Prediction of Zonisamide Concentration in Pediatric Patients With Epilepsy: A Machine Learning Approach
Vorhersage der Zonisamid-Konzentration bei pädiatrischen Patient:innen mit Epilepsie: Machine-Learning-Ansatz
CNS Neuroscience & Therapeutics · 2026-06 · 32 (6)
DOI: 10.1002/cns.70996 ↗Auf einen Blick
In einer retrospektiven Studie wurde ein Modell zur Vorhersage der Zonisamid-Konzentration bei Kindern mit Epilepsie entwickelt und validiert. Der Random-Forest-Algorithmus zeigte die beste Leistung.
Fragestellung
Lassen sich Zonisamid-Konzentrationen bei pädiatrischen Patient:innen mit Epilepsie mit Machine-Learning-Modellen vorhersagen, und welcher Algorithmus ist am besten?
Methode
Retrospektive Entwicklung und Validierung von 12 Machine-Learning-Regressionsmodellen; Daten aus Kunming Children’s Hospital; Aufteilung 7:3; 5-fache Kreuzvalidierung und Grid Search.
Ergebnisse
532 Patient:innen im Modellierungskollektiv und 436 in der externen Validierung. RF war am besten: Training R2 0,97 %, RMSE 0,83 %, MAE 0,57 %, Err20 7,40 %; intern R2 0,78 %, RMSE 1,99 %, MAE 1,48 %, Err20 31,20 %; extern R2 0,89 %, RMSE 1,31 %, MAE 0,86 %, Err20 16,50 %.
Schlussfolgerung der Autor:innen
Die Autor:innen berichten, dass auf Basis des Random Forest ein Zonisamid-Vorhersagemodell erfolgreich konstruiert und validiert wurde. Es zeigte hohe Präzision, Stabilität und gute Generalisierbarkeit.
Kernaussagen
- Random Forest war von 12 Modellen am leistungsstärksten.
- Dosierung und Geschlecht waren die wichtigsten Einflussfaktoren.
- Das Modell wurde intern und extern validiert.
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Fachartikel in der Zeitschrift CNS Neuroscience & Therapeutics, online erschienen am 22.06.2026. Verfasst von Li Fashuang und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pharmacy, Kunming Children's Hospital, Kunming, China. Hauptthemen laut MEDLINE: Zonisamide, Epilepsy, Anticonvulsants, Machine Learning. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Plan Project of Yunnan Province, Science and Technology Achievement Transformation Project of Yunnan Province, Special Program for Training High-Level Health Professionals of Yunnan Province.
Abstract (Originalsprache)
Objective
To construct and validate prediction models for zonisamide (ZNS) concentration in pediatric patients with epilepsy based on 12 machine learning algorithms, to screen for the optimal algorithm, and to provide a scientific basis for the formulation of individualized ZNS dosing regimens in children.
Methods
Clinical data of patients who underwent ZNS therapeutic drug monitoring at Kunming Children's Hospital from May 2022 to January 2026 were retrospectively collected and randomly divided into a training set and a test set at a ratio of 7:3. Key predictive variables were determined through a multi‐stage feature screening strategy (covering correlation analysis, collinearity diagnosis, univariate analysis, Lasso regression, and random forest algorithm). Based on the selected variables, 12 machine learning regression models were constructed to predict ZNS concentration, and grid search combined with 5‐fold cross‐validation was employed for parameter optimization and performance evaluation. The coefficient of determination ( R 2 ), mean squared error (MSE), root mean squared error (RMSE), and mean absolute error (MAE) were used as primary evaluation metrics. Finally, the SHAP method was adopted to interpret the feature contribution and decision logic of the optimal model.
Results
The modeling cohort of this study enrolled 532 pediatric patients who received zonisamide treatment at the Department of Neurology, Kunming Children's Hospital from May 2022 to May 2024. These patients were randomly divided into a training set (375 cases) and an internal validation set (157 cases) at a ratio of 7:3. Additionally, 436 pediatric patients from the same department of the same hospital from June 2024 to January 2026 were included as an external validation cohort. Comparisons of general clinical data, laboratory indicators, and medication‐related data among the groups showed no statistically significant differences (all p > 0.05), indicating that the baseline data were balanced and comparable. The median (interquartile range) ZNS concentrations in the training set, internal validation set, and external validation cohort were 9.65 (8.11, 11.98) μg/mL, 9.93 (8.23, 12.06) μg/mL, and 10.77 (7.67, 13.69) μg/mL, respectively. Through multi‐stage feature screening, gender, dosage, age, red blood cell count, concomitant medication status, total protein, uric acid, and platelets were identified as key factors influencing ZNS concentration. Among the 12 constructed machine learning models, the Random Forest (RF) algorithm demonstrated the optimal performance: in the training set, R 2 was 0.97%, RMSE was 0.83%, MAE was 0.57%, and Err20 was 7.40%; in the internal validation set, R 2 was 0.78%, RMSE was 1.99%, MAE was 1.48%, and Err20 was 31.20%; and in the external validation set, R 2 was 0.89%, RMSE was 1.31%, MAE was 0.86%, and Err20 was 16.50%. SHAP method combined with representative decision tree analysis revealed that dosage and gender were the primary factors influencing ZNS concentration, followed by total protein and uric acid; among them, dosage showed a positive contribution, gender exhibited a bidirectional effect, and laboratory indicators mostly showed nonlinear associations. Decision tree analysis indicated that the model used gender as the primary splitting feature and incorporated multi‐indicator interactions; its decision logic aligned with pharmacokinetic theory, providing strong support for the interpretability of the model's clinical application.
Conclusion
This study successfully constructed and validated a ZNS concentration prediction model for pediatric patients with epilepsy based on the random forest algorithm. The model demonstrated high precision, strong stability, and good generalization ability. Gender, dose, uric acid, and total protein are core variables influencing ZNS concentration. The findings can provide a reference for the formulation of individualized ZNS dosing regimens in children.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Pharmacy, Kunming Children's Hospital, Kunming, China.
- Laboratory Department, Kunming Children's Hospital, Kunming, China.
- Department of Pharmacy, Yunnan Provincial Hospital of Infectious Disease, Kunming, China.
ORCID-Profile: Li Fashuang, Li Na, Li Huiying
Förderung
- Science and Technology Plan Project of Yunnan Province
- Science and Technology Achievement Transformation Project of Yunnan Province
- Special Program for Training High-Level Health Professionals of Yunnan Province
- "Hundred Talents" Project for Health Science and Technology Talents Training of Kunming
Zitieren
APA
Fashuang, L., Mingbiao, M., Na, L., Huiying, L., Danyang, R., Caixia, T., Linbo, L., & Lilin, Z. (2026). Prediction of Zonisamide Concentration in Pediatric Patients With Epilepsy: A Machine Learning Approach. CNS Neuroscience & Therapeutics, 32(6). https://doi.org/10.1002/cns.70996
Vancouver
Fashuang L, Mingbiao M, Na L, Huiying L, Danyang R, Caixia T, et al. Prediction of Zonisamide Concentration in Pediatric Patients With Epilepsy: A Machine Learning Approach. CNS Neuroscience & Therapeutics. 2026;32(6). doi:10.1002/cns.70996
BibTeX
@article{Fashuang2026,
author = {Fashuang, Li and Mingbiao, Ma and Na, Li and Huiying, Li and Danyang, Ren and Caixia, Tu and Linbo, Li and Lilin, Zhang},
title = {Prediction of Zonisamide Concentration in Pediatric Patients With Epilepsy: A Machine Learning Approach},
journal = {CNS Neuroscience & Therapeutics},
year = {2026},
volume = {32},
number = {6},
doi = {10.1002/cns.70996}
}
EUVIMED