Our papers: Graph Neural Networks-Based Digital Twin Modeling of WBC and ANC Dynamics for Personalized Time-Series Prediction and Generative Adversarial Networks-Driven Synthetic Patient Data Creation for Risk Identification in Childhood Acute Lymphoblastic Leukemia, which we presented in 2025 as advancing the development of 6-MP drug treatment using GNN and GAN models, have just been indexed in the IEEE Xplore database!
Click on the titles to access the papers:
Graph Neural Networks-Based Digital Twin Modeling of WBC and ANC Dynamics for Personalized Time-Series Prediction
Generative Adversarial Networks-Driven Synthetic Patient Data Creation for Risk Identification in Childhood Acute Lymphoblastic Leukemia
Graph Neural Networks-Based Digital Twin Modeling of WBC and ANC Dynamics for Personalized Time-Series Prediction
Abstract:
This study introduces a digital twin model approach with Graph Neural Networks (GNNs) to forecast white blood cell (WBC) and absolute neutrophil count (ANC) levels during 6-mercaptopurine (6-MP) chemotherapy for treating childhood acute lymphoblastic leukemia (ALL). For incorporating clinical and lifestyle factors like daily medication dosage, anthropometric measurements (weight, height, and body surface area), diet, exercise, and vitamin D intake, the model is constructed using a synthetic patient dataset based on personalized computational Pharmacokinetics (PK) / Pharmacodynamics (PD) mathematical models. To capture temporal relationships, each data point is connected to earlier observations and is defined as a node within a time-dependent graph structure. The model, which was created with PyTorch Geometric, was evaluated by using MAE, MSE, and RMSE metrics after being trained with inputs, which are normalized by z-scores. The study results point that the developed GNN-based method works well as a digital twin tool for customized chemotherapy simulations and can predict changes in hematological parameters over time.
Generative Adversarial Networks-Driven Synthetic Patient Data Creation for Risk Identification in Childhood Acute Lymphoblastic Leukemia
Abstract:
This study aims to enhance real-world clinical data in childhood acute lymphoblastic leukemia (ALL) patients and enable more detailed patient analysis through risk category classification. New synthetic patient samples were generated via Generative Adversarial Network (GAN) model. Here, the GAN discriminator used patient data derived from a Graph Neural Network (GNN). The similarity between the synthetic patient data generated by the model and real patient data was assessed using various metrics. Distribution similarity analyses (t-SNE, PCA, and various statistical metrics) demonstrated substantial alignment between the synthetic and real patient datasets. The findings of the study demonstrated the effectiveness of GAN-based patient data augmentation in terms of data privacy and patient diversity. Furthermore, synthetically generated patient data can serve as a robust foundation for clinical digital twin applications and decision support systems.
Be First to Comment