From Dissertation to Deployment: A Unified Software Platform Operationalizing Clinical-Prediction and Sequential-Security AI for Healthcare

Advances in machine learning for healthcare are abundant, yet most validated models remain confined to research notebooks and never reach secure, usable clinical software. This paper addresses that deployment gap by presenting a unified, security-hardened software platform that operationalizes two complementary streams of doctoral research inside a single, role-based hospital information system. The first stream contributes a clinical-prediction capability: an ultra-hybrid ensemble that couples a quantum-inspired feature transformation, particle-swarm feature selection, and calibrated soft voting for cancer-outcome prediction (96.41% accuracy, AUC-ROC 0.983 on TCGA-BRCA), survival stratification, multi-cancer generalization, and pharmacogenomic drug-response classification (89.31% mean accuracy across 25 compounds). The second stream contributes a sequential-security capability built on a bidirectional gated recurrent unit (Bi-GRU) for network intrusion detection (94.95–98.40% accuracy across three datasets, including a purpose-built healthcare benchmark) and an attention-enhanced variant for electroencephalography (EEG) biometric identification (96.68% accuracy). The platform follows a three-tier architecture (Flutter client, ASP.NET Core gatekeeper, and an isolated model-serving service) in which security is embedded architecturally through role-based access control, audit logging, an intrusion-detection monitor, and a biometric access gate, aligned with HIPAA and GDPR obligations. A remote elderly-care module illustrates the platform in an aging-in-place scenario. The contribution is the engineering translation of research-grade AI into one deployed, compliant system.