The rapid advancement of the Internet of Medical Things (IoMT) has revolutionized remote healthcare monitoring, enabling real-time disease detection and patient care. This research introduces a novel AI-driven telemedicine framework that integrates IoMT, cloud computing, and wireless sensor networks for efficient healthcare monitoring. A key innovation of this study is the Transformer-based Self-Attention Model (TL-SAM), which enhances disease classification by replacing conventional convolutional layers with transformer layers. The proposed TL-SAM framework effectively extracts spatial and spectral features from patient health data, optimizing classification accuracy. Furthermore, the model employs an Improved Wild Horse Optimization with Levy Flight Algorithm (IWHOLFA) for hyperparameter tuning, enhancing its predictive performance. Real-time biosensor data is collected and transmitted to an IoMT cloud repository, where AI-driven analytics facilitate early disease diagnosis. Extensive experimentation on the UCI dataset demonstrates the superior accuracy of TL-SAM compared to conventional deep learning models, achieving an accuracy of 98.62%, precision of 97%, recall of 98%, and F1-score of 97%. The study highlights the effectiveness of AI-enhanced IoMT systems in reducing healthcare costs, improving early disease detection, and ensuring timely medical interventions. The proposed approach represents a significant advancement in smart healthcare, offering a scalable and efficient solution for remote patient monitoring and diagnosis.

Edge IoT deployments must evaluate the trustworthiness of peer devices continuously, locally, and under resource constraints that static scoring models cannot accommodate—particularly when adversaries adapt their mimicry strategies in response to observed detection outcomes. This study presents the Adaptive Dynamic Trust Evaluation (ADTE) framework, with three core novelties that address the distinct failure modes of prior research. First, an edge-masked heterogeneous attention (EMHA) operator suppresses adversarially injected graph edges through a learnable perturbation-aware gate, for which we prove a certified robustness radius under ℓ ∞ -bounded node-feature perturbation and quantify mask convergence under PGD-augmented training. We additionally demonstrate empirical—though not formally certified—robustness against gradient-based edge-injection attacks and explicitly define the gap between the analytic certificate (node features) and the main graph-poisoning threat model (edge structure). Second, a non-stationary MDP formulation models the adversary’s policy as a time-varying component of the transition kernel; we derive a regret bound of O ( T Δ T ) that holds under both piece-wise stationary and continuously drifting attack distributions by applying a sliding-window restart mechanism, proving that this bound extends to partially observable adversarial policies via a POMDP belief-state reduction. Third, a continual PPO agent augmented with elastic weight consolidation (EWC) prevents catastrophic forgetting over long deployment horizons; we demonstrate stable policy performance across 5000-episode simulations spanning ≈ 3.47 continuous deployment-days at 60 s evaluation windows (equivalent to 300,000 s of gateway operation). Unlike prior trust evaluation frameworks that address, at most, two of the three sub-problems (representation, decision, and adaptation), ADTE simultaneously targets all three, thus delivering certified robustness guarantees that are absent from GNN-based approaches, non-stationary regret bounds missing from RL-based methods, and continual learning stability unavailable in either category. Evaluated on N-BaIoT, MedBIoT, and UNSW-NB15 against eight baselines, ADTE achieves 95.3% trust classification accuracy, 41.8% FPR reduction over FedTrust, and sub-12 m edge latency at 1.8 W incremental power. The 41.8% FPR reduction over FedTrust is measured under equivalent single-gateway operating conditions. These results are validated under gradient-based adaptive graph poisoning, asynchronous decentralised gateway operation, and topology churn up to 1,200 devices—conditions no prior trust evaluation framework has simultaneously addressed.