BIO-STREAMS demonstrates how large-scale, organized biobanks can revolutionize childhood obesity research while maintaining strict GDPR compliance. This paper presents a scalable infrastructure that successfully manages large amounts of sensitive health data, from over $\mathbf{5 3, 8 0 0}$ participants across six European countries (42.400 retrospective participants from existing cohorts and 11,400 prospective participants from new clinical studies). The platform demonstrates its capabilities in handling high-volume, high-velocity data streams involving clinical biospecimens, digital biomarkers, behavioral patterns, and real-time mobile application data. The system processes large amounts of multi-modal health data, leveraging federated big data architecture, privacy-preserving analytics and AI-driven machine learning pipelines. The infrastructure supports real-time stream processing, automated data harmonization at scale, and synthetic data generation using machine learning models. Initial validation demonstrates the platform's capacity to handle unprecedented data volumes while enabling cross-border big data analytics for obesity research. BIO-STREAMS establishes a new paradigm for big data applications in pediatric healthcare, showcasing scalable solutions for managing sensitive health data at European scale. It also serves as a model for digital biobanks targeting complex chronic diseases requiring multidisciplinary research.

Mental fatigue during driving poses significant risks to road safety, necessitating accurate assessment methods to mitigate potential hazards. This study explores the impact of individual variability in brain networks on driving fatigue assessment, hypothesizing that subject-specific connectivity patterns play a pivotal role in understanding fatigue dynamics. By conducting a linear regression analysis of subject-specific brain networks in different frequency bands, this research aims to elucidate the relationships between frequency-specific connectivity patterns and driving fatigue. As such, an EEG sustained driving simulation experiment was carried out, estimating individuals’ brain networks using the Phase Lag Index (PLI) to capture shared connectivity patterns. The results unveiled notable variability in connectivity patterns across frequency bands, with the alpha band exhibiting heightened sensitivity to driving fatigue. Individualized connectivity analysis underscored the complexity of fatigue assessment and the potential for personalized approaches. These findings emphasize the importance of subject-specific brain networks in comprehending fatigue dynamics, while providing sensor space minimization, advocating for the development of efficient mobile sensor applications for real-time fatigue detection in driving scenarios.

In the continuously evolving landscape of healthcare technology, the evolution of robotics has revolutionized awide spectrum of services. This situation created a variety of opportunities and challenges. One of the main challenges concerns the interaction of robots with human users and other robots, along with the safety aspect of such interactions. The current paper introduces a project aiming to tackle this challenge, initially via a literature review aiming to explore and structure the domain of robotic interactions in healthcare. Subsequently, the results are conceptualized in a domain meta-model, aiming to establish the foundation for an information system, based on a multi-view modeling approach, with the capabilities to support by documenting and facilitating safer interactions between healthcare robots and external agents. The current study focuses on the safety viewpoint of robotic interaction. The developed model is suitable for initiating the development of the abovementioned system that will use multi-view modeling principles. It is demonstrated in a use case derived from the associated ENDORSE EU project.

BACKGROUND:Falls have high socioeconomic costs. Information and communication technologies may support provision and monitoring of multisensory (MSR) physiotherapy programmes. The HOLOBalance platform used augmented reality holograms to provide patient-centred, individualised MSR. OBJECTIVES:To determine the platform's safety, acceptability and feasibility, investigate functional gait and dynamic balance benefits and provide data for a definitive trial. DESIGN AND SETTING:Single-blinded pilot randomised controlled feasibility study. Interventions were conducted at clinical sites or participants' homes in three European countries. PARTICIPANTS:Community-dwelling older adults (median age 73 years; 64.2% female) at risk of falls were enrolled (May 2020-August 2021). METHODS:Participants were randomised to an 8-week clinic or home-based telerehabilitation MSR or OTAGO (control group) programme. Compliance, satisfaction, and adverse events determined feasibility. Clinical outcomes, assessed (blinded) within one-week prior to and post-intervention, included functional gait assessment (FGA), Mini BESTest and cognitive function. RESULTS:Randomisation to completion rate was 76.15% with 109 participants recruited (n = 289 screened). Drop-out rate was similar between groups. Adverse events were reported (n = 3) in the control group. Sixty-nine percent would recommend the HOLOBalance intervention. Findings were similar for the home and clinic-based arms of each intervention; data was combined for analysis. FGA (95%CI [1.63, 4.19]) and Mini-BESTest (95%CI [1.46, 3.93]) showed greater improvement in the HOLOBalance group with a clinically meaningful change of 4/30 noted for the FGA. CONCLUSIONS:HOLObalance was feasible to implement and acceptable to older adults at risk of falls, with FGA and Mini-BEST improvements exceeding those for the OTAGO programme. A definitive trial is warranted.

Prostate cancer is a leading cause of male cancer worldwide. With more than 70 % of prostate cancers arising in the peripheral zone of the prostate, accurate segmentation of this region is of paramount importance for the effective diagnosis and treatment of the disease. Although peripheral zone is well recognized as one of the most challenging regions to delineate within the prostate, no algorithms specifically tailored for this segmentation task are currently available. The present study introduces a new deep learning (DL) algorithm, named as ResQu-Net, which is designed to accurately segment the peripheral zone (PZ) of the prostate on T2-weighted magnetic resonance imaging (MRI). Using three publicly available datasets, the ResQu-Net outperformed the six DL segmentation models used for comparison, namely the Attention U-Net, the Dense2U-Net, the Proper-Net, the TransU-net, the U-Net, and the USE-Net, demonstrating superior performance for different anatomical regions, such as the apex, the midgland and the base. The assessment of the suggested approach was conducted not only quantitatively (Sensitivity, Balanced Accuracy, Dice Score, 95 % Hausdorff Distance, and Average Surface Distance) but also qualitatively. For the qualitative evaluation the feature maps obtained from the last layers of each model were compared with the Density Map of the Ground Truth annotations using root mean squared error. Overall, the ResQu-Net model exhibits improved performance compared to other models, of more than 5 % and 1.87 mm in terms of Dice Score and 95 % Hausdorff Distance, respectively. These advancements may contribute significantly in addressing the challenges associated with PZ segmentation, and ultimately enabling improved clinical decision-making and patient outcomes.

ASCAPE Project is a study aiming to implement the advances of Artificial Intelligence (AI), to support prostate cancer survivors, regarding quality of life issues. The aim of the study is to determine characteristics of patients who accepted to join ASCAPE project. It results that participants of the study mainly originate from higher-educated societies that are better informed about the potential benefits of AI in medicine. Therefore, efforts should be focused on eliminating patients' reluctancy by better informing them on the potential benefits of AI.

The paper describes a cloud-based platform that utilizes Artificial Intelligence (AI) and Explainable AI techniques to deliver evidence-based, personalized interventions to individuals over 65 suffering or at risk of hearing loss, cardiovascular disease, cognitive impairments, balance disorders, or mental health issues, while supporting efficient remote monitoring and clinician-driven guidance. As part of the SMART BEAR integrated project, this platform has been developed to support its large-scale clinical trials. The platform consists of a standards-based data harmonization and management layer, as well as a security component, a Big Data Analytics system, a Clinical Decision Support system, and a dashboard component to facilitate efficient data collection across pilot sites.

Driving with fatigue is a major contributor to traffic accidents and is closely linked to central nervous system functions. To investigate the evolution of brain dynamics during simulated driving under different EEG rhythms, we conducted an experiment in which participants performed a 1 h driving task while their EEG signals were recorded. We used the complex network theory to analyze data derived from the driving stimulation and found that as fatigue deepened, small-world metrics, namely the path lengths, clustering coefficients, and measures of efficiency (global, local, nodal), showed alterations against the driving time. Additionally, a major correlation (corr = 0.98) was observed between the cluster coefficient with local efficiency in all frequency bands (theta, alpha, beta). Our findings suggest that driving fatigue can cause significant trends in brain network characteristics, such as path length (m = −103 to −93), (m = 98) for specific rhythms (beta, alpha, theta band, respectively) and their related brain functions, which could serve as objective indicators when evaluating the fatigue level and in the future, preventing driving fatigue and its consequences.

Nowadays, changes in the conditions and nature of the workplace make it imperative to create unobtrusive systems for the automatic detection of occupational stress, which can be feasibly addressed through the adoption of Internet of Things (IoT) technologies and advances in data analysis. This paper presents the development of a multimodal automated stress detection system in an office environment that utilizes measurements derived from individuals' interactions with the computer and its peripheral units. In our analysis, behavioral parameters of computer keyboard and mouse dynamics are combined with physiological parameters recorded by sensors embedded in a custom-made smart computer mouse device. To validate the system, we designed and implemented an experimental protocol simulating an office environment and included the most known work stressors. We applied known classifiers and different data labeling methods to the physiological and behavioral parameters extracted from the collected data, resulting in high-performance metrics. The feature-level fusion analysis of physiological and behavioral parameters successfully detected stress with an accuracy of 90.06% and F1 score of 0.90. The decision-level fusion analysis, combining the features extracted from both the computer mouse and keyboard, showed an average accuracy of 66% and an average F1 score of 0.56.

Pancreatic ductal adenocarcinoma (PDAC) constitutes a leading cause of cancer-related mortality despite advances in detection and treatment methods. While computed tomography (CT) serves as the current gold standard for initial evaluation of PDAC, its prognostic value remains limited, as it relies on diagnostic stage parameters encompassing tumor size, lymph node involvement, and metastasis. Radiomics have recently shown promise in predicting postoperative survival of PDAC patients; however, they rely on manual pancreas and tumor delineation by clinicians. In this study, we collected a dataset of pre-operative CT scans from a cohort of 40 PDAC patients to evaluate a fully automated pipeline for survival prediction. Employing nnU-Net trained on an external dataset, we generated automated pancreas and tumor segmentations. Subsequently, we extracted 854 radiomic features from each segmentation, which we narrowed down to 29 via feature selection. We then combined these features with the Tumor, Node, Metastasis (TNM) system staging parameters, as well as the patient's age. We trained a random survival forest model to perform an overall survival prediction over time, as well as a random forest classifier for the binary classification of two-year survival, using repeated cross-validation for evaluation. Our results exhibited promise, with a mean C-index of 0.731 for survival modeling and a mean accuracy of 0.76 in two-year survival prediction, providing evidence of the feasibility and potential efficacy of a fully automated pipeline for PDAC prognostication. By eliminating the labor-intensive manual segmentation process, our streamlined pipeline demonstrates an efficient and accurate prognostication process, laying the foundation for future research endeavors.

This poster presents a comprehensive assessment of the transformative potential of telehealth ecosystems, integrating Internet of Things (IoT), Internet of Medical Things (IoMT), and Artificial Intelligence (AI) technologies. The study explores their impact on healthcare delivery and markets, emphasising the need for robust cybersecurity measures and technological integration. By facilitating continuous monitoring, personalised interventions, and improved patient outcomes, the integration of advanced technologies in telehealth ecosystems has the potential to revolutionise healthcare delivery and reduce healthcare costs. However, successful implementation and maximisation of their benefits require collaborative research and adherence to ethical and regulatory standards.

Tinnitus is a highly prevalent condition, affecting more than 1 in 7 adults in the EU and causing negative effects on sufferers' quality of life. In this study, we utilised data collected within the "UNITI" project, the largest EU tinnitus-related research programme. Initially, we extracted characteristics from both auditory brainstem response (ABR) and auditory middle latency response (AMLR) signals, which were derived from tinnitus patients. We then combined these features with the patients' clinical data, and integrated them to build machine learning models for the classification of individuals and their ears according to their level of tinnitus-related distress. Several models were developed and tested on different datasets to determine the most relevant features and achieve high performances. Specifically, seven widely used classifiers were utilised on all generated datasets: random forest (RF), linear, radial, and polynomial support vector machines (SVM), naive bayes (NB), neural networks (NN), and linear discriminant analysis (LDA). Results showed that features extracted from the wavelet-scattering transformed AMLR signals were the most informative data. In combination with the 15 LASSO-selected clinical features, the SVM classifier achieved optimal performance with an AUC value, sensitivity, and specificity of 92.53%, 84.84%, and 83.04%, respectively, indicating high discrimination performance between the two groups.

Within the scope of prostate cancer diagnostic imaging, distinguishing lesions is challenging due to their subtle appearance and the prostate gland’s complexity. This study employed the nnU-Net, a state-of-the-art medical image segmentation model, on a dataset of 301 patients from 2 openly available datasets to identify whether lesion sizes are affecting the model’s performance. By applying t-SNE dimensionality reduction algorithm among dice score and respective lesion sizes, we found that nnU-Net behaves differently for lesions smaller than 9mm compared to lesions larger than 15mm. These insights can inform specialized training approaches for future deep learning models in prostate lesion detection.Clinical Relevance: The main contributions of this study is, to investigate whether lesion sizes affects nnU-Net’s deficiency leading to the development of more specialized models in respect to these factors.

Occupational stress is a major challenge in modern societies, related with many health and economic implications. Its automatic detection in an office environment can be a key factor toward effective management, especially in the post-COVID era of changing working norms. The aim of this study is the design, development and validation of a multisensor system embedded in a computer mouse for the detection of office work stress. An experiment is described where photoplethysmography (PPG) and galvanic skin response (GSR) signals of 32 subjects were obtained during the execution of stress-inducing tasks that sought to simulate the stressors present in a computer-based office environment. Kalman and moving average filters were used to process the signals and appropriately formulated algorithms were applied to extract the features of pulse rate and skin conductance. The results found that the stressful periods of the experiment significantly increased the participants' reported stress levels while negatively affecting their cognitive performance. Statistical analysis showed that, in most cases, there was a highly significant statistical difference in the physiological parameters measured during the different periods of the experiment, without and with the presence of stressors. These results indicate that the proposed device can be part of an unobtrusive system for monitoring and detecting the stress levels of office workers.

The identification of the location of prostate cancer is of paramount importance for improved treatment. This process is strictly bonded with the accurate segmentation of the prostate gland and its zones, on MR images. In the present study, an ensemble of 3 deep learning models along with a Meta-learner module able to refine the outcomes of the models, is proposed (Transi-Net) to segment the prostate's transition zone. A method to quantify the model's uncertainty is introduced to measure the confidence of an architecture with respect to its final decision. The backbone of Transi-Net consist the original U-net, Dense2U-net and Bridged U-net models. The proposed model showcased significant improvement in comparison with its base components as well as an independent model, the USE-Net, while it was proven more confident about its decision. The proposed model resulted in an improvement of 5%, 3%, 3% and 4% for Sensitivity, Balanced Accuracy, Dice Score and Rand Error Index respectively, compared to the second best, USE-Net.

Brain–Machine Interfaces (BMIs) have made significant progress in recent years; however, there are still several application areas in which improvement is needed, including the accurate prediction of body movement during Virtual Reality (VR) simulations. To achieve a high level of immersion in VR sessions, it is important to have bidirectional interaction, which is typically achieved through the use of movement-tracking devices, such as controllers and body sensors. However, it may be possible to eliminate the need for these external tracking devices by directly acquiring movement information from the motor cortex via electroencephalography (EEG) recordings. This could potentially lead to more seamless and immersive VR experiences. There have been numerous studies that have investigated EEG recordings during movement. While the majority of these studies have focused on movement prediction based on brain signals, a smaller number of them have focused on how to utilize them during VR simulations. This suggests that there is still a need for further research in this area in order to fully understand the potential for using EEG to predict movement in VR simulations. We propose two neural network decoders designed to predict pre-arm-movement and during-arm-movement behavior based on brain activity recorded during the execution of VR simulation tasks in this research. For both decoders, we employ a Long Short-Term Memory model. The study’s findings are highly encouraging, lending credence to the premise that this technology has the ability to replace external tracking devices.

Artificial Intelligence (AI) has shown the ability to enhance the accuracy and efficiency of physicians. ChatGPT is an AI chatbot that can interact with humans through text, over the internet. It is trained with machine learning algorithms, using large datasets. In this study, we compare the performance of using a ChatGPT API 3.5 Turbo model to a general model, in assisting urologists in obtaining accurate, valid medical information. The API was accessed through a Python script that was applied specifically for this study based on 2023 EAU guidelines in PDF format. This custom-trained model leads to providing doctors with more precise, prompt answers about specific urologic subjects, thus helping them, ultimately, providing better patient care.

Tinnitus is the perception of sound when no actual external noise is present. Tinnitus is highly prevalent, with more than 1 in 7 adults in the EU having tinnitus, and it causes negative effects on quality of life for many individuals. However, there is currently no cure for tinnitus and its pathophysiology and genesis are unknown. Auditory evoked potentials (AEPs) provide a non-invasive means by which the electrical signals evoked by the brain can be recorded, and constitute a useful indicator for the evaluation of auditory disorders such as tinnitus and hearing loss. The present study analyzed a total of 98 auditory middle evoked potential (AMLR) waveforms, a subtype of AEPs, from 49 participants with subjective tinnitus, attempting to identify differences in AMLR parameters between sufferers with and without tinnitus distress. The waveforms were divided into three categories according to the ear's hearing level, and comparisons were made between sufferers in the same hearing level category. The results of the analysis indicated some statistically significant differences in AMLR latencies and amplitudes between the compared groups. Clinical Relevance– Identification of the electro-physiological profile of subjective tinnitus sufferers based on the distress manifested by tinnitus using AMLRs.

Auditory evoked potentials (AEPs) are brain-derived electrical signals, following an auditory stimulus, utilised to examine any obstructions along the brain neural-pathways and to diagnose hearing impairment. The clinical evaluation of AEPs is based on the measurements of the latencies and amplitudes of waves of interest; hence, their identification is a prerequisite for AEP analysis. This process has proven to be complex, as it requires relevant clinical experience, and the existing software for this purpose has little practical use. The aim of this study was the development of two automated annotation tools for ABR (auditory brainstem response)- and AMLR (auditory middle latency response)-tests. After the acquisition of 1046 raw waveforms, appropriate pre-processing and implementation of a four-stage development process were performed, to define the appropriate logical conditions and steps for each algorithm. The tools’ detection and annotation results, regarding the waves of interest, were then compared to the clinicians’ manual annotation, achieving match rates of at least 93.86%, 98.51%, and 91.51% respectively, for the three ABR-waves of interest, and 93.21%, 92.25%, 83.35%, and 79.27%, respectively, for the four AMLR-waves. The application of such tools in AEP analysis is expected to assist towards an easier interpretation of these signals.