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

A simulation study to assess the influence of population pharmacokinetic model selection on initial dosing recommendations of vancomycin in neonates

AIMS

The accuracy of model-informed precision dosing largely depends on selecting the most appropriate population pharmacokinetic (popPK) model from many available options. This study aims to evaluate the concordance of optimal initial simulated doses among various vancomycin popPK models developed in neonates and to explore the role of predictive performance in explaining the variability in probability of target attainment (PTA).

METHODS

A virtual neonatal patient population was created and 26 previously externally evaluated vancomycin popPK models were used to simulate 5 different dosing regimens. For each simulated scenario, the area under the concentration-time curve and PTA were calculated to assess the agreement on optimal initial doses across the 26 models. A multiple regression was performed to explore the impact of the models' predictive performance on PTA.

RESULTS

For most models (15/26), there was an agreement on the optimal dosing regimen. The highest PTA being achieved by the model with the best a priori predictive performance. The multiple regression model significantly predicted mean ln-transformed PTA, with F(2, 23) = 5.406 and P = .010, yielding an adjusted R2 of .21. PTA was significantly influenced by imprecision (P = .048) but not bias (P = .469).

CONCLUSION

In conclusion, our study demonstrated that, despite the variability in bias and imprecision, there was a consensus on the initial optimal doses for the majority of models; however, models with superior a priori predictive performance yielded higher PTA values. Bias and imprecision alone only seem to predict a small proportion of the variability in PTA, with imprecision having a more pronounced effect.

Prediction Trough Concentrations of Valproic Acid Among Chinese Adult Patients with Epilepsy Using Machine Learning Techniques

OBJECTIVE

This study aimed to establish an optimal model based on machine learning (ML) to predict Valproic acid (VPA) trough concentrations in Chinese adult epilepsy patients.

METHODS

A single-center retrospective study was carried out at the Jinshan Hospital affiliated with Fudan University from January 2022 to December 2023. A total of 102 VPA trough concentrations were split into a derivation cohort and a validation cohort at a ratio of 8:2. Thirteen ML algorithms were developed using 27 variables in the derivation cohort and were filtered by the lowest mean absolute error (MAE) value. In addition, feature selection was applied to optimize the model.

RESULTS

Ultimately, the extra tree algorithm was chosen to establish the personalized VPA trough concentration prediction model due to its best performance (MAE = 13.08). The SHapley Additive exPlanations (SHAP) plots were used to visualize and rank the importance of features, providing insights into how each feature influences the model's predictions. After feature selection, we found that the model with the top 9 variables [including daily dose, last dose, uric acid (UA), platelet (PLT), combination, gender, weight, albumin (ALB), aspartate aminotransferase (AST)] outperformed the model with 27 variables, with MAE of 6.82, RMSE of 9.62, R2 value of 0.720, relative accuracy (±20%) of 61.90%, and absolute accuracy (±20 mg/L) of 90.48%.

CONCLUSION

In conclusion, the trough concentration prediction model for VPA in Chinese adult epileptic patients based on the extra tree algorithm demonstrated strong predictive ability which is valuable for clinicians in medication guidance.

Prediction of teicoplanin plasma concentration in critically ill patients: a combination of machine learning and population pharmacokinetics

BACKGROUND

Teicoplanin has been widely used in patients with infections caused by Staphylococcus aureus, especially for critically ill patients. The pharmacokinetics (PK) of teicoplanin vary between individuals and within the same individual. We aim to establish a prediction model via a combination of machine learning and population PK (PPK) to support personalized medication decisions for critically ill patients.

METHODS

A retrospective study was performed incorporating 33 variables, including PPK parameters (clearance and volume of distribution). Multiple algorithms and Shapley additive explanations were employed for feature selection of variables to determine the strongest driving factors.

RESULTS

The performance of each algorithm with PPK parameters was superior to that without PPK parameters. The composition of support vector regression, categorical boosting and a backpropagation neural network (7:2:1) with the highest R2 (0.809) was determined as the final ensemble model. The model included 15 variables after feature selection, of which the predictive performance was superior to that of models considering all variables or using only PPK. The R2, mean absolute error, mean squared error, absolute accuracy (±5 mg/L) and relative accuracy (±30%) of external validation were 0.649, 3.913, 28.347, 76.12% and 76.12%, respectively.

CONCLUSIONS

Our study offers a non-invasive, fast and cost-effective prediction model of teicoplanin plasma concentration in critically ill patients. The model serves as a fundamental tool for clinicians to determine the effective plasma concentration range of teicoplanin and formulate individualized dosing regimens accordingly.

Development and validation of an automatic machine learning model to predict abnormal increase of transaminase in valproic acid-treated epilepsy

Valproic acid (VPA) is a primary medication for epilepsy, yet its hepatotoxicity consistently raises concerns among individuals. This study aims to establish an automated machine learning (autoML) model for forecasting the risk of abnormal increase of transaminase levels while undergoing VPA therapy for 1995 epilepsy patients. The study employed the two-tailed T test, Chi-square test, and binary logistic regression analysis, selecting six clinical parameters, including age, stature, leukocyte count, Total Bilirubin, oral dosage of VPA, and VPA concentration. These variables were used to build a risk prediction model using "H2O" autoML platform, achieving the best performance (AUC training = 0.855, AUC test = 0.789) in the training and testing data set. The model also exhibited robust accuracy (AUC valid = 0.742) in an external validation set, underscoring its credibility in anticipating VPA-induced transaminase abnormalities. The significance of the six variables was elucidated through importance ranking, partial dependence, and the TreeSHAP algorithm. This novel model offers enhanced versatility and explicability, rendering it suitable for clinicians seeking to refine parameter adjustments and address imbalanced data sets, thereby bolstering classification precision. To summarize, the personalized prediction model for VPA-treated epilepsy, established with an autoML model, displayed commendable predictive capability, furnishing clinicians with valuable insights for fostering pharmacovigilance.

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.

Clinical decision support for chemotherapy-induced neutropenia using a hybrid pharmacodynamic/machine learning model

Consensus guidelines recommend use of granulocyte colony stimulating factor in patients deemed at risk of chemotherapy-induced neutropenia, however, these risk models are limited in the factors they consider and miss some cases of neutropenia. Clinical decision making could be supported using models that better tailor their predictions to the individual patient using the wealth of data available in electronic health records (EHRs). Here, we present a hybrid pharmacokinetic/pharmacodynamic (PKPD)/machine learning (ML) approach that uses predictions and individual Bayesian parameter estimates from a PKPD model to enrich an ML model built on her data. We demonstrate this approach using models developed on a large real-world data set of 9121 patients treated for lymphoma, breast, or thoracic cancer. We also investigate the benefits of augmenting the training data using synthetic data simulated with the PKPD model. We find that PKPD-enrichment of ML models improves prediction of grade 3-4 neutropenia, as measured by higher precision (61%) and recall (39%) compared to PKPD model predictions (47%, 33%) or base ML model predictions (51%, 31%). PKPD augmentation of ML models showed minor improvements in recall (44%) but not precision (56%), and data augmentation required careful tuning to control overfitting its predictions to the PKPD model. PKPD enrichment of ML shows promise for leveraging both the physiology-informed predictions of PKPD and the ability of ML to learn predictor-outcome relationships from large data sets to predict patient response to drugs in a clinical precision dosing context.

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.

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.

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

BACKGROUND

Beta-lactam antimicrobial concentrations are frequently suboptimal in critically ill patients. Population pharmacokinetic (PopPK) modeling is the golden standard to predict drug concentrations. However, currently available PopPK models often lack predictive accuracy, making them less suited to guide dosing regimen adaptations. Furthermore, many currently developed models for clinical applications often lack uncertainty quantification. We, therefore, aimed to develop machine learning (ML) models for the prediction of piperacillin plasma concentrations while also providing uncertainty quantification with the aim of clinical practice.

METHODS

Blood samples for piperacillin analysis were prospectively collected from critically ill patients receiving continuous infusion of piperacillin/tazobactam. Interpretable ML models for the prediction of piperacillin concentrations were designed using CatBoost and Gaussian processes. Distribution-based Uncertainty Quantification was added to the CatBoost model using a proposed Quantile Ensemble method, useable for any model optimizing a quantile function. These models are subsequently evaluated using the distribution coverage error, a proposed interpretable uncertainty quantification calibration metric. Development and internal evaluation of the ML models were performed on the Ghent University Hospital database (752 piperacillin concentrations from 282 patients). Ensuing, ML models were compared with a published PopPK model on a database from the University Medical Centre of Groningen where a different dosing regimen is used (46 piperacillin concentrations from 15 patients.).

RESULTS

The best performing model was the Catboost model with an RMSE and [Formula: see text] of 31.94-0.64 and 33.53-0.60 for internal evaluation with and without previous concentration. Furthermore, the results prove the added value of the proposed Quantile Ensemble model in providing clinically useful individualized uncertainty predictions and show the limits of homoscedastic methods like Gaussian Processes in clinical applications.

CONCLUSIONS

Our results show that ML models can consistently estimate piperacillin concentrations with acceptable and high predictive accuracy when identical dosing regimens as in the training data are used while providing highly relevant uncertainty predictions. However, generalization capabilities to other dosing schemes are limited. Notwithstanding, incorporating ML models in therapeutic drug monitoring programs seems definitely promising and the current work provides a basis for validating the model in clinical practice.

Use of Antibiotics in Preterm Newborns

Due to complex maturational and physiological changes that characterize neonates and affect their response to pharmacological treatments, neonatal pharmacology is different from children and adults and deserves particular attention. Although preterms are usually considered part of the neonatal population, they have physiological and pharmacological hallmarks different from full-terms and, therefore, need specific considerations. Antibiotics are widely used among preterms. In fact, during their stay in neonatal intensive care units (NICUs), invasive procedures, including central catheters for parental nutrition and ventilators for respiratory support, are often sources of microbes and require antimicrobial treatments. Unfortunately, the majority of drugs administered to neonates are off-label due to the lack of clinical studies conducted on this special population. In fact, physiological and ethical concerns represent a huge limit in performing pharmacokinetic (PK) studies on these subjects, since they limit the number and volume of blood sampling. Therapeutic drug monitoring (TDM) is a useful tool that allows dose adjustments aiming to fit plasma concentrations within the therapeutic range and to reach specific drug target attainment. In this review of the last ten years’ literature, we performed Pubmed research aiming to summarize the PK aspects for the most used antibiotics in preterms.