish a prediction model of quetiapine concentration in patients with schizophrenia and depression, based on real-world data via machine learning techniques to assist clinical regimen decisions.

METHODS

A total of 650 cases of quetiapine therapeutic drug monitoring (TDM) data from 483 patients at the First Hospital of Hebei Medical University from 1 November 2019 to 31 August 2022 were included in the study. Univariate analysis and sequential forward selection (SFS) were implemented to screen the important variables influencing quetiapine TDM. After 10-fold cross validation, the algorithm with the optimal model performance was selected for predicting quetiapine TDM among nine models. SHapley Additive exPlanation was applied for model interpretation.

RESULTS

Four variables (daily dose of quetiapine, type of mental illness, sex and CYP2D6 competitive substrates) were selected through univariate analysis (P < .05) and SFS to establish the models. The CatBoost algorithm with the best predictive ability (mean [SD] R2  = 0.63 ± 0.02, RMSE = 137.39 ± 10.56, MAE = 103.24 ± 7.23) was chosen for predicting quetiapine TDM among nine models. The mean (SD) accuracy of the predicted TDM within ±30% of the actual TDM was 49.46 ± 3.00%, and that of the recommended therapeutic range (200-750 ng mL-1 ) was 73.54 ± 8.3%. Compared with the PBPK model in a previous study, the CatBoost model shows slightly higher accuracy within ±100% of the actual value.

CONCLUSIONS

This work is the first real-world study to predict the blood concentration of quetiapine in patients with schizophrenia and depression using artificial intelligent techniques, which is of significance and value for clinical medication guidance.

Use of Machine Learning for Dosage Individualization of Vancomycin in Neonates

BACKGROUND AND OBJECTIVE

High variability in vancomycin exposure in neonates requires advanced individualized dosing regimens. Achieving steady-state trough concentration (C0) and steady-state area-under-curve (AUC0-24) targets is important to optimize treatment. The objective was to evaluate whether machine learning (ML) can be used to predict these treatment targets to calculate optimal individual dosing regimens under intermittent administration conditions.

METHODS

C0 were retrieved from a large neonatal vancomycin dataset. Individual estimates of AUC0-24 were obtained from Bayesian post hoc estimation. Various ML algorithms were used for model building to C0 and AUC0-24. An external dataset was used for predictive performance evaluation.

RESULTS

Before starting treatment, C0 can be predicted a priori using the Catboost-based C0-ML model combined with dosing regimen and nine covariates. External validation results showed a 42.5% improvement in prediction accuracy by using the ML model compared with the population pharmacokinetic model. The virtual trial showed that using the ML optimized dose; 80.3% of the virtual neonates achieved the pharmacodynamic target (C0 in the range of 10-20 mg/L), much higher than the international standard dose (37.7-61.5%). Once therapeutic drug monitoring (TDM) measurements (C0) in patients have been obtained, AUC0-24 can be further predicted using the Catboost-based AUC-ML model combined with C0 and nine covariates. External validation results showed that the AUC-ML model can achieve an prediction accuracy of 80.3%.

CONCLUSION

C0-based and AUC0-24-based ML models were developed accurately and precisely. These can be used for individual dose recommendations of vancomycin in neonates before treatment and dose revision after the first TDM result is obtained, respectively.

Predicting busulfan exposure in patients undergoing hematopoietic stem cell transplantation using machine learning techniques

PURPOSE

This study aimed to establish an optimal model to predict the busulfan (BU) area under the curve at steady state (AUCss) by using machine learning (ML).

PATIENTS AND METHODS

Seventy-nine adult patients (age ≥18 years) who received BU intravenously and underwent therapeutic drug monitoring from 2013 to 2021 at Fujian Medical University Union Hospital were enrolled in this retrospective study. The whole dataset was divided into a training group and test group at the ratio of 8:2. BU AUCss were considered as the target variable. Nine different ML algorithms and one population pharmacokinetic (pop PK) model were developed and validated, and their predictive performance was compared.

RESULTS

All ML models were superior to the pop PK model (R2 = 0.751, MSE = 0.722, 14 and RMSE = 0.830) in model fitting and had better predictive accuracy. The ML model of BU AUCss established through support vector regression (SVR) and gradient boosted regression trees (GBRT) had the best predictive ability (R2 = 0.953 and 0.953, MSE = 0.323 and 0.326, and RMSE = 0.423 and 0.425).

CONCLUSION

All the ML models can potentially be used to estimate BU AUCss with the aim of facilitating rational use of BU on the individualized level, especially models built by SVR and GBRT algorithms.

Vancomycin population pharmacokinetics analysis in Chinese paediatric patients with varying degrees of renal function and ages: development of new practical dosing recommendations

OBJECTIVES

To describe the pharmacokinetics of vancomycin in a large Chinese paediatric cohort with varying degrees of renal function and ages and to develop practical dosing guidelines.

PATIENTS AND METHODS

We conducted a retrospective population pharmacokinetic study using data from paediatric patients who received vancomycin between June 2013 and June 2022. A non-linear mixed-effect modelling approach with a one-compartment model structure was applied. Monte Carlo simulations were used to stimulate an optimal dosage regimen to achieve the target of AUC24/MIC between 400 and 650.

RESULTS

We analysed a total of 673 paediatric patients and 1547 vancomycin serum concentrations. Covariate analysis revealed that physiological maturation, renal function, albumin and cardiothoracic surgery (CTS) significantly affected vancomycin pharmacokinetics. The typical clearance and volume of distribution, standardized to 70 kg, were 7.75 L/h (2.3% relative standard error, RSE) and 36.2 L (1.7% RSE), respectively. Based on the model, we proposed an optimal dosing regimen that considers the patient's age and estimate glomerular filtration rate (eGFR) to achieve a target AUC24/MIC for CTS and non-CTS patients. We also found that a loading dose of 20 mg/kg can help patients with an eGFR of <60 mL/min/1.73 m2 achieve the target AUC on the first day of treatment.

CONCLUSIONS

We established vancomycin pharmacokinetic parameters in Chinese paediatric patients and proposed a dosing guideline integrating eGFR, age and CTS status, potentially improving clinical outcomes and reducing nephrotoxicity risk.

External Evaluation of Population Pharmacokinetic Models for Precision Dosing: Current State and Knowledge Gaps

Predicting drug exposures using population pharmacokinetic models through Bayesian forecasting software can improve individual pharmacokinetic/pharmacodynamic target attainment. However, selecting the most adapted model to be used is challenging due to the lack of guidance on how to design and interpret external evaluation studies. The confusion around the choice of statistical metrics and acceptability criteria emphasises the need for further research to fill this methodological gap as there is an urgent need for the development of standards and guidelines for external evaluation studies. Herein we discuss the scientific challenges faced by pharmacometric researchers and opportunities for future research with a focus on antibiotics.

A model based on machine learning for the prediction of cyclosporin A trough concentration in Chinese allo-HSCT patients

BACKGROUND

Cyclosporin A is a calcineurin inhibitor which has a narrow therapeutic window and high interindividual variability. Various population pharmacokinetic models have been reported; however, professional software and technical personnel were needed and the variables of the models were limited. Therefore, the aim of this study was to establish a model based on machine learning to predict CsA trough concentrations in Chinese allo-HSCT patients.

METHODS

A total of 7874 cases of CsA therapeutic drug monitoring data from 2069 allo-HSCT patients were retrospectively included. Sequential forward selection was used to select variable subsets, and eight different algorithms were applied to establish the prediction model.

RESULTS

XGBoost exhibited the highest prediction ability. Except for the variables that were identified by previous studies, some rarely reported variables were found, such as norethindrone, WBC, PAB, and hCRP. The prediction accuracy within ±30% of the actual trough concentration was above 0.80, and the predictive ability of the models was demonstrated to be effective in external validation.

CONCLUSION

In this study, models based on machine learning technology were established to predict CsA levels 3-4 days in advance during the early inpatient phase after HSCT. A new perspective for CsA clinical application is provided.

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

Background and Aim: Many studies associated with the combination of machine learning (ML) and pharmacometrics have appeared in recent years. ML can be used as an initial step for fast screening of covariates in population pharmacokinetic (popPK) models. The present study aimed to integrate covariates derived from different popPK models using ML.

Methods: Two published popPK models of valproic acid (VPA) in Chinese epileptic patients were used, where the population parameters were influenced by some covariates. Based on the covariates and a one-compartment model that describes the pharmacokinetics of VPA, a dataset was constructed using Monte Carlo simulation, to develop an XGBoost model to estimate the steady-state concentrations (Css) of VPA. We utilized SHapley Additive exPlanation (SHAP) values to interpret the prediction model, and calculated estimates of VPA exposure in four assumed scenarios involving different combinations of CYP2C19 genotypes and co-administered antiepileptic drugs. To develop an easy-to-use model in the clinic, we built a simplified model by using CYP2C19 genotypes and some noninvasive clinical parameters, and omitting several features that were infrequently measured or whose clinically available values were inaccurate, and verified it on our independent external dataset.

Results: After data preprocessing, the finally generated combined dataset was divided into a derivation cohort and a validation cohort (8:2). The XGBoost model was developed in the derivation cohort and yielded excellent performance in the validation cohort with a mean absolute error of 2.4 mg/L, root-mean-squared error of 3.3 mg/L, mean relative error of 0%, and percentages within ±20% of actual values of 98.85%. The SHAP analysis revealed that daily dose, time, CYP2C19*2 and/or *3 variants, albumin, body weight, single dose, and CYP2C19*1*1 genotype were the top seven confounding factors influencing the Css of VPA. Under the simulated dosage regimen of 500 mg/bid, the VPA exposure in patients who had CYP2C19*2 and/or *3 variants and no carbamazepine, phenytoin, or phenobarbital treatment, was approximately 1.74-fold compared to those with CYP2C19*1/*1 genotype and co-administered carbamazepine + phenytoin + phenobarbital. The feasibility of the simplified model was fully illustrated by its performance in our external dataset.

Conclusion: This study highlighted the bridging role of ML in big data and pharmacometrics, by integrating covariates derived from different popPK models.

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

Background and Aim: Therapeutic drug monitoring (TDM) has evolved over the years as an important tool for personalized medicine. Nevertheless, some limitations are associated with traditional TDM. Emerging data-driven model forecasting [e.g., through machine learning (ML)-based approaches] has been used for individualized therapy. This study proposes an interpretable stacking-based ML framework to predict concentrations in real time after olanzapine (OLZ) treatment.

Methods: The TDM-OLZ dataset, consisting of 2,142 OLZ measurements and 472 features, was formed by collecting electronic health records during the TDM of 927 patients who had received OLZ treatment. We compared the performance of ML algorithms by using 10-fold cross-validation and the mean absolute error (MAE). The optimal subset of features was analyzed by a random forest-based sequential forward feature selection method in the context of the top five heterogeneous regressors as base models to develop a stacked ensemble regressor, which was then optimized via the grid search method. Its predictions were explained by using local interpretable model-agnostic explanations (LIME) and partial dependence plots (PDPs).

Results: A state-of-the-art stacking ensemble learning framework that integrates optimized extra trees, XGBoost, random forest, bagging, and gradient-boosting regressors was developed for nine selected features [i.e., daily dose (OLZ), gender_male, age, valproic acid_yes, ALT, K, BW, MONO#, and time of blood sampling after first administration]. It outperformed other base regressors that were considered, with an MAE of 0.064, R-square value of 0.5355, mean squared error of 0.0089, mean relative error of 13%, and ideal rate (the percentages of predicted TDM within ± 30% of actual TDM) of 63.40%. Predictions at the individual level were illustrated by LIME plots, whereas the global interpretation of associations between features and outcomes was illustrated by PDPs.

Conclusion: This study highlights the feasibility of the real-time estimation of drug concentrations by using stacking-based ML strategies without losing interpretability, thus facilitating model-informed precision dosing.

Adoption of Machine Learning in Pharmacometrics: An Overview of Recent Implementations and Their Considerations

Pharmacometrics is a multidisciplinary field utilizing mathematical models of physiology, pharmacology, and disease to describe and quantify the interactions between medication and patient. As these models become more and more advanced, the need for advanced data analysis tools grows. Recently, there has been much interest in the adoption of machine learning (ML) algorithms. These algorithms offer strong function approximation capabilities and might reduce the time spent on model development. However, ML tools are not yet an integral part of the pharmacometrics workflow. The goal of this work is to discuss how ML algorithms have been applied in four stages of the pharmacometrics pipeline: data preparation, hypothesis generation, predictive modelling, and model validation. We will also discuss considerations before the use of ML algorithms with respect to each topic. We conclude by summarizing applications that hold potential for adoption by pharmacometricians.

Long Short-Term Memory Network for Development and Simulation of Warfarin Dosing Model Based on Time Series Anticoagulant Data

Background

Warfarin is an effective treatment for thromboembolic disease but has a narrow therapeutic index, and dosage can differ tremendously among individuals. The study aimed to develop an individualized international normalized ratio (INR) model based on time series anticoagulant data and simulate individualized warfarin dosing.

Methods

We used a long short-term memory (LSTM) network to develop an individualized INR model based on data from 4,578 follow-up visits, including clinical and genetic factors from 624 patients whom we enrolled in our previous randomized controlled trial. The data of 158 patients who underwent valvular surgery and were included in a prospective registry study were used for external validation in the real world.

Results

The prediction accuracy of LSTM_INR was 70.0%, which was much higher than that of MAPB_INR (maximum posterior Bayesian, 53.9%). Temporal variables were significant for LSTM_INR performance (51.7 vs. 70.0%, P < 0.05). Genetic factors played an important role in predicting INR at the onset of therapy, while after 15 days of treatment, we found that it might unnecessary to detect genotypes for warfarin dosing. Using LSTM_INR, we successfully simulated individualized warfarin dosing and developed an application (AI-WAR) for individualized warfarin therapy.

Conclusion

The results indicate that temporal variables are necessary to be considered in warfarin therapy, except for clinical factors and genetic factors. LSTM network may have great potential for long-term drug individualized therapy.

Trial Registration

NCT02211326; www.chictr.org.cn:ChiCTR2100052089.

Application of Machine Learning Classification to Improve the Performance of Vancomycin Therapeutic Drug Monitoring

Bayesian therapeutic drug monitoring (TDM) software uses a reported pharmacokinetic (PK) model as prior information. Since its estimation is based on the Bayesian method, the estimation performance of TDM software can be improved using a PK model with characteristics similar to those of a patient. Therefore, we aimed to develop a classifier using machine learning (ML) to select a more suitable vancomycin PK model for TDM in a patient. In our study, nine vancomycin PK studies were selected, and a classifier was created to choose suitable models among them for patients. The classifier was trained using 900,000 virtual patients, and its performance was evaluated using 9000 and 4000 virtual patients for internal and external validation, respectively. The accuracy of the classifier ranged from 20.8% to 71.6% in the simulation scenarios. TDM using the ML classifier showed stable results compared with that using single models without the ML classifier. Based on these results, we have discussed further development of TDM using ML. In conclusion, we developed and evaluated a new method for selecting a PK model for TDM using ML. With more information, such as on additional PK model reporting and ML model improvement, this method can be further enhanced.

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

Objective

To establish an optimal model to predict the teicoplanin trough concentrations by machine learning, and explain the feature importance in the prediction model using the SHapley Additive exPlanation (SHAP) method.

Methods

A retrospective study was performed on 279 therapeutic drug monitoring (TDM) measurements obtained from 192 patients who were treated with teicoplanin intravenously at the First Affiliated Hospital of Army Medical University from November 2017 to July 2021. This study included 27 variables, and the teicoplanin trough concentrations were considered as the target variable. The whole dataset was divided into a training group and testing group at the ratio of 8:2, and predictive performance was compared among six different algorithms. Algorithms with higher model performance (top 3) were selected to establish the ensemble prediction model and SHAP was employed to interpret the model.

Results

Three algorithms (SVR, GBRT, and RF) with high R² scores (0.676, 0.670, and 0.656, respectively) were selected to construct the ensemble model at the ratio of 6:3:1. The model with R² = 0.720, MAE = 3.628, MSE = 22.571, absolute accuracy of 83.93%, and relative accuracy of 60.71% was obtained, which performed better in model fitting and had better prediction accuracy than any single algorithm. The feature importance and direction of each variable were visually demonstrated by SHAP values, in which teicoplanin administration and renal function were the most important factors.

Conclusion

We firstly adopted a machine learning approach to predict the teicoplanin trough concentration, and interpreted the prediction model by the SHAP method, which is of great significance and value for the clinical medication guidance.

Case Report: Monitoring Vancomycin Concentrations and Pharmacokinetic Parameters in Continuous Veno-Venous Hemofiltration Patients to Guide Individualized Dosage Regimens: A Case Analysis

There are limited pharmacokinetic (PK) studies on vancomycin in patients treated with continuous renal replacement therapy (CRRT), and the results have been inconsistent. Because of individual differences, proposing a definite recommendation for the clinical regimen is not possible. Rapidly reaching target vancomycin concentrations will facilitate effective treatment for critically ill patients treated with CRRT. In this study, to understand the dynamic change in drug clearance rates in vivo, analyze the effect of PK changes on drug concentrations, and recommend loading and maintenance dosage regimens, we monitored the blood concentrations of vancomycin and calculated the area under the curve in two critically ill patients treated with vancomycin and continuous veno-venous hemofiltration (CVVH). On the basis of real-time therapeutic drug monitoring results and PK parameters, an individualized vancomycin regimen was developed for patients with CVVH. Good clinical efficacy was achieved, which provided support and reference for empirical vancomycin therapy in these patients.

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

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 R ² (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.