Prediction of High-Dose Methotrexate Blood Concentration in Osteosarcoma Patients Using Machine Learning
Jin Zhao,1 Shuqi Dai,2 Jiali He,1 Na Liu,1 Baowanze Zhang,1 Su Li1 1Department of Pharmacy, Cancer Hospital of China Medical University, Liaoning Cancer Hospital & Institute, Shenyang, Liaoning, 110042, People’s Republic of China; 2Department of Pharmacy, Qujing Medical College, Qujing, Yunn...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Dove Medical Press
2025-05-01
|
| Series: | Drug Design, Development and Therapy |
| Subjects: | |
| Online Access: | https://www.dovepress.com/prediction-of-high-dose-methotrexate-blood-concentration-in-osteosarco-peer-reviewed-fulltext-article-DDDT |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850189888547192832 |
|---|---|
| author | Zhao J Dai S He J Liu N Zhang B Li S |
| author_facet | Zhao J Dai S He J Liu N Zhang B Li S |
| author_sort | Zhao J |
| collection | DOAJ |
| description | Jin Zhao,1 Shuqi Dai,2 Jiali He,1 Na Liu,1 Baowanze Zhang,1 Su Li1 1Department of Pharmacy, Cancer Hospital of China Medical University, Liaoning Cancer Hospital & Institute, Shenyang, Liaoning, 110042, People’s Republic of China; 2Department of Pharmacy, Qujing Medical College, Qujing, Yunnan, 655000, People’s Republic of ChinaCorrespondence: Su Li, Department of Pharmacy, Cancer Hospital of China Medical University, Liaoning Cancer Hospital & Institute, No. 44, Xiaoheyan Road, Dadong District, Shenyang, Liaoning, 110042, People’s Republic of China, Tel +86-024-81916806, Email lisu@cancerhosp-ln-cmu.comIntroduction: High-dose methotrexate is a typical chemotherapy that is widely used in the treatment of osteosarcoma. However, the unique dose-response relationship of methotrexate makes its treatment window relatively narrow, and its clinical use is in a dilemma: either the drug concentration in the patient’s body cannot reach the effective concentration level, or adverse reactions may occur due to drug overdose. For this circumstance, monitoring and predicting the drug concentration in the patient’s body is well founded and necessary. While pharmacokinetic models exist, they often oversimplify patient-specific covariates. This study addresses the unmet need for early-exposure prediction through interpretable machine learning, enabling data-driven decisions before toxicity manifestation.Methods: In this article, 68 osteosarcoma patients’ information including demography, administration and assay was gathered. We analyzed medical data and selected 10 important features using a random forest, including hydration status, red blood cell distribution width coefficient of variation, platelet distribution width, creatinine, γ-glutamyl transferase, large platelet ratio, serum potassium, lactate dehydrogenase, weight, and prealbumin. Then, cross-validation and SHAP has been conducted to confirm the robust and interpretation of the model.Results: On this basis, 7 machine learning regression models was built to predict the blood concentration of methotrexate. R2, MSE, RMSE, MAE are the evaluation metrics. Finally, LightGBM was selected as the best prediction model with a performance of R2=0.87, MSE=0.020, RMSE=0.141, MAE=0.065.Discussion: This machine learning framework addresses a critical gap in high-dose methotrexate therapeutic monitoring by achieving early and personalized blood drug concentration prediction, allowing for personalized dosing of patients based on predicted concentrations. The interpretability of SHAP-derived feature importance enhances clinical utility, offering a paradigm shift from reactive toxicity management to proactive precision dosing in osteosarcoma therapy.Keywords: high-dose methotrexate, osteosarcoma, machine learning, blood concentration prediction |
| format | Article |
| id | doaj-art-8468d75a3abb4a4da0358f2f097ad262 |
| institution | OA Journals |
| issn | 1177-8881 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Dove Medical Press |
| record_format | Article |
| series | Drug Design, Development and Therapy |
| spelling | doaj-art-8468d75a3abb4a4da0358f2f097ad2622025-08-20T02:15:29ZengDove Medical PressDrug Design, Development and Therapy1177-88812025-05-01Volume 19Issue 136313643102652Prediction of High-Dose Methotrexate Blood Concentration in Osteosarcoma Patients Using Machine LearningZhao J0Dai S1He J2Liu N3Zhang B4Li S5Department of PharmacyDepartment of PharmacyDepartment of PharmacyDepartment of PharmacyDepartment of PharmacyDepartment of PharmacyJin Zhao,1 Shuqi Dai,2 Jiali He,1 Na Liu,1 Baowanze Zhang,1 Su Li1 1Department of Pharmacy, Cancer Hospital of China Medical University, Liaoning Cancer Hospital & Institute, Shenyang, Liaoning, 110042, People’s Republic of China; 2Department of Pharmacy, Qujing Medical College, Qujing, Yunnan, 655000, People’s Republic of ChinaCorrespondence: Su Li, Department of Pharmacy, Cancer Hospital of China Medical University, Liaoning Cancer Hospital & Institute, No. 44, Xiaoheyan Road, Dadong District, Shenyang, Liaoning, 110042, People’s Republic of China, Tel +86-024-81916806, Email lisu@cancerhosp-ln-cmu.comIntroduction: High-dose methotrexate is a typical chemotherapy that is widely used in the treatment of osteosarcoma. However, the unique dose-response relationship of methotrexate makes its treatment window relatively narrow, and its clinical use is in a dilemma: either the drug concentration in the patient’s body cannot reach the effective concentration level, or adverse reactions may occur due to drug overdose. For this circumstance, monitoring and predicting the drug concentration in the patient’s body is well founded and necessary. While pharmacokinetic models exist, they often oversimplify patient-specific covariates. This study addresses the unmet need for early-exposure prediction through interpretable machine learning, enabling data-driven decisions before toxicity manifestation.Methods: In this article, 68 osteosarcoma patients’ information including demography, administration and assay was gathered. We analyzed medical data and selected 10 important features using a random forest, including hydration status, red blood cell distribution width coefficient of variation, platelet distribution width, creatinine, γ-glutamyl transferase, large platelet ratio, serum potassium, lactate dehydrogenase, weight, and prealbumin. Then, cross-validation and SHAP has been conducted to confirm the robust and interpretation of the model.Results: On this basis, 7 machine learning regression models was built to predict the blood concentration of methotrexate. R2, MSE, RMSE, MAE are the evaluation metrics. Finally, LightGBM was selected as the best prediction model with a performance of R2=0.87, MSE=0.020, RMSE=0.141, MAE=0.065.Discussion: This machine learning framework addresses a critical gap in high-dose methotrexate therapeutic monitoring by achieving early and personalized blood drug concentration prediction, allowing for personalized dosing of patients based on predicted concentrations. The interpretability of SHAP-derived feature importance enhances clinical utility, offering a paradigm shift from reactive toxicity management to proactive precision dosing in osteosarcoma therapy.Keywords: high-dose methotrexate, osteosarcoma, machine learning, blood concentration predictionhttps://www.dovepress.com/prediction-of-high-dose-methotrexate-blood-concentration-in-osteosarco-peer-reviewed-fulltext-article-DDDThigh-dose methotrexateosteosarcomamachine learningblood concentration prediction |
| spellingShingle | Zhao J Dai S He J Liu N Zhang B Li S Prediction of High-Dose Methotrexate Blood Concentration in Osteosarcoma Patients Using Machine Learning Drug Design, Development and Therapy high-dose methotrexate osteosarcoma machine learning blood concentration prediction |
| title | Prediction of High-Dose Methotrexate Blood Concentration in Osteosarcoma Patients Using Machine Learning |
| title_full | Prediction of High-Dose Methotrexate Blood Concentration in Osteosarcoma Patients Using Machine Learning |
| title_fullStr | Prediction of High-Dose Methotrexate Blood Concentration in Osteosarcoma Patients Using Machine Learning |
| title_full_unstemmed | Prediction of High-Dose Methotrexate Blood Concentration in Osteosarcoma Patients Using Machine Learning |
| title_short | Prediction of High-Dose Methotrexate Blood Concentration in Osteosarcoma Patients Using Machine Learning |
| title_sort | prediction of high dose methotrexate blood concentration in osteosarcoma patients using machine learning |
| topic | high-dose methotrexate osteosarcoma machine learning blood concentration prediction |
| url | https://www.dovepress.com/prediction-of-high-dose-methotrexate-blood-concentration-in-osteosarco-peer-reviewed-fulltext-article-DDDT |
| work_keys_str_mv | AT zhaoj predictionofhighdosemethotrexatebloodconcentrationinosteosarcomapatientsusingmachinelearning AT dais predictionofhighdosemethotrexatebloodconcentrationinosteosarcomapatientsusingmachinelearning AT hej predictionofhighdosemethotrexatebloodconcentrationinosteosarcomapatientsusingmachinelearning AT liun predictionofhighdosemethotrexatebloodconcentrationinosteosarcomapatientsusingmachinelearning AT zhangb predictionofhighdosemethotrexatebloodconcentrationinosteosarcomapatientsusingmachinelearning AT lis predictionofhighdosemethotrexatebloodconcentrationinosteosarcomapatientsusingmachinelearning |