EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Ensemble Machine Learning Model for Real-Time Valproic Acid Prediction in Epilepsy Treatment

Jiangchuan Xie, Pan Ma, Xinmei Pan, Liya Cao, Ruixiang Liu, Lirong Xiong, Hongqian Wang, Xin Zhang, Linli Xie, Yongchuan Chen

Pharmacopsychiatry · 01.05.2026 · 59 (03) · 145-156

DOI: 10.1055/a-2593-3125 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Pharmacopsychiatry, erschienen am 01.05.2026. Verfasst von Jiangchuan Xie und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of pharmacy, The First Affiliated Hospital of Army Medical University, Chongqing, China. Hauptthemen laut MEDLINE: Valproic Acid, Epilepsy, Machine Learning, Anticonvulsants. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To develop an optimal model to predict valproic acid (VPA) concentrations by machine learning, ensuring that the VPA plasma concentration is in the effective treatment range, and thus effectively control the patient’s epilepsy. This single-center, retrospective study included patients diagnosed with epilepsy from January 2014 to January 2022. Patients receiving VPA and having undergone therapeutic drug monitoring were enrolled. Top three algorithms exhibiting superior model performance were selected to establish the ensemble prediction model, with Shapley Additive exPlanations (SHAP) employed for model interpretation. An independent dataset was collected as a clinical validation group to verify the prediction model performance. The algorithms chosen for the ensemble model—Light Gradient Boosting, Categorical Boosting, and Gradient Boosted Regression Trees—demonstrated high R 2 (0.549, 0.515, and 0.503, respectively). Post-feature selection, the final model incorporated 20 variables, proving superior in predictive performance compared to models considering all 24 variables. The R 2 , mean absolute error, mean square error, absolute accuracy (±20 mg/L), and relative accuracy (±20%) of external validation were 0.621, 10.67, 221.50, 78.98%, and 66.48%, respectively. The importance and direction of each variable were visually represented using SHAP values, with VPA administration and liver function emerging as the most significant factors. The innovative application harnesses advanced multi-algorithm mining methodologies to forecast VPA concentrations in adult epileptic patients. Furthermore, it employs SHAP to elucidate the nuanced influence of each feature within the integrated prediction model, thereby providing a robust and plausible explanation for the determinants affecting VPA concentration predictions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Valproic AcidEpilepsyMachine LearningAnticonvulsantsHumansRetrospective StudiesFemaleMaleAdultMiddle AgedYoung AdultDrug MonitoringAlgorithmsAdolescent

Substanzen

Valproic AcidAnticonvulsants

Autor:innen und Institutionen

  • Department of pharmacy, The First Affiliated Hospital of Army Medical University, Chongqing, China.
  • Medical Big Data and Artificial Intelligence Center, the First Affiliated Hospital of Army Medical University, Chongqing, China.

Zitieren

APA

Xie, J., Ma, P., Pan, X., Cao, L., Liu, R., Xiong, L., Wang, H., Zhang, X., Xie, L., & Chen, Y. (2026). Ensemble Machine Learning Model for Real-Time Valproic Acid Prediction in Epilepsy Treatment. Pharmacopsychiatry, 59(03), 145-156. https://doi.org/10.1055/a-2593-3125

Vancouver

Xie J, Ma P, Pan X, Cao L, Liu R, Xiong L, et al. Ensemble Machine Learning Model for Real-Time Valproic Acid Prediction in Epilepsy Treatment. Pharmacopsychiatry. 2026;59(03):145-156. doi:10.1055/a-2593-3125

BibTeX
@article{Xie2026,
  author = {Xie, Jiangchuan and Ma, Pan and Pan, Xinmei and Cao, Liya and Liu, Ruixiang and Xiong, Lirong and Wang, Hongqian and Zhang, Xin and Xie, Linli and Chen, Yongchuan},
  title = {Ensemble Machine Learning Model for Real-Time Valproic Acid Prediction in Epilepsy Treatment},
  journal = {Pharmacopsychiatry},
  year = {2026},
  volume = {59},
  number = {03},
  pages = {145--156},
  doi = {10.1055/a-2593-3125}
}
Kostenlos starten →