Earticle

Sequential decision-making in dynamic, heterogeneous environments is often hindered by multivariate and correlated outcomes. This study introduces a unified Copula-CNN-LSTM Deep Q-Network (DQN) framework for multi-stage individualized policy learning in pseudo temporal settings. Motivated by the need for agents that account for inter-outcome dependencies, we extend static covariates from benchmark datasets (Boston Housing and Wine Quality Red) into pseudo-temporal sequences to emulate state transitions. Multivariate rewards with controlled correlations (ρ = 0.5 and ρ = −0.5) are standardized via an empirical copula transformation to assess policy robustness under varying dependency structures. The DQN agent optimizes policies using experience replay and temporal discounting of state-action reward trajectories. The framework demonstrates stable convergence in average rewards across both datasets under positive and negative correlation structures. Analysis of the resulting dynamic conditional average treatment effects (CATEs) across outcome dimensions highlights the model’s ability to discern heterogeneous treatment impacts. Furthermore, learned policy matrices and dynamic Directed Acyclic Graphs (DAGs) reveal interpretable temporal dependencies, with edge structures reflecting the complex multivariate nature of the optimal policy. Overall, the proposed framework effectively captures inter-temporal dependencies and adapts to correlated rewards, providing a scalable and interpretable solution for sequential decision making in complex environments.

This study investigates the pathogeneses and interactions among diseases associated with multiple organ dysfunction syndrome (MODS). The research applied a three-step analytical framework using data mashups and big data techniques. First, association rule analysis was conducted using hospital mortality data from general hospitals. Second, text-mining techniques were applied to medical information collected through web crawling from the PLM network. Third, social media data from Twitter and blogs were analyzed to identify hidden disease relationships. The study identified significant associations between pneumonia, sepsis, respiratory insufficiency, lung cancer, and MODS. Results showed that complications, infections, viruses, and inflammation play major roles in disease progression. Pneumonia was strongly linked to respiratory insufficiency and MODS through reduced immune function and lung damage. Sepsis and septic shock were also found to contribute significantly to organ failure and mortality. The research demonstrated that integrating structured and unstructured medical data can reveal meaningful pathogenic pathways. The proposed framework provides a quantitative method for mapping disease interactions and improving clinical understanding. This study contributes to future medical big data research by supporting predictive analysis and clinical decision-making.

The rapid advancement of artificial intelligence (AI) technology is driving innovative changes across the entire healthcare sector. To systematically identify the latest research trends in the field of Medical AI, this study collected abstracts from a total of 1,043 academic papers published between 2006 and 2026 and applied a BERTopic-based topic modeling method to identify and classify major research topics. The analysis revealed that Medical AI research is categorized into 35 specific topics, including medical education and the use of ChatGPT/LLMs, medical imaging and deep learning diagnostics, privacy protection and federated learning, AI explainability (XAI) and ethics, medical device regulation and legal liability, clinical data and disease prediction, IoMT and security, and COVID-19 and public health applications. The number of papers has shown an explosive increase since 2023. This study provides practical implications for setting future directions in Medical AI research and formulating policies.

Big data has a lot of influence around the world. Singapore, EU, United States, and Japan have been trying to find national long-term policies and future issues through Big Data. Korea also established Big Data strategy center to find new growth power. So, we tried to analyze various issue technologies through Big Data analysis methods. Issue technologies are Big Data, 3D printing, Internet of Things (IoT), wearable computing devices (Smart watch and Google glasses) which are introduced by National IT Industry Promotion Agency, Gartner, and SK C&C. We think the end users of technology are public, and SNS is a suitable place to share their thoughts. Otherwise, News uses easy words to understand and delivers the information for public. This study proposes a new approach predicting the future of technologies by simulating human brains: left and right brains. For this this study analyzed SNS data and News data by using text mining and opinion mining. With the sensitivity of SNS and the logicality of News, we found elements of technologies and classified them by positivity and negativity. And then, we did three analyses using Futures Wheel. First, the element analysis of five technologies was conducted. Second, we used these elements to predict the future of technologies. Finally, the possibility of convergence of five technologies was confirmed. This paper has three contributions. First, we found the opportunity and threaten elements of five technologies. Second, we predicted the future of technologies with these elements. Third, we identified the opportunity and threaten elements for the convergence of each technology.

Pressure injuries continue to impose a substantial clinical and economic burden on hospitalized adults and older adults in long-term care, despite the availability of established prevention bundles and specialized support surfaces. At the same time, recent advances in voice interfaces, flexible sensors, explainable analytics, and textile-based thermal systems have made it increasingly plausible to conceptualize an integrated prevention platform. The purpose of this study was to synthesize the technological components, clinical evidence, and translational limitations of voice-based pressure injury neglect alerts and pressureredistribution smart cooling/heating systems. A structured literature review was performed across PubMed, Web of Science Core Collection, Scopus, IEEE Xplore, ScienceDirect, SpringerLink, Wiley Online Library, JMIR, and MDPI for studies published from January 2020 to May 2026. Eligible studies addressed pressure injury prevention or enabling technologies directly relevant to prevention, including voice interaction, multimodal sensing, posture classification, predictive analytics, support surfaces, microclimate management, and cooling/heating actuation. Thirty-seven studies were included in the qualitative synthesis, and 34 representative international journal articles were prioritized in this manuscript. The strongest clinical evidence remained concentrated in multicomponent prevention bundles and specialized support surfaces. The highest engineering maturity was observed in battery-free or flexible multimodal sensing of pressure, temperature, hydration, and posture. Voice-based systems were promising for repositioning adherence, remote follow-up, and caregiver escalation, but direct trials using pressure injury incidence as the primary endpoint were scarce. Active cooling/heating technologies were advancing rapidly in smart textiles and thermoelectric wearables, yet translation to fully integrated medical support surfaces remained limited. The most realistic next-generation architecture is therefore a layered platform that combines multimodal sensing, explainable risk alerts, voice interaction, pressure redistribution, and adjunctive microclimate control. Prospective clinical trials should evaluate pressure injury incidence, interface pressure, local temperature/humidity, alarm burden, caregiver workload, and cost-effectiveness simultaneously.