Time-series foundation models excel at tasks like forecasting across diverse data types by leveraging informative waveform representations. Wearable sensing data, however, pose unique challenges due to their variability in patterns and frequency bands, especially for healthcare-related outcomes. The main obstacle lies in crafting generalizable representations that adapt efficiently across heterogeneous sensing configurations and applications. To address this, we propose NormWear , the first paradigm multi-modal and ubiquitous framework of foundation model designed to extract generalized and informative representations from wearable sensing data. Specifically, we design a channel-aware attention mechanism with a shared special liaison [CLS] token to detect signal patterns in both intra-sensor and inter-sensors. This helps the model to extract more meaningful information considering both time series themselves and the relationships between input sensors. This helps the model to be widely compatible with various sensors settings. NormWear is pretrained on a diverse set of physiological signals, including PPG, ECG, EEG, GSR, and IMU, from various public datasets. Our model shows exceptional generalizability across 11 public wearable sensing datasets, spanning 18 applications in mental health, body state inference, vital sign estimation, and disease risk evaluation. It consistently outperforms competitive baselines under zero-shot, partial-shot, and full-shot settings, indicating broad applicability in real-world health applications.

Ensuring equitable Artificial Intelligence (AI) in healthcare demands systems that make unbiased decisions across all demographic groups, bridging technical innovation with ethical principles. Foundation Models (FMs), trained on vast datasets through self-supervised learning, enable efficient adaptation across medical imaging tasks while reducing dependency on labeled data. These models demonstrate potential for enhancing fairness, though significant challenges remain in achieving consistent performance across demographic groups. Our review indicates that effective bias mitigation in FMs requires systematic interventions throughout all stages of development. While previous approaches focused primarily on model-level bias mitigation, our analysis reveals that fairness in FMs requires integrated interventions throughout the development pipeline, from data documentation to deployment protocols. This comprehensive framework advances current knowledge by demonstrating how systematic bias mitigation, combined with policy engagement, can effectively address both technical and institutional barriers to equitable AI in healthcare. The development of equitable FMs represents a critical step toward democratizing advanced healthcare technologies, particularly for underserved populations and regions with limited medical infrastructure and computational resources.

This study introduces a novel approach to enhance acne severity classification by leveraging cross-dataset training within a Label Distribution Learning (LDL) framework. Traditional acne grading methods are often subjective and inconsistent, while automated systems struggle to generalize across diverse datasets, limiting their real-world applicability. This research addresses this challenge by integrating data from multiple sources (Acne04 and AcneSCU) to train a robust model capable of accurately classifying acne severity despite variations in image quality, lighting, and skin tone. We explore the impact of different backbone architectures (ResNet50, EfficientNet B7, and BEiT) within the LDL framework, which is specifically designed to handle the inherent ambiguity in acne severity labeling. Our results demonstrate that cross-dataset training within the LDL framework significantly improves generalization performance compared to models trained on individual datasets. Additionally, results demonstrate that integrating EfficientNet B7 and BEiT enhances the model’s accuracy and robustness. This novel approach offers a promising solution for developing scalable and reliable automated acne grading systems suitable for telemedicine and dermatology applications, ultimately aiding dermatologists in providing more precise and personalized treatment plans.

Joint blind source separation (JBSS) is commonly used to uncover latent structures across multiple datasets. However, it often struggles with high-dimensional data and inaccurate latent dimensionality estimation, limiting its scalability and separation accuracy. To address these challenges, we propose a novel common subspace independent vector analysis model based on a bounded multivariate generalized Gaussian mixture distribution, referred to as BMIVA-CS. The model extracts low-rank common sources across datasets while modeling subject-specific variations. It incorporates a bounded indicator function and leverages spatial correlations to improve robustness, particularly under noisy, high-dimensional conditions. We validate the model through simulations and experiments on resting-state fMRI datasets from individuals with schizophrenia and autism. BMIVA-CS reliably identifies clinically relevant sources and consistently localizes affected brain regions across subjects. These results demonstrate the effectiveness of BMIVA-CS and its potential as a diagnostic tool for neurological and psychiatric disorders using rs-fMRI data.

Accurately predicting Emergency Department (ED) visits is essential for optimising resource allocation, including staffing adjustments and Operating Room scheduling. Despite the proliferation of AI-driven models, effective ED visit prediction remains challenging due to limited generalisability, susceptibility to overfitting and underfitting, scalability and the complexity of fine-tuning hyper-parameters. To address these challenges, we propose a novel Meta-Learning Gradient Booster (Meta-ED) approach to forecast daily ED visits. Meta-ED leverages a comprehensive dataset spanning 23 years from Canberra Hospital, incorporating exogenous variables such as socio-demographic characteristics, healthcare usage, chronic diseases, diagnoses and climate parameters. Meta-ED combines four foundational learners—CatBoost, Random Forest, Extra Trees and LightGBM—with a Multi-Layer Perceptron (MLP) as the master-level learner, thereby enhancing predictive precision by integrating the strengths of diverse base models. Our comparative analysis, which involved testing 23 models against a set of predefined criteria, demonstrates the superior performance of Meta-ED, achieving an accuracy of 85.7% (95% CI [85.4%, 86.0%]) and outperforming prominent models like XGBoost, Random Forest, AdaBoost, LightGBM and Extra Trees by up to 106.3%. Furthermore, incorporating climate features resulted in a 3.25% improvement in prediction accuracy, effectively capturing seasonal variations that influence patient volumes. These results underscore the potential of Meta-ED to advance predictive analytics in complex healthcare environments.

As digital innovation progresses, individuals are increasingly, often unknowingly, exposed to digital temptations and deceptive tactics. These risks, now magnified by foundation AI models, call for protective measures beyond what current digital health technologies can offer. This article introduces Health Behavioral Security , a novel AIoT-driven framework that positions trusted AIoT devices as a distributed “System 0” layer—an always-on, pre-conscious filter that can sense, interpret, and modulate persuasive cues in real time. Guided by five behavior-centric constructs—Assets, Threats, Vulnerabilities, Risks, and Countermeasures—the framework could establish a secure behavioral ecosystem in which adaptive sensing and nudging loops help preserve autonomy while promoting well-being. We present this vision, outline key research challenges, and discuss future directions for advancing AIoT-based behavioral security in today’s increasingly digital society.

The increasingly large amount of available biomedical literature is making it difficult to gather and synthesise all the necessary information. Moreover, this domain-specific task demands a high level of reliability in the generated text and concepts. Pre-trained large language models have recently shown promising results. Given the specific requirements of biomedical text summarisation, our evaluation focuses on extractive models, prioritising the accuracy of the generated text. In this article, we evaluate the capabilities of 18 general-domain and biomedical pre-trained language models in various configurations on the biomedical extractive summarisation task using one single and two multi-document datasets consisting of 33,000, 5,000 and 470,000 PubMed articles, respectively. We performed the comparison using several well-known metrics, namely ROUGE-1, ROUGE-2, ROUGE-L, BERTScore, BLEU and METEOR. The main contribution of this work lies in providing a detailed performance analysis, highlighting the differences between general-domain and biomedical models, and identifying key factors that influence model performance in extractive summarisation tasks within the biomedical domain. Experimental results show that biomedical models tend to result in higher recall, while general-domain models produce higher precision, while general-domain models produce higher precision. This corresponds to more expressive summaries for biomedical models and shorter summaries for general-domain models.

While deep learning techniques are nowadays a powerful field to automatically learn and perform accurate EEG data classification in the clinical context, they still lack wide acceptance within the medical and health research community. This lack of trust is associated with the high complexity deep learning algorithms typically have which contributes to a low level of interpretability of the outcome and predictions. This survey aims to provide a comprehensive discussion of the latest advancements in deep learning models applied to EEG analysis, while also emphasizing research in explainable AI within this domain. It explores commonly used algorithms in EEG analysis, their main application areas, and the insights provided by XAI. Moreover, the survey addresses current limitations, such as the evaluation of XAI methods and the need for clinical validation, as well as ongoing challenges in this field. One critical insight from this review is the relative paucity of clinical evaluations of the rich stock of proposed techniques and methods for AI explainability. By showcasing various applications and breakthroughs in EEG analysis facilitated by XAI, the survey underscores the potential of these technologies to revolutionize neurological diagnosis and treatment, paving the way for wider acceptance and implementation in clinical settings.

Parkinson’s Disease (PD) is a neurodegenerative condition primarily affecting the elderly but also occurring in younger individuals. It is caused by a progressive loss of nerve cells in the brain’s substantia nigra that release dopamine, essential for controlling movements. Dopamine deficiency results in symptoms affecting both motor and non-motor functions, which vary among individuals. Diagnosis relies on clinical symptoms and medical history, often supported by brain scans, as there is no specific diagnostic test available. Diagnosis is challenging due to vague initial symptoms resembling other conditions. Current research indicates that AI can significantly enhance data and image analysis, aiding in the diagnosis and monitoring of PD progression. To this aim, this study proposes a hybrid model allowing the integrated use of clinical data and single photon emission computed tomography images of a patient to predict the presence of the disease. The approach consists of a combination of two types of neural networks, an LSTM for clinical data and a CNN for images. The validation is performed on a widely validated dataset belonging to the Parkinson’s Progression Markers Initiative, from which the data recording visits of 1,814 patients were extracted. The obtained results are interesting and useful to address further investigations.

EEG data classification plays a pivotal role in understanding brain activity and its applications in various domains. Deep learning has emerged as a powerful paradigm for automatically learning complex patterns from raw data, eliminating the need for manual feature extraction. However, in the context of medical data, and in particular for EEG analysis, the use of deep learning approaching while having been very successful is not being included in medical diagnosis routines, yet. The aim of this survey is twofold. On one side, it provides a comprehensive overview of the current state-of-the-art in EEG data classification, with a specific focus on the use of deep learning techniques. On the other side, it also addresses the clinician community, explaining the power and trustfulness of such new approaches. The survey begins with an introduction highlighting the limitations of traditional model-based approaches and the potential of deep learning in EEG data classification. The fundamental principles and architectures of deep learning models are presented, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and graph convolution neural networks (GCNNs) that have been successfully applied to EEG data classification tasks. A detailed review and analysis of existing literature on deep learning-based EEG data classification are provided, categorizing the studies based on the type of the input data, e.g., sequences, images, graphs, or multi-modalities. We also discuss about the existing tools and technologies for EEG data classification and highlights the challenges and limitations associated with deep learning in EEG data classification, including limited data availability, interpretability of deep models, and bias mitigation. Potential solutions and ongoing research efforts to overcome these challenges are explored, providing insights into the future directions of this field. This survey serves as a valuable resource for researchers, practitioners, and healthcare professionals involved in EEG data classification. It provides an extensive understanding of the advancements, challenges, and potential applications of deep learning techniques in this domain, guiding further research and development of accurate and interpretable approaches for EEG data analysis and interpretation.