Optimizing Cancer Drug Treatments Using Big Data Integration of Genomic and Clinical Data for Personalized Medicine

Personalized cancer care depends on the seamless integration of genetic profiles, medical histories, and continuous patient monitoring to optimize therapeutic outcomes. Current clinical strategies struggle to combine these disparate, highly heterogeneous data streams, frequently resulting in incomplete diagnostic evaluations and suboptimal treatment selections. Factors such as poor cross-platform compatibility, low prediction precision, and the omission of real-time clinical parameters limit the practical deployment of precision medicine. To address these limitations, this study introduces BigCancerNet (BCN), a robust big data framework that merges multi-source information and uses a Graph Neural Network for Cancer Treatment Optimization (GNN-CTO) to accurately forecast individual drug responses and patient survival trajectories. This initiative is driven by the aspiration to boost treatment success, reduce toxic side effects, and permit flexible, patient-centric therapeutic adaptations. The processing pipeline comprises collecting genomic, clinical, and real-time biometric data from numerous repositories, including The Cancer Genome Atlas (TCGA), Gene Expression Omnibus (GEO), Cancer Dependency Map (DepMap), and hospital Electronic Health Records (EHRs). Data preprocessing applies Deep Embedding Networks (D2EN) to regularize genomic sequences, handle missing values, and standardize clinical features. The Hybrid Multi-Omics Fusion Algorithm (HMOFA) integrates these diverse datasets, harmonizing genomic, clinical, and wearable information while minimizing batch effects. The GNN-CTO model captures complex, nonlinear relationships among mutations, clinical factors, and drug responses, while Real-Time Model Adaptation with Dynamic Feedback Loop (RT-MADFL) continuously updates predictions. Results demonstrate reduced RMSE (0.160-0.245) and MAE (0.110-0.180), high stability with fold accuracy variance below 0.3%, fast training (12-15s per epoch), and prediction metrics exceeding 91%. Future work includes expanding to multi-cancer cohorts and integrating explainable AI to support transparent clinical decision-making.