The real-time systems perform key functionalities in various fields to automate the communication and response in critical events. The Internet of Things (IoT), integrated with numerous physical objects, gathers environmental data, processes it at the edge, and provides intelligent decisions while routing health records to processing units. However, the dynamic and resource-constrained nature of IoT-based healthcare environments introduces significant challenges related to latency, transmission costs, and the reliable interaction of devices amid uncertain activities. In this work, we propose a framework for a consistent and trustworthy system that uses a weighted trust aggregation model to consider multiple parameters and support timely routing decisions in a Fog-driven healthcare environment. Furthermore, authorized access to critical and sensitive health data is achieved through mutual authentication among devices, ensuring data integrity. The analysis of trust scores dynamically enhances resilience and the timely detection of malicious actions, thereby improving the healthcare system’s performance across unpredictable channels. The performance of the proposed framework is tested and validated against CLCSR and FSRF, and performance results revealed the significance for energy consumption, response time, network throughput, trust level, and accuracy across varying fog node capacity and interference scenarios.

This article presents a Hierarchical Pathway-Masked Attention Autoencoder (H-PAAE), a biologically inspired representation-learning framework that enables explainable AI-guided cancer diagnosis. The model directly integrates the curated MSigDB Hallmark pathways, introducing pathway-constrained information flow and mechanistic interpretability through multi-level attention mechanisms. Based on TCGA RNA-seq data from 33 tumor types, H-PAAE compresses approximately 20,000 genes into a 128-dimensional latent space while preserving biologically meaningful structure. When used with XGBoost classification, H-PAAE delivers 92.37% test accuracy and 99.38% macro-AUROC with robust cross-validation results (92.5 $\pm$ 0.6%). SHAP analysis identifies a small number of key latent features, corresponding to conserved oncogenic processes, and pathway enrichment analysis shows strong overlap with cancer hallmarks. H-PAAE provides a clear and interpretable biological foundation for pan-cancer classification, with well-calibrated posterior probabilities that can be used for clinical decision-making, and can be easily integrated into multimodal diagnostic workflows.