Deep Learning Methods Applied to Drug Concentration Prediction of Olanzapine
Pharmacometrics and the utilization of population pharmacokinetics play an integral role in model-informed drug discovery and development (MIDD). Recently, there has been a growth in the application of deep learning approaches to aid in areas within MIDD. In this study, a deep learning model, LSTM-A...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Pharmaceutics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4923/15/4/1139 |
| _version_ | 1827744078135033856 |
|---|---|
| author | Richard Khusial Robert R. Bies Ayman Akil |
| author_facet | Richard Khusial Robert R. Bies Ayman Akil |
| author_sort | Richard Khusial |
| collection | DOAJ |
| description | Pharmacometrics and the utilization of population pharmacokinetics play an integral role in model-informed drug discovery and development (MIDD). Recently, there has been a growth in the application of deep learning approaches to aid in areas within MIDD. In this study, a deep learning model, LSTM-ANN, was developed to predict olanzapine drug concentrations from the CATIE study. A total of 1527 olanzapine drug concentrations from 523 individuals along with 11 patient-specific covariates were used in model development. The hyperparameters of the LSTM-ANN model were optimized through a Bayesian optimization algorithm. A population pharmacokinetic model using the NONMEM model was constructed as a reference to compare to the performance of the LSTM-ANN model. The RMSE of the LSTM-ANN model was 29.566 in the validation set, while the RMSE of the NONMEM model was 31.129. Permutation importance revealed that age, sex, and smoking were highly influential covariates in the LSTM-ANN model. The LSTM-ANN model showed potential in the application of drug concentration predictions as it was able to capture the relationships within a sparsely sampled pharmacokinetic dataset and perform comparably to the NONMEM model. |
| first_indexed | 2024-03-11T04:38:51Z |
| format | Article |
| id | doaj.art-f7df49c5ef6b459888c680de4f2f76f2 |
| institution | Directory Open Access Journal |
| issn | 1999-4923 |
| language | English |
| last_indexed | 2024-03-11T04:38:51Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Pharmaceutics |
| spelling | doaj.art-f7df49c5ef6b459888c680de4f2f76f22023-11-17T20:53:17ZengMDPI AGPharmaceutics1999-49232023-04-01154113910.3390/pharmaceutics15041139Deep Learning Methods Applied to Drug Concentration Prediction of OlanzapineRichard Khusial0Robert R. Bies1Ayman Akil2Department of Pharmaceutical Sciences, College of Pharmacy, Mercer University, Atlanta, GA 30341, USADepartment of Pharmaceutical Sciences, School of Pharmacy and Pharmaceutical Sciences, University at Buffalo, Buffalo, NY 14214, USADepartment of Pharmaceutical Sciences, College of Pharmacy, Mercer University, Atlanta, GA 30341, USAPharmacometrics and the utilization of population pharmacokinetics play an integral role in model-informed drug discovery and development (MIDD). Recently, there has been a growth in the application of deep learning approaches to aid in areas within MIDD. In this study, a deep learning model, LSTM-ANN, was developed to predict olanzapine drug concentrations from the CATIE study. A total of 1527 olanzapine drug concentrations from 523 individuals along with 11 patient-specific covariates were used in model development. The hyperparameters of the LSTM-ANN model were optimized through a Bayesian optimization algorithm. A population pharmacokinetic model using the NONMEM model was constructed as a reference to compare to the performance of the LSTM-ANN model. The RMSE of the LSTM-ANN model was 29.566 in the validation set, while the RMSE of the NONMEM model was 31.129. Permutation importance revealed that age, sex, and smoking were highly influential covariates in the LSTM-ANN model. The LSTM-ANN model showed potential in the application of drug concentration predictions as it was able to capture the relationships within a sparsely sampled pharmacokinetic dataset and perform comparably to the NONMEM model.https://www.mdpi.com/1999-4923/15/4/1139pharmacometricsdeep learningpopulation pharmacokineticsdrug concentration predictionsLSTMneural networks |
| spellingShingle | Richard Khusial Robert R. Bies Ayman Akil Deep Learning Methods Applied to Drug Concentration Prediction of Olanzapine Pharmaceutics pharmacometrics deep learning population pharmacokinetics drug concentration predictions LSTM neural networks |
| title | Deep Learning Methods Applied to Drug Concentration Prediction of Olanzapine |
| title_full | Deep Learning Methods Applied to Drug Concentration Prediction of Olanzapine |
| title_fullStr | Deep Learning Methods Applied to Drug Concentration Prediction of Olanzapine |
| title_full_unstemmed | Deep Learning Methods Applied to Drug Concentration Prediction of Olanzapine |
| title_short | Deep Learning Methods Applied to Drug Concentration Prediction of Olanzapine |
| title_sort | deep learning methods applied to drug concentration prediction of olanzapine |
| topic | pharmacometrics deep learning population pharmacokinetics drug concentration predictions LSTM neural networks |
| url | https://www.mdpi.com/1999-4923/15/4/1139 |
| work_keys_str_mv | AT richardkhusial deeplearningmethodsappliedtodrugconcentrationpredictionofolanzapine AT robertrbies deeplearningmethodsappliedtodrugconcentrationpredictionofolanzapine AT aymanakil deeplearningmethodsappliedtodrugconcentrationpredictionofolanzapine |