The integration of the Internet of Things (IoT) in healthcare has revolutionized supply chain operations by enabling real-time monitoring, data-driven decision-making, and automation. This study proposes a secure and resilient IoT-enabled healthcare supply chain framework that enhances agility, integrity, and operational efficiency. The framework uses edge and cloud computing for real-time data aggregation, AI-driven predictive analytics for demand forecasting and anomaly detection, and blockchain technology for ensuring data security and traceability. Additionally, it employs renewable energy sources and low-power IoT protocols for sustainability in resource-constrained environments. The proposed framework uses renewable energy sources and low-power IoT protocols to guarantee viability in environments with limited resources. The results indicate substantial gains, including an 86.67% reduction in device authentication failures, a 91.67% decrease in data manipulation instances, an 88% decrease in illegal access attempts, and a 95% upgrade in data encryption security. Enhanced system resilience and availability metrics comprise a 7.31% increase in uptime and a 75% reduction in redundancy failures. The root mean square error and mean absolute error for the proposed framework are 0.28 and 0.03.

With the implementation of 6G networks and IoT devices within the healthcare sector, the collection, processing, and utilization of medical data has changed significantly and, at the same time, generated massive amounts of patient information in disparate spaces. Such technological integrations allow for real-time monitoring, AI-assisted diagnostics, and individualized treatment protocols that were not possible before. However, centralized healthcare data management systems encounter substantial obstacles, including single points of failure, limited patient control over personal information, vulnerability to cyber-attacks, and complex regulatory compliance issues. This article proposes BTHRiD, a blockchain-enabled, trustworthy healthcare, reliable IoT data-sharing mechanism for 6G networks. BTHRiD introduces a proof-of-storage consensus mechanism combining block validation with decentralized medical data storage and a layered propagation approach for efficient data distribution across healthcare nodes. Through mathematical modeling, we analyze block propagation latency and network decentralization characteristics, deriving optimal operational points for healthcare data sharing. Experimental results show that the proposed BTHRiD outperforms other solutions by 34% in processing latency and 28% in detection accuracy of malicious behavior. BTHRiD’s practical effectiveness is demonstrated in a real-world implementation example of tracking COVID-19 patient trajectories where data consistency was preserved at 96% during recovery phases while achieving a 42% reduction in storage overhead. Additional telemedicine, EHR sharing, and clinical trial application testing confirm the system’s adaptability to diverse healthcare requirements. The proposed mechanism enables secure, efficient, and trustworthy medical data sharing in 6G-IoT healthcare networks while preserving patient privacy and ensuring data reliability across heterogeneous healthcare environments.

Multimodal data have emerged as a cornerstone for understanding and analyzing complex human behaviors, particularly in mental health monitoring. In this study, we propose a deep learning-driven behavioral modeling framework for intelligence of social things (IoST)-based mental health monitoring and intervention, designed to integrate and analyze multimodal data—including text, speech, and physiological signals—captured from interconnected IoST devices. The framework incorporates an adaptive attention-based fusion mechanism that dynamically adjusts the contribution of each modality based on contextual relevance, enhancing the robustness of multimodal integration. Additionally, we employ a temporal-aware recurrent neural network with an attention mechanism to capture long-term dependencies and evolving behavioral patterns, ensuring precise mental health state prediction. To validate the framework, extensive experiments were conducted using three publicly available datasets: DAIC-WOZ, SEED, and MELD. Comparative experiments demonstrate the superior performance of the proposed framework, achieving state-of-the-art accuracy of 93.5%, F1-scores of 92.9%, and AUC-ROC of 0.95 values. Ablation studies highlight the critical roles of attention mechanisms and multimodal integration, showcasing significant performance improvements over single-modality and simplified fusion approaches. These findings underscore the framework’s potential as a reliable and efficient tool for real-time mental health monitoring in IoST environments, paving the way for scalable and personalized interventions.

The increasing demand for accurate and accessible cancer detection has driven the development of AI-driven diagnostic systems on consumer-grade medical electronics. However, deploying large-scale deep learning models on these devices presents challenges due to limited computational resources, network constraints, and data privacy concerns. In this study, we propose an innovative Split Federated Learning (SFL) framework that synergistically combines the strengths of federated learning and split learning. The SFL framework introduces a novel hybrid architecture where deep learning models are partitioned between client-side and server-side components, enabling efficient local feature extraction while preserving data privacy through secure, encrypted intermediate feature transmission. Experiments conducted on the BreakHis dataset demonstrate the framework’s effectiveness, with the proposed method achieving a 93.1% accuracy while significantly reducing communication overhead. We further analyze the impact of dimensionality reduction techniques and model partitioning configurations to balance accuracy with efficiency. Results show that the SFL framework provides a practical, scalable solution for distributed cancer detection in real-world medical applications, offering a promising approach for privacy-preserving and bandwidth-efficient AI deployment on medical consumer electronics.

Cervical cancer is a malignant tumor that endangers women's life and health. While deep learning has enhanced the accuracy of cervical cell classification, there remain obstacles impeding further performance enhancement, including the similarities between different categories, variability between single cells and cell clusters, as well as the accuracy of annotations. To address these issues, a novel multi-task collaborative framework for cervical cell classification is proposed. Specifically, to solve the similarity between different categories, we propose a grouping cell contrast auxiliary branch, which divides cervical cells into different groups and utilizes supervised contrastive learning to learn representative feature between different categories. And we introduce a multi-level cell classification auxiliary branch that simultaneously performs 5-class, 3-class, and 2-class classification tasks, and explicitly constrains the inter-class relationship learning of cervical cells. Furthermore, to solve the variations within the same category of single cells and cell clusters, we propose an image reconstruction auxiliary branch, which encourages the model to learn more contextual features. Finally, to solve subjectivity and accuracy of annotations, we introduce a soft label distillation auxiliary branch, which constrains the consistency of probability distributions between the encoder and the momentum encoder. It is worth noting that these auxiliary branches only work during training and will not add additional computational consumption during inference. We validate on the HSJCC, DSCC and SIPaKMeD datasets. Compared to existing methods, our approach has achieved outstanding performance and effectively mitigates the issues raised, demonstrating its effectiveness in automated cervical cell classification.

The rapid proliferation of Internet of Things (IoT) devices in healthcare has posed considerable hurdles in data processing, energy efficiency, and real-time response demands. This study presents a novel framework for cognitive energy-Efficient healthcare-enabled aerial computing and trajectory optimization (CEHEAT) to solve these difficulties. CEHEAT enhances energy efficiency by merging cognitive IoT (CIoT) capabilities with autonomous aerial vehicles (AAV) aerial computing to address the varied needs of healthcare applications. The system guarantees efficient data collecting and processing using cognitive skills, such as adaptive sensing and dynamic resource allocation while ensuring trustworthy healthcare monitoring. Simulation results demonstrate that CEHEAT significantly outperforms existing approaches across multiple performance metrics. The framework achieves 25%–35% higher energy efficiency, 3x faster convergence, and improved scalability compared to baseline methods. Moreover, CEHEAT’s adaptive sensing and speed control mechanisms contribute to overall energy savings while maintaining effective coverage of the healthcare IoT network. The findings indicate CEHEAT’s ability to improve the efficiency and effectiveness of smart healthcare systems, especially in situations that demand real-time monitoring, faster response as well as large quantities of data processing. This work gives useful guidelines for deploying the AAV-assisted aerial computing system in health facilities that extend the scope of healthcare delivery systems.