A machine learning approach to personalized dose adjustment of lamotrigine using noninvasive clinical parameters
Abstract The pharmacokinetic variability of lamotrigine (LTG) plays a significant role in its dosing requirements. Our goal here was to use noninvasive clinical parameters to predict the dose-adjusted concentrations (C/D ratio) of LTG based on machine learning (ML) algorithms. A total of 1141 therap...
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Nature Portfolio
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/36e436b9525e4b3b9f9f54c1a7914a6c |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:36e436b9525e4b3b9f9f54c1a7914a6c |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:36e436b9525e4b3b9f9f54c1a7914a6c2021-12-02T13:20:22ZA machine learning approach to personalized dose adjustment of lamotrigine using noninvasive clinical parameters10.1038/s41598-021-85157-x2045-2322https://doaj.org/article/36e436b9525e4b3b9f9f54c1a7914a6c2021-03-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-85157-xhttps://doaj.org/toc/2045-2322Abstract The pharmacokinetic variability of lamotrigine (LTG) plays a significant role in its dosing requirements. Our goal here was to use noninvasive clinical parameters to predict the dose-adjusted concentrations (C/D ratio) of LTG based on machine learning (ML) algorithms. A total of 1141 therapeutic drug-monitoring measurements were used, 80% of which were randomly selected as the "derivation cohort" to develop the prediction algorithm, and the remaining 20% constituted the "validation cohort" to test the finally selected model. Fifteen ML models were optimized and evaluated by tenfold cross-validation on the "derivation cohort,” and were filtered by the mean absolute error (MAE). On the whole, the nonlinear models outperformed the linear models. The extra-trees’ regression algorithm delivered good performance, and was chosen to establish the predictive model. The important features were then analyzed and parameters of the model adjusted to develop the best prediction model, which accurately described the C/D ratio of LTG, especially in the intermediate-to-high range (≥ 22.1 μg mL−1 g−1 day), as illustrated by a minimal bias (mean relative error (%) = + 3%), good precision (MAE = 8.7 μg mL−1 g−1 day), and a high percentage of predictions within ± 20% of the empirical values (60.47%). This is the first study, to the best of our knowledge, to use ML algorithms to predict the C/D ratio of LTG. The results here can help clinicians adjust doses of LTG administered to patients to minimize adverse reactions.Xiuqing ZhuWencan HuangHaoyang LuZhanzhang WangXiaojia NiJinqing HuShuhua DengYaqian TanLu LiMing ZhangChang QiuYayan LuoHongzhen ChenShanqing HuangTao XiaoDewei ShangYuguan WenNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-14 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
Medicine R Science Q |
| spellingShingle |
Medicine R Science Q Xiuqing Zhu Wencan Huang Haoyang Lu Zhanzhang Wang Xiaojia Ni Jinqing Hu Shuhua Deng Yaqian Tan Lu Li Ming Zhang Chang Qiu Yayan Luo Hongzhen Chen Shanqing Huang Tao Xiao Dewei Shang Yuguan Wen A machine learning approach to personalized dose adjustment of lamotrigine using noninvasive clinical parameters |
| description |
Abstract The pharmacokinetic variability of lamotrigine (LTG) plays a significant role in its dosing requirements. Our goal here was to use noninvasive clinical parameters to predict the dose-adjusted concentrations (C/D ratio) of LTG based on machine learning (ML) algorithms. A total of 1141 therapeutic drug-monitoring measurements were used, 80% of which were randomly selected as the "derivation cohort" to develop the prediction algorithm, and the remaining 20% constituted the "validation cohort" to test the finally selected model. Fifteen ML models were optimized and evaluated by tenfold cross-validation on the "derivation cohort,” and were filtered by the mean absolute error (MAE). On the whole, the nonlinear models outperformed the linear models. The extra-trees’ regression algorithm delivered good performance, and was chosen to establish the predictive model. The important features were then analyzed and parameters of the model adjusted to develop the best prediction model, which accurately described the C/D ratio of LTG, especially in the intermediate-to-high range (≥ 22.1 μg mL−1 g−1 day), as illustrated by a minimal bias (mean relative error (%) = + 3%), good precision (MAE = 8.7 μg mL−1 g−1 day), and a high percentage of predictions within ± 20% of the empirical values (60.47%). This is the first study, to the best of our knowledge, to use ML algorithms to predict the C/D ratio of LTG. The results here can help clinicians adjust doses of LTG administered to patients to minimize adverse reactions. |
| format |
article |
| author |
Xiuqing Zhu Wencan Huang Haoyang Lu Zhanzhang Wang Xiaojia Ni Jinqing Hu Shuhua Deng Yaqian Tan Lu Li Ming Zhang Chang Qiu Yayan Luo Hongzhen Chen Shanqing Huang Tao Xiao Dewei Shang Yuguan Wen |
| author_facet |
Xiuqing Zhu Wencan Huang Haoyang Lu Zhanzhang Wang Xiaojia Ni Jinqing Hu Shuhua Deng Yaqian Tan Lu Li Ming Zhang Chang Qiu Yayan Luo Hongzhen Chen Shanqing Huang Tao Xiao Dewei Shang Yuguan Wen |
| author_sort |
Xiuqing Zhu |
| title |
A machine learning approach to personalized dose adjustment of lamotrigine using noninvasive clinical parameters |
| title_short |
A machine learning approach to personalized dose adjustment of lamotrigine using noninvasive clinical parameters |
| title_full |
A machine learning approach to personalized dose adjustment of lamotrigine using noninvasive clinical parameters |
| title_fullStr |
A machine learning approach to personalized dose adjustment of lamotrigine using noninvasive clinical parameters |
| title_full_unstemmed |
A machine learning approach to personalized dose adjustment of lamotrigine using noninvasive clinical parameters |
| title_sort |
machine learning approach to personalized dose adjustment of lamotrigine using noninvasive clinical parameters |
| publisher |
Nature Portfolio |
| publishDate |
2021 |
| url |
https://doaj.org/article/36e436b9525e4b3b9f9f54c1a7914a6c |
| work_keys_str_mv |
AT xiuqingzhu amachinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters AT wencanhuang amachinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters AT haoyanglu amachinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters AT zhanzhangwang amachinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters AT xiaojiani amachinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters AT jinqinghu amachinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters AT shuhuadeng amachinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters AT yaqiantan amachinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters AT luli amachinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters AT mingzhang amachinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters AT changqiu amachinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters AT yayanluo amachinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters AT hongzhenchen amachinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters AT shanqinghuang amachinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters AT taoxiao amachinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters AT deweishang amachinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters AT yuguanwen amachinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters AT xiuqingzhu machinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters AT wencanhuang machinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters AT haoyanglu machinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters AT zhanzhangwang machinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters AT xiaojiani machinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters AT jinqinghu machinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters AT shuhuadeng machinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters AT yaqiantan machinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters AT luli machinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters AT mingzhang machinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters AT changqiu machinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters AT yayanluo machinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters AT hongzhenchen machinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters AT shanqinghuang machinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters AT taoxiao machinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters AT deweishang machinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters AT yuguanwen machinelearningapproachtopersonalizeddoseadjustmentoflamotrigineusingnoninvasiveclinicalparameters |
| _version_ |
1718393202649595904 |