Informa (Italy)

The chapter describes how the initiative to bring bio-medical and medical-data scientists together with law scholars, was conceived. The EuCARE project is a research initiative funded by the European Union, focusing on the study of the SARS-CoV-2 pandemic. It involves nearly 30 partners worldwide and faced numerous legal and ethical issues, thus serving as a test-bed for the European legal framework for the use of personal health data. EuCARE is based on cohorts of patients, healthcare workers, and students, with activities encompassing a laboratory network, artificial intelligence, and organizational management. The projects’ cahiers de doleances regarding ethical and legal issues regards specifically data reuse, the lack of regulatory uniformity across European countries, international data sharing and studies involving minors. Data reuse, essential for the project, clashes with varying interpretations of the GDPR among countries. The fragmentation of regulations has created difficulties in conducting multicentr studies. Data sharing with international organizations and non-EU countries has required careful consideration of data protection regulations. Studies involving minors have highlighted how the need for careful ethical evaluation, with differing approval regulations among countries, could hamper these studies.

Boson-sampling problems are specific cases of multi-photon quantum interference in which the complexity of sampling from the output distribution of multiple photons on multiple modes arises from its relation to certain matrix functions that cannot be efficiently computed in polynomial time using the best-known classical algorithms. Specifically, gaussian boson sampling (GBS) is a protocol that employs Gaussian states as inputs to a linear interferometer, and whose output samples can be used to accelerate graph search and optimization problems [1]. To date, GBS experiments have been reported by using path or time-bin encoding of the optical modes.

BackgroundPost COVID-19 condition (PCC) affects 10–40% of patients and is characterized by persisting symptoms at ≥ 4 weeks after SARS-CoV-2 infection. Symptoms can last 7 or even more months. How long PCC persists and any changes in its clinical phenotypes over time require further investigation. We investigated PCC trajectories and factors associated with PCC persistence.Material and methodsWe included both hospitalized COVID-19 patients and outpatients from February 2020 to June 2023, who underwent at least one follow-up visit after acute infection at San Paolo Hospital, University of Milan. Follow-up visits were conducted at the post COVID-19 clinic or via telemedicine. During each follow-up examination, patients completed a short version of the World Health Organization (WHO) Case Report Form (CRF) for ongoing symptoms, the Hospital Anxiety and Depression Scale (HADS), and a screening tool for Post-Traumatic Stress Disorder (PTSD). Statistical analyses involved Chi-square, Mann–Whitney, Kruskal–Wallis tests, and logistic regression analysis.ResultsWe enrolled 853 patients (median age 62, IQR 52–73; 41% females). 551/853 (64.6%), 152/418 (36.4%) and 21/69 (30.4%) presented PCC at median follow up of 3 (IQR 2–3), 7 (IQR 6–10) and 26 (IQR 20–33) months, respectively (p < 0.001). The main clinical phenotypes were fatigue, respiratory sequelae, brain fog and chronic pain; anosmia/dysgeusia was observed mostly in the first post-acute period. Female sex, acute disease in 2020, a longer hospital stay and no COVID-19 vaccination were associated with persistence or resolution of PCC compared to never having had PCC. Anxiety, depression and PTSD were more common in PCC patients. By fitting a logistic regression analysis, acute infection in 2020 remained independently associated with persistent PCC, adjusting for age, sex, preexisting comorbidities and disease severity (AOR 0.479 for 2021 vs 2020, 95%CI 0.253–0.908, p = 0.024; AOR 0.771 for 2022 vs 2020, 95%CI 0.259–2.297, p = 0.641; AOR 0.086 for 2023 vs 2020, 95%CI 0.086–3.830, p = 0.565).ConclusionsThere was a reduction in the PCC burden 7 months following the acute phase; still, one third of patients experienced long-lasting symptoms. The main clinical presentations of PCC remain fatigue, respiratory symptoms, brain fog, and chronic pain. Having had SARS-CoV-2 infection during the first pandemic phases appears to be associated with persistent PCC.

We consider the application of Neural Networks (NNs) to the case of multi-monostatic inversion of two-dimensional metallic scatterers. The aim is twofold. First, we want to reconstruct the support of the involved objects from the scattering data. Second, we want to demonstrate a pruning process to reduce the NN complexity without a worsening of its performance. In particular, the NN result is compared to that achieved with the standard approach of reconstructing the re-flection coefficient by a Truncated Singular Value Decomposition (TSVD) scheme. The approach is validated experimentally.

We developed an innovative system that combines Natural Language Understanding (NLU), a curated knowledge base, and the efficient management of a Large Language Model (LLM) to support motivational health coaching. Using Rasa as the core framework, we enhanced it by integrating the GPT-3.5-turbo model. Users opt into reflective dialogues during conversations. When they respond to open-ended questions, their input goes directly to the GPT-3.5-turbo model, allowing for more flexible responses. To provide curated trustworthy content, we integrated a knowledge provision component that searches a PDF-based knowledge base and generates user-friendly responses using Retrieval-Augmented Generation. We tested the system in a real-world scenario by deploying it on a Nao robot in seven older adults’ homes for 1–2 weeks, encouraging positive behavioral changes in some users. Our system serves as a valuable foundation for building an even more integrated, personalized system that can connect with other Application Programing Interfaces (APIs) and integrate with home sensors and edge devices.

This paper addresses the monitoring and continual learning of data-based dynamical models. Throughout the lifespan of any process, many changes can occur. In an indirect control design framework, in order to maintain an effective control system, it is crucial to monitor the modelling performance and adapt the existing model to possible system variations while preserving previously acquired information. A comprehensive methodology is hence proposed to detect a system-model mismatch and its cause, and to update the model accordingly. The proposed idea consists in leveraging control charts constructed on operational data to spot an anomaly and to determine its cause (endogenous or exogenous). The procedure then provides an adaptation algorithm based on the type of change detected: if endogenous, the model is 'partially' updated by means of a Moving Horizon Estimation (MHE) algorithm, if exogenous, the model is 'incrementally' updated by means of a model uncertainty estimation algorithm. The proposed methodology is tested in simulation on a district heating system benchmark, showing promising results from the monitoring and continual learning perspective.

This paper explores advancements in improving the well-being of aging people at home by integrating data-driven environmental dialogues. Building upon a preliminary study focused on human-coach conversations, our research investigates the implementation of these advancements in the e-VITA virtual coaching system. Core enhancements include utilizing smart environmental sensing as dialogue triggers and crafting dialogue scenarios tailored to the user's context. The focus on heat stroke prevention, utilizing the Wet-Bulb Globe Temperature (WBGT) index, highlights the system's proactive approach to dynamically changing environmental conditions. Through this methodology, we aim to address the specific needs of the aging population by fostering a more personalized and adaptive interaction, emphasizing solutions for independence and safety.

The European Project GATEKEEPER aims to develop a platform and marketplace to ensure a healthier independent life for the aging population. In this platform the role of HL7 FHIR is to provide a shared logical data model to collect data in heterogeneous living, which can be used by AI Service and the Gatekeeper HL7 FHIR Implementation Guide was created for this purpose. Independent pilots used this IG and illustrate the impact of the approach, benefit, value, and scalability.

With a substantial rise in life expectancy throughout the last century, society faces the imperative of seeking inventive approaches to foster active aging and provide adequate aging care. The e-VITA initiative, jointly funded by the European Union and Japan, centers on an advanced virtual coaching methodology designed to target essential aspects of promoting active and healthy aging. This paper describes the technical framework underlying the e-VITA virtual coaching system platform and presents preliminary feedback on its use. At its core is the e-VITA Manager, a pivotal component responsible for harmonizing the seamless integration of various specialized devices and modules. These modules include the Dialogue Manager, Data Fusion, and Emotional Detection, each making distinct contributions to enhance the platform's functionalities. The platform's design incorporates a multitude of devices and software components from Europe and Japan, each built upon diverse technologies and standards. This versatile platform facilitates communication and seamless integration among smart devices such as sensors and robots while efficiently managing data to provide comprehensive coaching functionalities.