The emergence of COVID-19 and the pandemic have changed and devastated every aspect of our lives. Before effective vaccines are widely used, it is important to predict the epidemic patterns of COVID-19. As SARS-CoV-2 is transferred primarily by droplets of infected people, the incorporation of human mobility is crucial in epidemic dynamics models. This study expands the susceptible–exposed–infected–recovered compartment model by considering human mobility among a number of regions. Although the expanded meta-population epidemic model exhibits better performance than general compartment models, it requires a more accurate estimation of the extended modeling parameters. To estimate the parameters of these epidemic models, the meta-population model is incorporated with deep learning models. The combined deep learning model generates more accurate modeling parameters, which are used for epidemic meta-population modeling. In order to demonstrate the effectiveness of the proposed hybrid deep learning framework, COVID-19 data in South Korea were tested, and the forecast of the epidemic patterns was compared with other estimation methods.

Diarrhea is responsible for killing around 525,000 children every year, even though it is preventable and treatable. This research focuses on both houseflies’ roles and humans’ roles in carrying pathogens causing diarrhea as multiple disease carriers. Both human and fly compartmental models are simulated with five diseases control strategies in order to identify the epidemic dynamics. The framework considers the life cycle of flies modeled into eggs, larvae, pupae, susceptible flies, and carrier flies, while the human system follows a compartment model as susceptible, infected, recovered, and back to susceptible again (SIRS). The relationships are modeled into an ordinary differential equation-based compartmental system. Then, the control parameters of the compartmental framework are analyzed. In order to propose effective control methods, five control strategies are considered: (1) elimination of flies’ breeding site, (2) sanitation, (3) installation of UV light trap, (4) good personal and food hygiene, and (5) water purification. Then, overall, ten control scenarios using the five control strategies are analyzed. Among them, effective control solutions considering various dynamic epidemiology are provided with the simulations and analyses. The proposed framework contributes to an effective control strategy in reducing the number of both flies and infected humans, since it minimizes the spread of the disease and considers cost-effectiveness.

Patient falls are a major concern in healthcare due to their impact on patient safety, prolonged hospital stays, and increased costs. Traditional fall prevention methods often lack precision and adaptability, emphasizing the need for predictive approaches. This study reviews the current literature and explores the integration of human-centered artificial intelligence (AI)-based decision support systems to improve fall prevention through proactive risk assessment and prediction. This system enables early identification of fall risks, facilitating personalized interventions and real-time monitoring via advanced sensors and wearable devices. These technologies may provide timely alerts to caregivers and support administrators in optimizing resource allocation. Additionally, this study highlights the importance of systems thinking, recognizing patient falls as outcomes of interconnected system failures. By leveraging causal loop analysis and feedback mechanisms, healthcare stakeholders can develop dynamic, system-wide strategies to enhance fall prevention and operational efficiency.

Sepsis is a severe medical condition caused by an abnormal response to infection, impacting overall patient safety and quality of care in healthcare management. Although early warning systems have been developed to identify patients at higher risk of sepsis, they often generate too many false positive alarms, causing digital fatigue and being ignored by healthcare providers. This problem escalated into late recognition of sepsis, as heavy workload and low staffing levels made completing the sepsis bundle within an hour challenging. To address this issue, the current study proposes a Human-AI Decision Support Framework (HADS) to identify high-risk patients and improve sepsis prevention and management. More specifically, we develop a prediction model that incorporates physicians' expert knowledge to identify at-risk patients for early recognition. This retrospective study used records from 74,567 patients in the Medical Information Mart for Intensive Care (MIMIC-IV). Second, mitigation strategies are recommended to enhance decision-making by leveraging a systems-thinking approach. The proposed framework, utilizing a Bayesian Belief Network, outperforms the existing alert system in terms of model performance and reduces false alarms by 48%. Results highlight that antibiotic prescription, initiating blood culture collection, oxygen saturation monitoring, and hourly observations are the critical interventions that significantly influence the onset and the management of sepsis. Our framework eliminates several processes in current sepsis pathways, reducing response time and improving outcomes by preventing deterioration during the critical golden hour. Future research directions and applications for healthcare management, based on the proposed framework, are discussed.

BACKGROUND Sepsis is a life-threatening condition where the body's reaction to infection leads to organ dysfunction. It is a significant patient safety concern, requiring prompt diagnosis and treatment to prevent complications or death. For such prevention, an AI-driven Decision Support System (DSS) may play a vital role in managing sepsis through early detection, alerting clinicians to potential cases, and facilitating prompt interventions. OBJECTIVE This paper reviews the existing AI-driven DSS applications in sepsis diagnosis and provides initial intervention and suitable treatment recommendations. All original literature (qualitative and quantitative) was reviewed to understand the current scope of DSS for sepsis management and to analyze existing methods used to evaluate and report the systems. METHODS A literature review, guided by PRISMA 2020 and supported by bibliometric analysis, was conducted in June 2024. The search utilized two electronic databases, SCOPUS and PubMed, and included articles focused on using DSS for diagnosing and managing sepsis. RESULTS The search strategy identified 3,470 articles, with 37 meeting the inclusion criteria. The publications spanned from 2010 to 2024, with 57% conducted in the United States. The studies primarily explored the use of AI-driven DSS for diagnosing sepsis in adults and managing its progression. Various data types, such as electronic health records, expert-derived knowledge, and clinical notes, were utilized to determine risk factors linked to sepsis. CONCLUSIONS Current research needs more evidence on the tangible impact of DSS in aiding healthcare providers with sepsis-related decision-making. Additional studies are required to refine the design and implementation of clinical DSS, assess their effects on clinical practices, identify barriers to adoption, and explore innovative strategies for advancing sepsis management. Improving these systems' accuracy, reliability, and usability could enhance sepsis detection, optimize treatment decisions, and ultimately save more lives in combating this deadly condition.