Comparison of small-sample multi-class machine learning models for plasma concentration prediction of valproic acid
- VernacularTitle:丙戊酸血药浓度预测的小样本多分类机器学习模型对比
- Author:
Xi CHEN
1
;
Shen’ao YUAN
2
;
Hailing YUAN
1
;
Jie ZHAO
3
;
Peng CHEN
2
;
Chunyan TIAN
1
;
Yi SU
1
;
Yunsong ZHANG
1
;
Yu ZHANG
1
Author Information
1. Dept. of Pharmacy，Xi’an International Medical Center Hospital，Xi’an 710100，China
2. School of Information Engineering，Chang’an University，Xi’an 710064，China
3. School of Economics and Management，Chang’an University，Xi’an 710064，China
- Publication Type:Journal Article
- Keywords:
valproic acid;
machine learning;
plasma
- From:
China Pharmacy
2025;36(11):1399-1404
- CountryChina
- Language:Chinese
-
Abstract:
OBJECTIVE To construct three-class （insufficient， normal， excessive） and two-class （insufficient， normal） models for predicting plasma concentration of valproic acid （VPA）， and compare the performance of these two models， with the aim of providing a reference for formulating clinical medication strategies. METHODS The clinical data of 480 patients who received VPA treatment and underwent blood concentration test at the Xi’an International Medical Center Hospital were collected from November 2022 to September 2024 （a total of 695 sets of data）. In this study， predictive models were constructed for target variables of three-class and two-class models. Feature ranking and selection were carried out using XGBoost scores. Twelve different machine learning algorithms were used for training and validation， and the performance of the models was evaluated using three indexes: accuracy， F1 score， and the area under the working characteristic curve of the subject （AUC）. RESULTS XGBoost feature importance scores revealed that in the three-class model， the importance ranking of kidney disease and electrolyte disorders was higher. However， in the two-class model， the importance ranking of these features significantly decreased， suggesting a close association with the excessive blood concentration of VPA. In the three-class model， Random Forest method performed best， with F1 score of 0.704 0 and AUC of 0.519 3 on the test set； while in the two-class model， CatBoost method performed optimally， with F1 score of 0.785 7 and AUC of 0.819 5 on the test set. CONCLUSIONS The constructed three-class model has the ability to predict excessive VPA blood concentration， but its prediction and model generalization abilities are poor； the constructed two-class model can only perform classification prediction for insufficient and normal blood concentration cases， but its model performance is stronger.
