The effectiveness of Digital Therapeutics (DTx) relies on understanding and shaping human behavior, yet development is hindered by fragmented conversational scripts and repetitive chatbot implementation. Integrating advanced agentic components such as Large Language Models (LLMs) and multi-agent systems further complicates clinical safety, data provenance, and ethical risks. We present Flow Builder, a no-code platform within the MAESTRO (Multi-Agent Enhanced System for Therapy Routine Orchestration) framework, designed to standardize conversation design. Leveraging a modular block-based hierarchy with over seventeen specialized processors, from text delivery to semantic retrieval and multi-step LLM reasoning, Flow Builder enables clinicians to focus on therapeutic logic while ensuring safe, consistent, and scalable agentic execution.

Neoadjuvant chemotherapy (NAC) enables tumor downstaging and assessment of response in early breast cancer (EBC). Pathological complete response (pCR) predicts favorable outcomes, but patients with residual disease are heterogeneous, and the prognostic value of residual tumor biology remains incompletely defined. We retrospectively analyzed 586 patients with EBC treated with NAC between 2000 and 2021. Baseline clinical, pathological, and treatment-related variables—including residual disease characteristics—were collected. The primary endpoints were pCR and long-term outcomes. Event-free survival (EFS), relapse-free survival (RFS), and overall survival (OS) were estimated using Kaplan–Meier curves and compared with log-rank tests. Multivariable logistic and Cox regression identified independent predictors of pCR and survival. Overall, 36.3

The integration of Large Language Models (LLMs) into conversational systems has greatly enhanced their expressive capabilities but also introduced challenges in structure, control, and reproducibility. Current design approaches often fall between rigid, rule-based systems that are predictable but limited in scalability, and fully LLM-driven models that enable natural interaction but lack transparent logic. We present MAESTRO (Multi-Agent Enhanced System for Therapy Resources Orchestration), a framework for the trustworthy integration of LLMs in complex settings such as psychological digital interventions. Central to MAESTRO is a flow-based abstraction model that represents conversational logic as assemblies of modular, reusable blocks. This approach allows designers to construct explicit interaction flows in which LLMs can serve as bounded-reasoning components, preserving predictability while enabling controlled flexibility.

The prognosis for Hormonal Receptor positive-HER2-negative (HR+ HER2-negative) metastatic breast cancer (mBC) has significantly improved by advances in hormone therapies, targeted drugs, and antibody–drug conjugates (ADCs). Nevertheless, maintaining quality of life (QoL), managing symptoms, and reducing treatment-related toxicity remain essential. Background: eHealth solutions offer new opportunities to enhance patient engagement and well-being through digital tools. This paper aims to delineate the fundamental functionalities and objectives of TreC_Metha, a technologically advanced instrument to provide effective support during all care process of patients diagnosed with HR+HER2-negative mBC able to proactively change its configuration depending on the treatment line or on the intra-line treatment phase the patient undergoes, as set by the healthcare team. Methods: The TreC_Metha platform was developed through a structured, evidence-based four-phase process aimed at scalability, usability, and clinical relevance. The development began with a formal analysis of the metastatic breast cancer (mBC) care pathway using BPMN modeling to map phases, activities, and stakeholders, highlighting differences from early-stage breast cancer. This analysis informed the identification of key points where digital support could enhance care. Patient needs were assessed through a web-based questionnaire (N = 20) and two focus groups (N = 11), enabling a participatory design approach. Based on these insights, the platform’s functional and non-functional requirements were defined, leading to the design and implementation of a patient-facing mobile app and a clinical dashboard tailored to mBC-specific needs. Results: Preliminary findings from the web survey focus groups revealed significant gaps in communication and information delivery during the mBC care journey, contributing to patient anxiety and reduced confidence. Participants expressed a preference for digital and printed resources to improve understanding and facilitate interactions with healthcare providers. These insights informed the development of the TreC_Metha platform. The clinical dashboard enables real-time monitoring and decision-making, while the mobile app supports bidirectional communication, therapy adherence, and patient-reported data collection. A system prototype is currently under refinement and will undergo usability testing with a small cohort of users. Following this phase, the pilot study will evaluate the platform’s impact on QoL, aiming for a ≥10% improvement in outcome measures and contributing to a more patient-centered care model in the mBC setting. Conclusions: TreC_Metha represents an innovative tool that may enable involvement and active participation in the mBC care process for both a multidisciplinary care team of professionals and the patient, and that can be easily adapted to other cancer types and chronic diseases.

This paper presents DigiTher, a flexible AI-based platform for clinical research on digital therapeutics, enabling personalized treatment plans and real-time monitoring of patient progress. The DigiTher platform has been designed to deliver three specific kinds of Digital Therapeutics, which are mainly based on conducting motivational dialogues with the patients or providing multimedia material to accompany and support patients. Conversational solutions and sensing technology are used to (i) support the management of chronic conditions (e.g., nutritional ones), (ii) run Cognitive Behavioral Therapy (e.g., within mental health management scenarios), and (iii) support Behavioral Enhancement Interventions (e.g., improve lifestyle).

Background:The use of technologies in the health field has progressively increased. Within the context of a broader project funded by the Italian Ministry of Health (TELEMECHRON study), a randomised controlled trial (RCT) has been conducted in the Autonomous Province of Trento on type 2 diabetes individuals with an untargeted glycated haemoglobin (HbA1c) level. Methods:The overall aim was to evaluate the impact of the "TreC Diabete" digital platform, including a smartphone application (app) and a dashboard. This open-label, parallel-group, 1:1 allocation ratio RCT in which the intervention group used the app for data entry, symptoms questionnaire, communication with healthcare staff and medication recording, while the control group received standard care. The primary endpoint was change in HbA1c levels at 12 months between groups. Results:Between December 2022 and August 2023, 103 participants were enrolled (51 intervention; 52 control), with a median age of 67 years old, time from diabetes diagnosis to enrolment 13 years, and 72% male. At 12 months, the median change in HbA1c levels did not differ significantly between groups. Regarding app usage, data entries decreased significantly from the first quarter to the second quarter but subsequently stabilised (p = 0.001). System usability (from 42 responders in the intervention group) had a median score of 95 (range: 0-100), indicating a high level of satisfaction with the platform. Discussion:The study faced several challenges, including platform technical issues, service interruption, data entry anomalies and difficulties in participant recruitment. Study generalisability may be limited by the sample's demographics, as the trial predominantly included younger male individuals with a specific HbA1c level. Conclusion:The study highlighted key factors for future implementations, including understanding technology benefits, addressing adoption barriers, and providing education and support to both patients and healthcare providers.

In oncologia e in particolare nella cura del tumore mammario, il ricorso alla telemedicina si è dimostrato essere una via sicura ed efficace per migliorare la qualità della vita e dell'assistenza per i pazienti. L'emergenza Covid-19 e l'esigenza di ridurre gli accessi ai presidi ospedalieri hanno rappresentato un momento di accelerazione nel disegno e nell'utilizzo di strumenti di telemedicina.L'uso della telemedicina può trovare ampia applicazione nell'assistenza alle pazienti affette da tumore mammario che, grazie alla cronicizzazione della malattia, hanno un bisogno continuo di assistenza e di disponibilità di informazioni chiare e accessibili.L'efficacia degli interventi di telemedicina può essere migliorata attraverso i processi partecipativi di co-design che coinvolgano gli utenti finali e gli stakeholder in tutti gli aspetti dello sviluppo dell'intervento. Questo contributo riporta un'esperienza di co-design partecipato finalizzato allo sviluppo di un'applicazione mobile per le pazienti affette da tumore mammario all'interno della Rete Senologica dell'APSS di Trento.

This article reports the study protocol of a nationwide multicentric study in seven Italian regions aimed at assessing the effectiveness of a digitally supported approach for the early screening of frailty risk factors in community-dwelling older adults. SUNFRAIL+ is a prospective observational cohort study aimed at carrying out a multidimensional assessment of community-dwelling older adults through an IT platform, which allows to connect the items of the SUNFRAIL frailty assessment tool with a cascading multidimensional in-depth assessment of the bio–psycho–social domains of frailty. Seven centers in seven Italian regions will administer the SUNFRAIL questionnaire to 100 older adults. According to the answers provided by older adults, they will be subjected to one or more validated in-depth scale tests in order to perform further diagnostic or dimensional evaluations. The study aims to contribute to the implementation and validation of a multiprofessional and multistakeholder service model for the screening of frailty in community-dwelling older adult population.

Introduction Type 2 diabetes mellitus (T2DM) is a non-communicable disease representing one of the most serious public health challenges of the twenty-first century. Its incidence continues to rise in both developed and developing countries, causing the death of 1.5 million people every year. The use of technology (e.g. smartphone application—App) in the health field has progressively increased as it has been proved to be effective in helping individuals manage their long-term diseases. Therefore, it has the potential to reduce the use of health service and its related costs. The objective of this study is to evaluate the impact of using a digital platform called “TreC Diabete” embedded into a novel organisational asset targeting poorly controlled T2DM individuals in the Autonomous Province of Trento (PAT), Italy. Methods This trial was designed as a multi-centre, open-label, randomised, superiority study with two parallel groups and a 1:1 allocation ratio. Individuals regularly attending outpatient diabetes clinics, providing informed consent, are randomised to be prescribed TreC Diabete platform as part of their personalised care plan. Healthcare staff members will remotely assess the data shared by the participants through the App by using a dedicated online medical dashboard. The primary end-point is the evaluation of the Hb1Ac level at 12-month post-randomisation. Data will be analysed on an intention-to-treat (ITT) basis. Discussion This trial is the first conducted in the PAT area for the use of an App specifically designed for individuals with poorly controlled T2DM. If the effects of introducing this specific App within a new organisational asset are positive, the digital platform will represent a possible way for people diagnosed with T2DM to better manage their health in the future. Results will be disseminated through conferences and peer-reviewed journals once the study is completed. Trial registration ClinicalTrials.gov NCT05629221. Registered on November 29, 2022, prior start of inclusion.

The onset of cancer disease is a traumatic experience for both patients and their families that suddenly change the patient’s life and is accompanied by important physical, emotional, and psycho-social problems. The complexity of this scenario has been exacerbated by the COVID-19 pandemic which dramatically affected the continuity of the provision of optimal care to chronic patients. Telemedicine can support the management of oncology care paths by furnishing a suite of effective and efficient tools to monitor the therapies of cancer patients. In particular, this is a suitable setting for therapies that are administered at home. In this paper, we present an AI-based system, called Arianna, designed and implemented to support and monitor patients treated by the professionals belonging to the Breast Cancer Unit Network (BCU-Net) along the entire clinical path of breast cancer treatment. We describe in this work the three modules composing the Arianna system (the tools for patients and clinicians, and the symbolic AI-based module). The system has been validated in a qualitative way and we demonstrated how the Arianna solution reached a high level of acceptability by all types of end-users by making it suitable for a concrete integration into the daily practice of the BCU-Net.

Previous studies have shown that ethanol decreases the level of ionized calcium (iCa) in the blood, and appears to prevent a compensatory increase in parathyroid hormone level. We have shown, however, that the presence of ethanol interferes with the measurement of blood iCa by the most commonly used iCa analyzer. It is impossible to interpret ethanol-induced alterations in Ca-regulating hormone levels without accurate measurement of blood iCa, thus the purpose of this study was to determine if ethanol decreases blood iCa levels independent of methodological artifacts. The time course of ethanol's effect and the relationship between iCa and blood ethanol concentration (BEC) were also examined. Rats (n=22) received ethanol (1.5 or 3 g/kg body weight) or saline by intraperitoneal injection. Blood samples were obtained by tail nick at 0, 2, 6, 24, 48 h and 8 days postinjection, and analyzed for iCa, pH, and BEC. Blood iCa and pH were measured using the I-Stat Clinical Analyzer, whose performance is not affected by the presence of ethanol. Ethanol administration resulted in a decrease in blood iCa levels. The magnitude and time course of the decrease varied with dose of ethanol, being greater and more prolonged with the higher dose, and blood iCa levels were not fully recovered at 48 h postinjection. No significant relationship was found between individual iCa and BEC values. This study confirms that ethanol decreases blood iCa levels, independent of methodological artifacts. Prolonged disruptions in Ca homeostasis resulting from ethanol consumption could have implications for long-term bone health.

The International Journal of Integrated Care (IJIC) is an online, open-access, peer-reviewed scientific journal that publishes original articles in the field of integrated care on a continuous basis.IJIC has an Impact Factor of 2.913 (2021 JCR, received in June 2022)The IJIC 20th Anniversary Issue was published in 2021.

Background A platform designed to support the home management of oral anticancer treatments and provide a secure web-based patient–health care professional communication modality, ONCO-TreC, was tested in 3 cancer centers in Italy. Objective The overall aims of the trial are to customize the platform; assess the system’s ability to facilitate the shared management of oral anticancer therapies by patients and health professionals; and evaluate system usability and acceptability by patients, caregivers, and health care professionals. Methods Patients aged ≥18 years who were candidates for oral anticancer treatment as monotherapy with an Eastern Cooperative Oncology Group performance status score of 0 to 1 and a sufficient level of familiarity with mobile devices were eligible. ONCO-TreC consisted of a mobile app for patients and a web-based dashboard for health care professionals. Adherence to treatment (pill count) and toxicities reported by patients through the app were compared with those reported by physicians in medical records. Usability and acceptability were evaluated using questionnaires. Results A total of 40 patients were enrolled, 38 (95%) of whom were evaluable for adherence to treatment. The ability of the system to measure adherence to treatment was high, with a concordance of 97.3% (95% CI 86.1%-99.9%) between the investigator and system pill count. Only 60% (3/5) of grade 3, 54% (13/24) of grade 2, and 19% (7/36) of grade 1 adverse events reported by physicians in the case report forms were also reported in the app directly by patients. In total, 94% (33/35) of patients had ≥1 app launch each week, and the median number of daily accesses per patient was 2. Approximately 71% (27/38) and 68% (26/38) of patients used the app for messages and vital sign entering, respectively, at least once during the study period. Conclusions ONCO-TreC is an important tool for measuring and monitoring adherence to oral anticancer drugs. System usability and acceptability were very high, whereas its reliability in registering toxicity could be improved. Trial Registration ClinicalTrials.gov NCT02921724; https://www.clinicaltrials.gov/ct2/show/NCT02921724

Fondazione Bruno Kessler is developing a mobile app prototype for empowering citizens to improve their health conditions through different lifestyle interventions that will be incorporated into a mobile application for lifestyle promotion of the Province of Trento in the context of the Trentino Salute 4.0 Competence Center. The envisioned interventions are based on promoting behaviour change in various domains such as physical activity, mental health and nutrition. In particular, the nutrition component is a self-monitoring module that collects dietary habits to analyse them and recommend healthier eating behaviours. Dietary assessment is completed using a Food Frequency Questionnaire on the Mediterranean diet that is presented to the user as a grid of images. The questionnaire returns feedback on 11 aspects of nutrition. Although the questionnaire used in the application only consists of 24 questions, it still could be a bit overwhelming and a bit crowded when shown on the screen. In this paper, we tried to find a machine-learning-based solution to reduce the number of questions in the questionnaire. We proposed a method that uses the user's previous answers as additional information to find the goals that need more attention. We compared this method with a case where the subset of questions is randomly selected and with a case where the subset is chosen using feature selection. We also explored how large the subset should be to obtain good predictions. All the experiments are conducted as a multi-target regression problem, which means several goals are predicted simultaneously. The proposed method adjusts well to the user in question and has the slightest error when predicting the goals.

The use of oral treatments is constantly growing in the area of onco-hematology, raising adherence and safety issues. There is an increasing body of literature highlighting the importance of patient empowerment in the self-management of cancer therapies. Within this scenario, the ONCO-TreC platform was customized and fine-tuned through a prospective multicenter training-validation study in cancer patients treated with oral anticancer drugs. This prospective randomized trial was designed to compare the effectiveness of two different strategies, ie, an electronic diary (ONCO-TreC) and a paper diary, for the management of oral cancer treatments in patients with solid and hematological tumors. Ad hoc strategies are planned to measure and monitor adherence to treatment and to assess usability and acceptability of the electronic diary. Informed consent will be obtained from all study participants. This innovative eHealth system is expected to contribute to increasing the adherence to and safety of cancer care, promoting patient empowerment and improving patient-doctor communication. Ethical approval was obtained from the Independent Ethics Committees of the participating institutions (CEIIAV protocol no. 2982/2020; reference no. 2108). Findings will be disseminated through peer-reviewed journals, conferences and event presentations. ClinicalTrials.gov NCT04826458; Institutional ID no. IRST100.28

Explainable AI aims at building intelligent systems that are able to provide a clear, and human understandable, justification of their decisions. This holds for both rule-based and data-driven methods. In management of chronic diseases, the users of such systems are patients that follow strict dietary rules to manage such diseases. After receiving the input of the intake food, the system performs reasoning to understand whether the users follow an unhealthy behaviour. Successively, the system has to communicate the results in a clear and effective way, that is, the output message has to persuade users to follow the right dietary rules. In this paper, we address the main challenges to build such systems: i) the natural language generation of messages that explain the reasoner inconsistency; ii) the effectiveness of such messages at persuading the users. Results prove that the persuasive explanations are able to reduce the unhealthy users' behaviours.

Explainable AI aims at building intelligent systems that are able to provide a clear, and human understandable, justification of their decisions. This holds for both rule-based and data-driven methods. In management of chronic diseases, the users of such systems are patients that follow strict dietary rules to manage such diseases. After receiving the input of the intake food, the system performs reasoning to understand whether the users follow an unhealthy behavior. Successively, the system has to communicate the results in a clear and effective way, that is, the output message has to persuade users to follow the right dietary rules. In this paper, we address the main challenges to build such systems: (i) the Natural Language Generation of messages that explain the reasoner inconsistency; and, (ii) the effectiveness of such messages at persuading the users. Results prove that the persuasive explanations are able to reduce the unhealthy users’ behaviors.

Introduction: Health care has been deeply revolutionized by the new wave of information and communication technology (ICT) development, particularly related to the electronic/personal health record (PHR). The present paper describes the original design and implementation approach followed in the Trentino Province (Italy) to promote an Integrated Care Model for patients' empowerment and data repository, by means of an evolving Personal Health Record - PHR platform, named TreC (Trentino Citizens Clinical Record). Materials and Methods: The TreC Platform is conceived as a communication hub among different stakeholders. The core assumption of the TreC platform strategy is to consider the citizen/patient as main manager and owner of both his/her own health and his/her contacts with the health care systems. Results: Over the years, the TreC platform has represented the core pillar in the digitalization process promoted at Province level. This has been strategically embedded in the multi-faceted e-government strategy endorsed by the Province of Trento. So far (October 2018), more than 89,000 citizens within the Province of Trento are using TreC platform as a way to communicate with the health care system and access their own personal health records. Conclusions: The experience gained through the TreC platform implementation and its results are promising, supporting the idea that a PHR platform can represent a key driving factor in improving health care quality and efficiency, both from a patient and a health care staff perspective.