Artificial intelligence (AI) is increasingly applied in a wide range of healthcare and Intensive Care Unit (ICU) areas to serve—among others—as a tool for disease detection and prediction, as well as for healthcare resources’ management. Since sepsis is a high mortality and rapidly developing organ dysfunction disease afflicting millions in ICUs and costing huge amounts to treat, the area can benefit from the use of AI tools for early and informed diagnosis and antibiotic administration. Additionally, resource allocation plays a crucial role when patient flow is increased, and resources are limited. At the same time, sensitive data use raises the need for ethical guidelines and reflective datasets. Additionally, explainable AI is applied to handle AI opaqueness. This study aims to present existing clinical approaches for infection assessment in terms of scoring systems and diagnostic biomarkers, along with their limitations, and an extensive overview of AI applications in healthcare and ICUs in terms of (a) sepsis detection/prediction and sepsis mortality prediction, (b) length of ICU/hospital stay prediction, and (c) ICU admission/hospitalization prediction after Emergency Department admission, each constituting an important factor towards either prompt interventions and improved patient wellbeing or efficient resource management. Challenges of AI applications in ICU are addressed, along with useful recommendations to mitigate them. Explainable AI applications in ICU are described, and their value in validating, and translating predictions in the clinical setting is highlighted. The most important findings and future directions including multimodal data use and Transformer-based models are discussed. The goal is to make research in AI advances in ICU and particularly sepsis prediction more accessible and provide useful directions on future work.

Explainable artificial intelligence (AI) focuses on developing models and algorithms that provide transparent and interpretable insights into decision-making processes. By elucidating the reasoning behind AI-driven diagnoses and treatment recommendations, explainability can gain the trust of healthcare experts and assist them in difficult diagnostic tasks. Sepsis is characterized as a serious condition that happens when the immune system of the body has an extreme response to an infection, causing tissue and organ damage and leading to death. Physicians face challenges in diagnosing and treating sepsis due to its complex pathogenesis. This work aims to provide an overview of the recent studies that propose explainable AI models in the prediction of sepsis onset and sepsis mortality using intensive care data. The general findings showed that explainable AI can provide the most significant features guiding the decision-making process of the model. Future research will investigate explainability through argumentation theory using intensive care data focused on sepsis patients.

This study introduces a novel end-to-end framework designed to optimize patient outcomes and operational efficiency in intensive care units (ICUs) through fairness-aware and accurate length of stay (LOS) predictions within an IoT-enabled environment. Motivated by the concept of “fairness through unawareness,” our proposed framework employs a demographic feature exclusion strategy, preventing access to potentially discriminatory information, and thus enforcing an inductive bias that redirects learning toward non-discriminatory pattern dependencies. To address the loss of static information, we introduce a custom graph neural network that dynamically reconstructs patient relationships over time, adapting from static demographics to evolving inter-patient correlations via multi-modal embeddings (e.g., medications, procedures, vitals, conditions) and learned feature-driven edge formation. We evaluate our approach on MIMIC-IV across diverse time-series formats and demonstrate its superiority over top performing LOS prediction methods, showcasing notable performance improvements while maintaining comparable computational complexity. Additionally, we present a performance analysis highlighting our approach’s computational and predictive scalability across different graph sizes at inference, while underscoring its intrinsic ability to improve performance when deprived of demographic features by dynamically readjusting its expressive power, unlike all evaluated methodologies in this study. Finally, we present a comparative study against the literature’s top-performing LOS prediction approaches that highlights our method’s predictive superiority, demonstrating significant performance gains in predicting LOS exceeding 3 and 7 days, with improvements of up to 13.1% AUC and 10.3% ARP, and 14.1% AUC and 42.0% ARP, respectively. The code is available at https://github.com/icsa-hua/mimic_fairness_aware_gnn

The emergence and spread of deadly pandemics has repeatedly occurred throughout history, causing widespread infections and loss of life. The rapid spread of pandemics have made governments across the world adopt a range of actions, including non-pharmaceutical measures to contain its impact. However, the dynamic nature of pandemics makes selecting intervention strategies challenging. Hence, the development of suitable monitoring and forecasting tools for tracking infected cases is crucial for designing and implementing effective measures. Motivated by this, we present a hybrid pandemic infection forecasting methodology that integrates compartmental model and learning-based approaches. In particular, we develop a compartmental model that includes time-varying infection rates, which are the key parameters that determine the pandemic's evolution. To identify the time-dependent infection rates, we establish a hybrid methodology that combines the developed compartmental model and tools from optimization and neural networks. Specifically, the proposed methodology estimates the infection rates by fitting the model to available data, regarding the COVID-19 pandemic in Cyprus, and then predicting their future values through either a) extrapolation, or b) feeding them to neural networks. The developed approach exhibits strong accuracy in predicting infections seven days in advance, achieving low average percentage errors both using the extrapolation (9.90%) and neural network (5.04%) approaches.

Severe acute respiratory disease SARS-CoV-2 has had a found impact on public health systems and healthcare emergency response especially with respect to making decisions on the most effective measures to be taken at any given time. As demonstrated throughout the last three years with COVID-19, the prediction of the number of positive cases can be an effective way to facilitate decision-making. However, the limited availability of data and the highly dynamic and uncertain nature of the virus transmissibility makes this task very challenging. Aiming at investigating these challenges and in order to address this problem, this work studies data-driven (learning, statistical) methods for incrementally training models to adapt to these nonstationary conditions. An extensive empirical study is conducted to examine various characteristics, such as, performance analysis on a per virus wave basis, feature extraction, "lookback" window size, memory size, all for next-, 7-, and 14-day forecasting tasks. We demonstrate that the incremental learning framework can successfully address the aforementioned challenges and perform well during outbreaks, providing accurate predictions.