ICT4AWE 2025 Abstracts

Area 1 - Ageing Well – Social and Human Sciences Perspective
Full Papers Short Papers
Area 2 - Digital Health
Full Papers Short Papers
Area 3 - Telemedicine and Independent Living
Full Papers Short Papers

Area 1 - Ageing Well – Social and Human Sciences Perspective

Full Papers
Paper Nr: 38
Title:

Password Authentication for Older People: Problems, Behaviours and Strategies
Authors:

Burak Merdenyan and Helen Petrie
Abstract: Many aspects of life are now conducted online, and many services requiring a secure account, usually password protected. Creating and tracking many online accounts and passwords is difficult for everyone. For older people it may be particularly problematic but vitally important as online accounts now give access to many healthcare, financial and support services. This study used an online questionnaire to investigate the behaviours, problems, and strategies in relation creating and using password-protected online accounts with a sample of 75 older UK participants (aged 65 to 89) and compare them with a similar sample of young UK participants (aged 18 to 30). The results were surprising, with unexpected differences between the groups, but many similarities. For example, older participants had no difficulties creating passwords of the right length, whereas young participants had difficulties in that task. Older participants had many more complex strategies for creating and remembering passwords, while young participants relied more on re-using old passwords with small changes which then probably caused difficulties remembering them. These results suggest we need to rethink the approach to better supporting older people in password creation and use, taking a more universal design approach, supporting all users with a range of options.
Download
Short Papers
Paper Nr: 18
Title:

Information Seeking Behavior Associated with Willingness for COVID-19 Vaccination in 60+ Estonians
Authors:

Marianne Paimre and Andri Ahven
Abstract: Research consistently suggests that seeking health information (HI) online can positively impact individuals' health behavior choices (HBC). However, the relationship between online health information-seeking behavior (OHISB) and COVID-19 vaccination among older adults – often considered a digitally underserved group – remained largely underexplored. This study contributes to bridging this gap by investigating the OHISB of Estonians aged 60+ and its associations with HBC, including COVID-19 vaccination readiness (CVR). Survey data from 329 respondents revealed that frequent online HI searches, along with better access to digital devices, higher self-reported digital skills, and higher levels of education and income, were positively associated with increased CVR. Preference for reliable HI sources, such as international organizations and physician-curated websites, further reinforced vaccine support, while vaccine refusers predominantly relied on alternative media. However, no clear association was found between OHISB and other HBCs, such as healthy eating, physical activity, or drug use, suggesting the need for further investigation. The study highlights the potential of digital technologies and online health information seeking (OHIS) among older generations in promoting health-protective behavior during a health crisis. These findings also underscore the critical role of promoting digital literacy and access to credible HI to enhance public health outcomes.
Download
Paper Nr: 21
Title:

Older Adults Say Yes to Technology: How Digital Empowerment of this Audience Helps Reduce Loneliness
Authors:

Juliana Camargo, Telmo Silva and Jorge Ferraz de Abreu
Abstract: The HUGTV system (Helping Unite Generations through Television) was designed to help older adults stay connected with their families by combining TV notifications with voice commands, making communication easier and more accessible. To understand their perceptions of both technologies, 110 interviews were conducted between April 2022 and November 2023, with participants aged between 60 and 91. The results indicate that 84.5% of participants watch television on a daily basis, with 70% of the total considering it a companion.. The study also revealed that the proposed system was generally well received by this audience, especially the functionality of viewing photos and videos of family members on TV. The television proved to be a familiar and comfortable device for older adults, which reduces the levels of fear and anxiety related to new technologies and resources. Voice interaction, for example, were significantly accepted, especially among individuals with visual and motor limitations. The study concludes that older adults recognize the value of technology for communication and information, and TV, being a familiar device, offers a promising path for digital inclusion and the reduction of loneliness.
Download
Paper Nr: 37
Title:

Familiarity Breeds Confidence: Creating Effective Digital Literacy Resources for Older Adults
Authors:

Meredith Kellenberger, Sarah Leidich and Dharini Balasubramaniam
Abstract: As population ageing is observed globally, and technology continues to expand into most parts of our lives, many older adults face challenges in adapting to a world that they feel unprepared to inhabit — one filled with increasingly intertwined and fast-evolving technologies that have become necessary to fully participate in society. The age-related digital divide, caused by the gaps in access, motivation and skills of many older adults to use digital technologies compared to younger people, is now a significant problem for the wellbeing and independence of older adults and requires urgent solutions. Increasing the digital literacy and confidence of older adults may help reduce this gap. However, effective strategies for improving digital literacy in later life must take into account the needs and preferences of older learners. This paper reports on two pilot studies conducted to create and evaluate prototype digital literacy resources to discover effective forms and content. This work draws from literature, related work, and feedback on our prototypes from older adults in local communities. Our findings indicate that older adults often prefer device and task-specific digital literacy resources in printed form as a familiar medium before progressing to digital learning, and value community involvement in ongoing support for the learning process. Resources that use figure-of-speech based language and informative diagrams can also be beneficial to older adults, particularly when learning novel digital tasks. These preliminary insights also highlight the potential for conflicting requirements from a diverse demographic and the need for further exploration of the topic.
Download
Paper Nr: 52
Title:

Digitalization of an Integrated “Social and Health” Care Path
Authors:

Barbara Leoni, Erika Guareschi and Marco Foracchia
Abstract: The integrated care pathway, designed by the Italian regulatory framework, for individuals who are non-self-sufficient or have serious disabilities, is crucial not only to address healthcare needs but also to meet social needs. It provides access to social and healthcare services through single points of access (PUA) and multidisciplinary integrated teams working at PUAs to define the integrated individual care plan (PAI).This pathway must be organized through close collaboration between healthcare organizations and local social services, requiring integration of services, human resources, as well as the digitalization of processes and interoperability between IT systems. The introduction of a shared computerized platform, configurable and interoperable, enables the creation of a unified socio-health record, facilitating a truly integrated and digitalized care journey where the patient is at the center of attention.
Download
Paper Nr: 69
Title:

The Role of Gender and Clear Communication in Digital Health Engagement for Blood Clot Management
Authors:

Ionel Roşu, Petru Kallay and Tudor Dan Mihoc
Abstract: This study examines factors influencing older patients’ use of the Internet to access health-related information, focusing on gender differences and the clarity of information provided by emergency units about anticoagulant treatment and blood clot management. Data were collected from respondents aged 60+ through a survey, with responses weighted to align with population demographics. Statistic methods and regressions were employed to analyze the data. The results indicate that gender significantly predicts Internet use, along with the clarity of emergency service offerings. However, reverse analysis suggests that Internet usage does not significantly improve patient understanding of emergency unit support.
Download

Area 2 - Digital Health

Full Papers
Paper Nr: 16
Title:

Analysing the Impact of Images and Text for Predicting Human Creativity Through Encoders
Authors:

Amaia Pikatza-Huerga, Pablo Matanzas de Luis, Miguel Fernandez-De-retana Uribe, Javier Peña Lasa, Unai Zulaika and Aitor Almeida
Abstract: This study explores the application of multimodal machine learning techniques to evaluate the originality and complexity of drawings. Traditional approaches in creativity assessment have primarily focused on visual analysis, often neglecting the potential insights derived from accompanying textual descriptions. The research assesses four target features: drawings’ originality, flexibility and elaboration level, and titles’ creativity, all labelled by expert psychologists. The research compares different image encoding and text embeddings to examine the effectiveness and impact of individual and combined modalities. The results indicate that incorporating textual information enhances the predictive accuracy for all features, suggesting that text provides valuable contextual insights that images alone may overlook. This work demonstrates the importance of a multimodal approach in creativity assessment, paving the way for more comprehensive and nuanced evaluations of artistic expression.
Download
Paper Nr: 23
Title:

Evaluating the Impact on Usability and Acceptance of ECAs in m-Health Applications for Older Adults
Authors:

Raquel Lacuesta Gilaberte, Eva Cerezo Bagdasari and Javier Navarro-Alamán
Abstract: In the context of m-health applications, developing user-friendly interfaces to improve usability and acceptance by older adults has become a prominent research topic. The use of embodied conversational agents (ECAs) seems promising as they allow interacting through natural verbal and nonverbal communication. However, analyses about the design and acceptance of embodied conversational agents embedded in m-health applications for older adults are needed. In this paper, we present a study carried out to analyse the usability and acceptance of ECAs interfaces in m-health applications, compared to traditional tactile text interfaces. The study carried out has involved 23 users over 65 years old with promising results. The ECA interface was positively assessed and its acceptance increased compared to the traditional one, but although the feelings arisen are positive, users still claim for less complexity and a more careful design.
Download
Paper Nr: 25
Title:

MentalRAG: Developing an Agentic Framework for Therapeutic Support Systems
Authors:

Francisco R. E. Silva, Pedro A. Santos and João Dias
Abstract: This paper introduces MentalRAG, a multi-agent system built upon an agentic framework designed to support mental health professionals through the automation of patient data collection and analysis. The system effectively gathers and processes high-sensitivity mental health data from users. It employs locally run open-source models for most tasks, while leveraging advanced state-of-the-art models for more complex analyses, ensuring the maintenance of data anonymity. The system’s models have showed improvements in delivering empathetic and contextually adaptive responses, particularly in sensitive contexts such as emotional distress and crisis management. Notably, an integrated agent for detecting levels of suicidal ideation allows the system to assess and respond sensitively to diverse levels of risk, promptly alerting mental health professionals as needed. This innovation represents a stride towards creating a more reliable, efficient, and ethically responsible mental health support tool, capable of addressing both patient and doctor needs effectively while minimizing associated risks.
Download
Paper Nr: 33
Title:

Interactive Solutions for Advancing Attention Deficit Hyperactivity Disorder Diagnosis and Management in Children
Authors:

Rim Walha, Fadoua Drira, Imen Guizani, Wissem Regaieg, Khaoula Khemakhem, Maryam Chaabane, Hela Ayedi and Yousr Moalla
Abstract: Attention Deficit Hyperactivity Disorder (ADHD) is a complex neurodevelopmental condition that influences a person’s thinking patterns and behavior. Early diagnosis and intervention for ADHD are crucial for improving outcomes, as they can significantly enhance the overall development and well-being of those affected. However, many families encounter various challenges that can lead to delays in treating this disorder. To address these issues, this paper presents an innovative and interactive gaming-based platform designed to enhance the assessment and therapy of ADHD in children. By leveraging engaging gameplay mechanics and user-friendly mobile technology, the proposed solution aims to provide a dynamic platform for evaluating ADHD symptoms while delivering therapy treatment. In particular, our platform incorporates cognitive, behavioral and emotional therapeutic exercises, capable of offering significant support to children with ADHD by enhancing self-control, managing impulse and building organizational skills. These exercises are carefully selected by healthcare professionals. Clinical insights and feedback from child psychologists were integral in developing the games’ mechanics, which not only assess attention but also reinforce coping strategies and behavioral skills. This study underscores the potential of mobile gaming as a transformative tool in pediatric mental health care, paving the way for future research and application in this critical area.
Download
Paper Nr: 36
Title:

Comparing Large Language Models for Automated Subject Line Generation in e-Mental Health: A Performance Study
Authors:

Philipp Steigerwald and Jens Albrecht
Abstract: Large Language Models (LLMs) have the potential to enhance e-mental health and psychosocial e-mail coun-selling by automating tasks such as generating concise and relevant subject lines for client communications. However, concerns regarding accuracy, reliability, data privacy and resource efficiency persist. This study investigates the performance of several LLMs in generating subject lines for e-mail threads, yielding a total of 253 generated subjects. Each subject line was assessed by six raters, including five counselling professionals and one AI system, using a three-category quality scale (Good, Fair, Poor). The results show that LLMs can generally produce concise subject lines considered helpful by experts. While GPT-4o and GPT-3.5 Turbo outperformed other models, their use is restricted in mental health settings due to data protection concerns, making the evaluation of open-source models crucial. Among open-source models, SauerkrautLM LLama 3 70b (4-bit) and SauerkrautLM Mixtral 8x7b (both 8-bit and 4-bit versions) delivered promising results with potential for further development. In contrast, models with lower parameter counts produced predominantly poor outputs.
Download
Paper Nr: 39
Title:

iSupport-Portugal: Challenges and Insights in Designing a Web Platform for Intervention and Research on Informal Dementia Caregivers
Authors:

Soraia Teles, Constança Paúl, João Viana, Alberto Freitas, Sara Alves, Óscar Ribeiro and Ana Ferreira
Abstract: eHealth programmes are increasingly explored to improve access to training and support for informal caregivers of people with dementia (PwD). iSupport-Portugal is an eHealth programme for these caregivers, culturally adapted from the World Health Organization's original iSupport. iSupport-Portugal is the only version being explored internationally as a remote measurement tool (RMT) to collect sociodemographic, health and psychosocial data on care dyads. The aim of this paper is to discuss the challenges and lessons learned in the deployment of iSupport-Portugal. Four studies were conducted, including a mixed-methods cross-sectional study of informal dementia caregivers' attitudes and needs towards eHealth interventions (N=157), a usability study (N=17), a pilot randomised controlled trial (N=42), and an ongoing prospective cohort study (N=173). Insights and recommendations are provided on user uptake of eHealth interventions and user-centred approaches, ethics and data privacy considerations, study design for usability and effectiveness evaluation, and the use of platform data for research. This paper provides insights relevant to researchers, developers, and designers involved in implementing digital solutions for caregivers of PwD and other audiences. To realise the full potential of eHealth interventions and RMTs, it is imperative to establish guidelines that address the ethical, technological, and methodological complexities of the field.
Download
Paper Nr: 48
Title:

Emotional Dynamics in Semi-Clinical Settings: Speech Emotion Recognition in Depression-Related Interviews
Authors:

Bakir Hadžić, Julia Ohse, Mohamad Eyad Alkostantini, Nicolina Peperkorn, Akihiro Yorita, Thomas Weber, Naoyuki Kubota, Youssef Shiban and Matthias Rätsch
Abstract: The goal of this study was to utilize a state-of-the-art Speech Emotion Recognition (SER) model to explore the dynamics of basic emotions in semi-structured clinical interviews about depression. Segments of N = 217 interviews from the general population were evaluated using the emotion2vec+ large model and compared with the results of a depressive symptom questionnaire. A direct comparison of depressed and non-depressed subgroups revealed significant differences in the frequency of happy and sad emotions, with participants with higher depression scores exhibiting more sad and less happy emotions. A multiple linear regression model including the seven most predicted emotions plus the duration of the interview as predictors explained 23.7 % of variance in depression scores, with happiness, neutrality, and interview duration emerging as significant predictors. Higher depression scores were associated with lesser happiness and neutrality, as well as a longer interview duration. The study demonstrates the potential of SER models in advancing research methodology by providing a novel, objective tool for exploring emotional dynamics in mental health assessment processes. The model’s capacity for depression screening was tested in a realistic sample from the general population, revealing the potential to supplement future screening systems with an objective emotion measurement.
Download
Short Papers
Paper Nr: 9
Title:

Traumatic Rescue Experiences and Post-Traumatic Stress Disorder in Firefighters: The Moderating Roles of Inhibitory Control and Cognitive Flexibility
Authors:

Zhong Xia and Wang Jingyi
Abstract: OBJECTIVES: This study aimed to analyze the correlation between traumatic stress exposure and PTSD symptoms in Chinese firefighters using questionnaire and test methods, and to examine the moderating effects of inhibitory control and cognitive flexibility of executive functions. METHODS: A total of 263 frontline firefighters from China participated in this study. The self-developed "20-item Firefighter Stress Trauma Exposure Experience Inventory" was employed to investigate the subjects' experiences of traumatic events related to firefighting and rescue tasks since their recruitment. The Post-Traumatic Stress Disorder Scale (PCL-5) was used to assess the presence and severity of PTSD-related symptoms. Inhibitory control and cognitive flexibility were evaluated using the Stroop test and the number manipulation test, respectively. A moderating model was constructed through path analysis. RESULTS: Linear regression analysis revealed that traumatic stress exposure significantly and positively predicted the severity of PTSD symptoms in firefighters (p < 0.05). The moderating effect of inhibitory control was significant (p < 0.05), with simple slope analysis indicating that firefighters with strong inhibitory control were less adversely affected by traumatic stress exposure. Although the moderating effect of cognitive flexibility was not significant (p > 0.05), the simple slope analysis exhibited a trend similar to that of inhibitory control. CONCLUSION: Inhibitory control and cognitive flexibility can moderate the development of PTSD in firefighters to some extent. The findings underscore the potential value of utilizing executive function and other cognitive training to enhance firefighters’ resilience to PTSD.
Paper Nr: 10
Title:

Pneumonia Detection in X-Ray Chest Images Based on Convolutional Neural Networks and Data Augmentation Methods
Authors:

Samia Dardouri
Abstract: Pneumonia, a widespread lung ailment, stands as a leading global cause of mortality, particularly affecting vulnerable demographics such as children under five, the elderly, and individuals with underlying health conditions. Accounting for a significant portion of childhood fatalities, at 18%, pneumonia remains a critical health concern. Despite advancements in imaging diagnostic methods, chest radiographs remain pivotal due to their cost-effectiveness and rapid results. The proposed model, trained on data sourced from a readily available Kaggle database, consists of two primary stages: image preprocessing and feature extraction/image classification. Utilizing a CNN model, the framework achieves remarkable performance metrics, with precision, recall, F1-score, and accuracy reaching 93%, 96%, 94%, and 96%, respectively. These results underscore the CNN model's effectiveness in pneumonia detection, showcasing superior consistency and accuracy compared to other pretrained deep learning models.
Download
Paper Nr: 15
Title:

BOVNet: Cervical Cells Classifications Using a Custom-Based Neural Network with Autoencoders
Authors:

Diogen Babuc and Darian Onchiş
Abstract: Cervical cancer is a major global health challenge being the fourth-most common type of cancer. This emphasizes the need for accurate and efficient diagnostic tools that work well for small clinical datasets. This paper introduces an approach to computer-aided cervical scanning by integrating a custom-based neural network with autoencoders. The proposed architecture, Baby-On-Vision neural network (BOVNet), is tailored to extract intricate features from cervical images, while the autoencoders mitigate noise and enhance image quality. State-of-the-art architectures and the BOVNet architecture are trained on three comprehensive data sets (496, 484, and 1050 samples) that include Pap smear scans and histopathological findings. We demonstrate the effectiveness of our approach in accurately predicting cervical cancer risk and stratifying patients into appropriate risk categories. A comparative analysis with existing screening methods indicates the superior performance of BOVNet in terms of sensitivity (between 90.9% and 98.81% for three data sets), general predictive accuracy (between 92% and 94.86%), and time efficiency in identifying the increased risk of cervical abnormalities.
Download
Paper Nr: 20
Title:

Deep Learning Characterization of Volatile Organic Compounds with Spectrometer-on-Card
Authors:

Ander Cejudo, Markel Arrojo, Miriam Gutiérrez, Karen López-Linares, Hossam Haick, Iván Macía and Cristina Martín
Abstract: The exposome encompasses all environmental exposures that affect internal biological processes throughout a person’s life, influencing health outcomes. Among these exposures, volatile organic compounds (VOCs) are particularly significant, as they are closely related to respiratory issues, cardiovascular diseases, cancer, and other health conditions. Detecting some of them is therefore critical for assessing environmental impacts on health. In this study, we use a low-cost, highly portable SPectrometer-On-Card (SPOC) device designed to characterize complex mixtures by separating VOCs through its layers. The device was previously tested to detect VOCs in controlled laboratory conditions. Hereby, we explore artificial intelligence algorithms to identify patterns in the signals captured by the SPOC in closer to real-word conditions. Specifically, we focus on two different use cases including direct exposure to a VOC source and indoors versus outdoors signal recognition. Our top-performing model, a recurrent neural network, achieves accuracies of 92,4% and 97,2% for each use case, respectively, effectively identifying exposures in the first case and correctly classifying 87,5% of exposures in the second. These results demonstrate the potential of our methodology applied to SPOC data for broader health-related applications, such as detecting incomplete combustions, identifying diseases like cancer through exhaled breath, and detecting leaks from industrial plants.
Download
Paper Nr: 26
Title:

Unveiling Insights from Hematobiometry Data: A Data Science Approach Using Data from a Quito Clinical Laboratory
Authors:

Miguel Ortiz, Paúl Campaña, Jhonny Pincay and Dora Rosero
Abstract: In this applied research study, a data science approach is employed to analyze anonymized hematological data obtained from a clinical laboratory located in Quito, Ecuador. The analysis aims to examine machine learning models that could potentially be used to aid in early anemia and polycythemia detection, ultimately contributing to improved healthcare decision-making. A rigorous MLOps-driven methodology is employed, and well-established techniques such as clustering, decision trees, and neural networks are applied. These methods are evaluated to identify the most suitable approach for the specific characteristics of the data. The findings showed that clustering methods were not advisable for the type of data used for the exploration and no significative results could be obtained. However, decision trees and neural networks demonstrated superior performance in predicting the presence of these blood disorders. Additionally, the outcomes of this research have the potential to be particularly significant for Ecuador, a nation facing challenges in healthcare access and malnutrition, where early anemia detection could be highly impactful.
Download
Paper Nr: 31
Title:

Detecting Suicidal Ideation on Social Media Using Large Language Models with Zero-Shot Prompting
Authors:

Golnaz Nikmehr, Aritz Bilbao-Jayo, Aron Henriksson and Aitor Almeida
Abstract: Detecting suicidal ideation in social media posts using Natural Language Processing (NLP) and Machine Learning has become an essential approach for early intervention and providing support to at-risk individuals. The role of data is critical in this process, as the accuracy of NLP models largely depends on the quality and quantity of labeled data available for training. Traditional methods, such as keyword-based approaches and models reliant on manually annotated datasets, face limitations due to the complex and time-consuming nature of data labeling. This shortage of high-quality labeled data creates a significant bottleneck, limiting model fine-tuning. With the recent emergence of Large Language Models (LLMs) in various NLP applications, we utilize their strengths to classify posts expressing suicidal ideation. Specifically, we apply zero-shot prompting with LLMs, enabling effective classification even in data-scarce environments without needing extensive fine-tuning, thus reducing the dependence on large annotated datasets. Our findings suggest that zero-shot LLMs can match or exceed the performance of traditional approaches like fine-tuned RoBERTa in identifying suicidal ideation. Although no single LLM outperforms consistently across all tasks, their adaptability and effectiveness underscore their potential to detect suicidal thoughts without requiring manually labeled data.
Download
Paper Nr: 32
Title:

FlexiDialogue: Integrating Dialogue Trees for Mental Health with Large Language Models
Authors:

João Fernandes, Ana Antunes, Joana Campos, João Dias and Pedro A. Santos
Abstract: The increasing prevalence of mental health issues among university students is exacerbated by limited access to support due to shortages of mental health professionals and the stigma associated with seeking help. Virtual mental health assistants can extend the reach of existing resources, but traditional systems reliant on scripted dialogues are constrained by inflexibility and limited adaptability to diverse user inputs. This paper introduces FlexiDialogue, a system that transforms rigid dialogue trees into instruction sets for large language models, facilitating dynamic, contextually appropriate, and multilingual interactions while maintaining the structure and quality of expert-validated dialogue flows. The system was evaluated in three phases: (1) determining how effectively large language models could map open-ended user responses to predefined dialogue tree options, allowing for more natural interaction without compromising control; (2) assessing the models’ ability to paraphrase scripted dialogues to improve conversational fluidity while remaining grounded in the original tree; and (3) conducting an expert review to assess overall performance. Results demonstrated that FlexiDialogue enhanced the flexibility and coherence of interactions, with expert evaluations confirming its potential for mental health support.
Download
Paper Nr: 35
Title:

Promoting Healthy Development in Early Childhood: A Proposal of a Mobile Application
Authors:

Joana Tavares, Rita Santos and Oksana Tymoshchuk
Abstract: Developing digital solutions to support parents of children in early childhood is crucial for enhancing parenting practices and promoting child development. In the context of an intervention project that advocates the child's emotional, social, cognitive and cultural development and stable growth from prenatal life until the first three years of life, a multidisciplinary team collaborated to propose a mobile application supporting parents in promoting their children's healthy development during this period. The study followed a development research methodology, including a literature review, comparative analysis of existing apps, prototype development, and evaluation. This approach, combined with user-centred design, helped to identify critical features and design principles for an effective parental support app. The resulting app proposal foresees personalized resources, from different categories, a digital diary, suggestions of activities to be carried out with the child and recommendations of events. Evaluation results showed that an app based on this proposal can be an important resource for parents and foster positive parenting behaviours, benefiting parents and children. This research contributes to the growing field of digital health solutions for early childhood development, presenting a promising tool to enhance parental support and child well-being.
Download
Paper Nr: 44
Title:

Open Complex Systems Approach Utilizing ICT to Address Immune-Related Diseases in Aging Society
Authors:

Tatsuya Kawaoka, Ryota Sakayama, Kousaku Ohta and Masatoshi Funabashi
Abstract: Immune-related diseases, such as allergies, asthma, and dementia, are rising globally, driven by aging populations and declining ecosystem functions. Traditional elementary reductionist approaches struggle to address the complex pathologies underlying these diseases. This study explores a personalized, ecosystem-based approach to mitigating immune dysregulation using a supportive ICT platform. We developed a data-driven analytical system that identifies individual metabolic challenges through the measurement of multiple biomarkers and clinical interviews, categorizing them into metabolic traits such as inflammatory, stress-related, and glucotoxic factors. Based on these assessments, professional staff provided tailored lifestyle advice and rehabilitation interventions, including light exercises in high biodiversity environments. The results showed significant improvements in cognitive and immune functions: Participants exhibited a 3.5-point average increase in MoCA scores over three months, including functional recovery from Parkinson’s disease and CVA. Furthermore, the study identified phytochemical-rich foods, such as coarse green tea, as significant factors enhancing rehabilitation outcomes. These findings emphasize the importance of synergy between ecological environments and public health initiatives, aligning with the Planetary Health framework. By integrating multivariate analysis, personalized interventions, and ecosystem considerations through an integrative ICT platform, this approach offers a scalable solution to addressing immune-related diseases and reducing social security costs, with implications for global healthcare and environmental policies.
Download
Paper Nr: 50
Title:

Multimodal Pain Assessment Based on Physiological Biosignals: The Impact of Demographic Factors on Perception and Sensitivity
Authors:

Elisavet Pavlidou and Manolis Tsiknakis
Abstract: Pain is a multidimensional and highly personalized sensation that affects individuals’ physical and emotional state. Visual analog scales, numeric rate indicators, and various questionnaires, all relying on patient-reported outcome measurements, are considered the “gold” standard methods for assessing the severity of pain. Nevertheless, self-report tools require cognitive, linguistic, and social abilities, which may manifest variations in certain populations such as neonates, individuals with intellectual disabilities, and those affected by dementia. The purpose of this study is to automate the process through multimodal physiological-data-driven machine-learning models in order to gain deeper insights into pain sensation. We developed a pipeline using electrocardiogram (ECG), galvanic skin response (GSR), and electromyogram (EMG), along with demographic information from the BioVid dataset. The Pan & Tompkins algorithm was applied for ECG signal processing, while statistical analysis was used for feature extraction across all signals. Our study achieved 82.83% accuracy in the SVM classification task of baseline (BL) vs the highest level of pain (PA4) for females aged 20-35.
Download
Paper Nr: 54
Title:

Design of a Digital Solution to Motivate Older Adults to Follow Cognitive and Physical Training for an Active and Healthy Ageing
Authors:

Valentina Guadagno, Ana Isabel Martins, Christina Schneegass, Tilman Dingler, Joana Pais, Nelson P. Rocha and Jos Kraal
Abstract: Active and healthy ageing depends on maintaining physical and cognitive activity, but it is still challenging to motivate older adults to participate in regular training. This paper describes the iterative design and evaluation of a digital platform for increasing older adults' motivation to perform physical and cognitive exercises. The digital solution was designed and evaluated in four iterations with a total of 13 older adults. The first stage focused on identifying effective communication methods, including different formats of instructional delivery and feedback, as well as tone. The second stage explored the combination of physical activity with cognitively stimulating activities, such as brain games, sport, and hobbies, to find the most motivating combinations. The final stage developed the prototype further by integrating motivational elements into one coherent design, emphasizing clarity, guidance, and user agency. The final evaluation reviewed the overall design, including the importance of adaptive systems that dynamically adjust the difficulty level to align with users' physical and cognitive abilities to increase motivation. This study contributes to the growing field of participatory design within digital health interventions, aligning with best practices that emphasize the need for dynamic user involvement in all stages of development.
Download
Paper Nr: 57
Title:

Recommendations of Embodied Conversational Agents to Healthcare Applications
Authors:

Julio Oliveira, Telmo Silva, Rita Oliveira and Elizabeth Furtado
Abstract: This paper identifies recommendations for Embodied Conversational Agents (ECA) in Healthcare applications. The methodology employed consists of two systematic literature reviews in the fields of conversational systems and health care. Twenty-six recommendations for ECA were categorized into four groups: CS Interface, ECA Functionalities, Agent Behavior, ECA Customization Features, and Older Adults Engagement. Additionally, six Healthcare dimensions were identified: Interactive Learning, Disease-Specific Knowledge, Reinforcement, Emergency Detection, and Empathy/Rapport. These two sets of findings were combined for evaluation by a group of experts. The impact evaluation revealed six essential, two necessary, and eighteen desirable recommendations. The essential recommendations, derived from empirical methods, include the following: storing encrypted information, providing secure and accurate information to patients, facilitating interactive learning, allowing users to choose whether to enable proactive mode and ensuring ease of installation and use. The set of recommendations is an important contribution for ECA developers as this research presents.
Download
Paper Nr: 27
Title:

StreamTag: A Platform for Flexible Tagged Data Management
Authors:

David Díaz-Jiménez, Francisco Mata-Mata, José L. López, Luis G. Pérez-Cordón, José-María Serrano, Carmen Martínez-Cruz, Juana M. Morcillo-Martínez, Ángeles Verdejo-Espinosa, Juan C. Cuevas-Martínez, Raquel Viciana-Abad, Pedro J. Reche-López, José M. Pérez-Lorenzo, Juan F. Gaitán-Guerrero and Macarena Espinilla
Abstract: This paper presents StreamTag, a platform designed for the efficient management of labeled data in healthcare environments, particularly for activity recognition systems in residential and nursing home settings. Human Activity Recognition (HAR) is crucial for monitoring patient behaviors and supporting personalized care, and this field has evolved significantly with advances in IoT and AI. StreamTag integrates a flexible data labeling structure and a modular architecture, enabling data collection, labeling, and secure management of activity data. The system leverages non-relational databases for scalable data handling, along with secure protocols to ensure data integrity and privacy. This work examines existing approaches in HAR, including data-driven, knowledge-based, and hybrid models, and situates StreamTag as a versatile solution that combines flexible user-controlled labeling with high adaptability for diverse healthcare contexts. Future directions are suggested for enhancing system functionality and integration with more advanced analytical tools.
Download
Paper Nr: 29
Title:

N2ICT-CIO: Clinical Informatics Outlet via Neural Networks for Inclusive, Contextual, and Tractable eHealth
Authors:

Sheldon Liang and Henry Whitlow
Abstract: Studies on Ageing Well and eHealth aim to improve health-related quality for well being life in AWE that applies Information & Communication Technologies to Clinical Informatics as Outlets to help people stay healthier, and more independent and active at work or in their community. The Clinical Informatics Outlet has emerged from information-driven technologies in which the neural network plays a key role in applied artificial intelligence and machine learning (AIM) for the effective use of information and data technology in healthcare to improve patient outcomes, streamline clinical workflows, and enhance the delivery of care. This paper presents N2ICT-CIO acting as a clinical informatics outlet (platform) that aims for the use of digital technologies and electronic communication tools to support and improve healthcare services with inclusivity, contextuality and tractability. Where the ICT can be redefined from a service perspective via AIM and Neural Networks characterized through inclusivity via inclusive design for equitable services that are accessible, usable, and enjoyable; contextuality for charming user experience in a contextual, individual and assemblable approach to help other people consider something in its context; and tractability is to propel handlings of situations with ease. The novel CIO (N2ICT-CIO) represents a revolutionary step forward in healthcare delivery, leveraging advanced technologies. Designed to address inefficiencies, improve patient portfolio, and enhance security and collaboration across healthcare systems, it can be built as a cohesive platform able & capable to integrate these technologies around core pillars: neural networks, universal interactivity, resilient enhancement, and self-adaptive automation (Magic G.I.F.T). As a result, N2ICT-CIO, based on the previous inventive work of wiseCIO, prioritizes generative criteria for equity of eHealth service regardless of their abilities, such as age, background, or circumstances, contextualizes dynamical portfolio optimization to user-centered experience, and most important, synergizes CARE (for content management & delivery), DATA (for OLAP), and UnIX (universal interface & experience) as a whole to promote cloud-based orchestrated Anything-as-a-Service (XaaS) with Magic G.I.F.T characterized via dynamically Grouping, Indexing, Folding & Targeting for eHealth services available at the user’s fingertips.
Download
Paper Nr: 51
Title:

Towards Dependable, Interoperable and Evolvable Personal Health Data Spaces Within the European Health Data Space
Authors:

Gunnar Piho, Igor Bossenko, Marten Kask, Peeter Ross and Toomas Klementi
Abstract: This paper examines the challenges and preliminary findings in developing a dependable, interoperable, and evolvable PHDS within the EHDS. The proposed architecture consolidates personal health data, including laboratory results, medical history, imaging, omic data, patient-reported outcomes, and wearable device data into an integrated master copy under individual control. It ensures seamless interoperability for primary use cases such as diagnosis and treatment and de-identified secondary uses such as research and AI, adhering to strict consent requirements. Dependability ensures data integrity, interoperability enables smooth data exchange, and evolvability allows adaptation to regulatory and technological changes. This framework enhances health data management, supports sustainable healthcare, and addresses key issues in ownership, security, and usability.
Download

Area 3 - Telemedicine and Independent Living

Full Papers
Paper Nr: 17
Title:

How Many Times Do I Need to Say, ‘It Is Me’? Investigating Two-Factor Authentication with Older Adults in Norway
Authors:

Way Kit Bong and Yuan Jing Li
Abstract: We will have fewer healthcare personnel per older adult in the future. The use of assistive technology has been introduced to change the ways in which elderly care function, considering a more sustainable caregiving system. However, with the growing threats in cybersecurity, assistive technologies must be implemented with strong protective measures to ensure the privacy and safety of the elderly population. Two-factor authentication (2FA) has been implemented in most technologies used today, but not in assistive technologies. Research has also shown that 2FA methods can sometimes be user-unfriendly. Hence, in this study, we aim to explore the user experiences and attitudes of older adults in Norway towards performing 2FA, hoping that our findings can inform the implementation of assistive technologies. Through user testing and interviews with eight older adults, we found that 2FA methods using the physical bank code device and SMS verification were preferred. The perception of user-friendliness varied; Some prioritized ease in performing 2FA, while others valued familiarity, focusing more on avoiding mistakes. Based on our findings, we intend to implement the proposed 2FA methods into commonly used assistive technologies within the Norwegian caregiving system and evaluate these methods with a larger sample of older adults.
Download
Paper Nr: 49
Title:

Redesign and New Evaluation of a Pervasive Game for Older Adults
Authors:

Alberto Urquía, Jesús Gallardo, Raquel Lacuesta, Joan-Josep Ordóñez-Bonet and Silvia Ramis-Guarinos
Abstract: Older adults are a growing segment of the population. Many aspects of technology could help this sector improve different facets of their daily lives. One such aspect is video games, something with which older adults are becoming increasingly familiar. Within video games, a field that has grown a lot in recent years is that of pervasive games, those that break some of the classic spatial, temporal or social limits that classic video games have. Following this trend, we developed a pervasive mobile game designed for older adults inspired by Pokémon Go that consisted of players having to move through a physical space to locate real objects that would allow them to unlock memories that were stored in an album. The game had a lot of room for improvement in terms of its visual aspect, and to improve it a redesign and evaluation has been carried out, resulting in a new interface for the application, along with a series of modifications to the game mechanics and introduction of additional ones that allow branching the game experience towards different profiles and needs. In addition, the problems related to its accessibility and usability have been addressed through a series of considerations that can be extrapolated to the design of applications for older adults.
Download
Paper Nr: 60
Title:

Digital Touchpoints: Generating Synthetic Data for Elderly Smartphone Interactions
Authors:

Bilal Maqbool and Sebastian Herold
Abstract: Context: Ensuring smartphone interfaces are usable and accessible is essential for elderly users, particularly those with motor impairments, who face challenges with touchscreen interactions. Problem: Hand tremors and limited motor control can hinder touchscreen accuracy and efficiency. Meanwhile, recruiting elderly participants for usability studies can be challenging, often resulting in limited interaction data. Objectives: This study aimed to investigate elderly users’ smartphone interaction patterns, identify key challenges, and generate synthetic data to address data scarcity for usability research. Method: A custom-designed mobile app collected interaction data from 51 elderly participants performing tapping, dragging, and tracing tasks. Hand steadiness was assessed using accelerometer data. Gaussian Process Regression (GPR) and Long Short-Term Memory (LSTM) models were used to generate synthetic datasets replicating user interaction patterns. Results: Users with shaky hands struggled with precision tasks, especially involving smaller GUI elements, while larger elements improved performance. Continuous control was also found to be challenging in tracing tasks. Synthetic datasets successfully replicated spatial, temporal, and distributional metrics, demonstrating potential utility in future usability evaluation research. Conclusions: Inclusive GUI designs and adaptive features can improve accessibility for the elderly with limited motor control. Synthetic data can offer a potential solution for further usability evaluation research in building AI-driven design evaluation tools, reducing reliance on resource-intensive participant recruitment in earlier prototypes. Future work should examine diverse tasks and scenarios and involve people with severe motor impairments.
Download
Paper Nr: 62
Title:

Social Media as a Tool for Promoting Inclusion: An Analysis of the Facebook and Instagram Pages of Inclusive Spaces
Authors:

Francisca Rocha Lourenço, Rita Oliveira and Oksana Tymoshchuk
Abstract: This study explores the use of social media platforms, specifically Facebook and Instagram, by Inclusive Spaces (IS) to promote social and digital inclusion. Through a mixed-methods approach, combining quantitative analysis of engagement metrics and qualitative content analysis, the research examines how IS use different types and formats of content to engage audiences and disseminate inclusive practices. The results reveal that visual content, especially images, dominates posts on both platforms, with solidarity and record-orientated content generating the highest engagement averages per post. Instagram stands out as the platform with higher overall interaction rates compared to Facebook, despite a lower presence among ISs. The study identifies a strong emotional and relational appeal in solidarity content, highlighting its effectiveness in fostering public engagement. In addition, differences in platform functionality influence content strategies, with Instagram favouring collaborative and visually dynamic posts. The results emphasise the potential of social media as a tool for increasing the visibility of SI initiatives and strengthening community involvement in inclusive causes.
Download
Short Papers
Paper Nr: 28
Title:

Perceptions and Acceptability of Sensor-Based Activity Recognition Systems Among Older Adults and Their Families
Authors:

David Díaz-Jiménez, José L. López, Francisco J. Flores-Avilés and Macarena Espinilla
Abstract: This paper examines activity recognition systems that use sensor devices with specific activity models. It presents a new system that combines motion, open/close, and ambient sensors with wristband devices and location beacons. Alongside a detailed review of the system, the study also explores the views of two main groups of users: older adults and their family members. Although related studies exist, this research introduces the system and thoroughly analyzes user feedback. An important aspect is the acknowledgment of improvements in sensor-based smart devices, especially in terms of size and subtlety compared to earlier bracelet designs. This study included 40 anonymous participants who tested these system and key factors analyzed include acceptability, safety, peace of mind, privacy, quality of life, autonomy, trust, perceived social support, loneliness, and economic cost. This assessment offers useful insights into how users perceive and accept the system, to understand the main concerns with commonly used devices like cameras and sensors helps identify which devices older adults might be open to using in their routines. These insights are expected to guide the development of future systems that better address user needs.
Download
Paper Nr: 45
Title:

Unified Parkinson’s Disease Rating Scale Rest Tremor Score Estimation Using the Fundamental Frequency
Authors:

Beatriz Lopo Ferreira, Virginie Felizardo, Nuno Cruz Garcia, Mehran Pourvahab, Henriques Zacarias, Leonice Pereira and Nuno M. Garcia
Abstract: Parkinson’s disease (PD) is a chronic, progressive and neurodegenerative disease that affects more than 10 million people worldwide. One of the cardinal symptoms of this disease is tremor, which is characterized as an involuntary, oscillatory movement of a body part. The tremor associated with PD can be divided into rest tremor, postural tremor, and kinetic tremor and is characterized as a regular and asymmetric tremor. Emerging methods involve the use of data from inertial sensors to measure, analyze and quantify tremor and other symptoms of PD. In this publication, a method for the monitoring of rest tremor scores is explored. This method is based on the number of windows in a signal with a fundamental frequency within the rest tremor frequency band and has potential to be applied as a support for monitoring this symptom. This method had a 87.88% success rate for predicting rest tremor scores on the X axis of a 4 hour accelerometer signal, establishing promising results that will be further explored in future work.
Download
Paper Nr: 61
Title:

Mobile Application for Optimizing Exercise Posture Through Machine Learning and Computer Vision in Gyms
Authors:

Kendall Contreras-Salazar, Paulo Costa-Mondragon and Willy Ugarte
Abstract: This paper introduces a mobile application that aims to improve exercise posture analysis in gym environments using machine learning and computer vision. The solution processes user-uploaded videos to detect posture errors, utilizing Long Short-Term Memory (LSTM) networks and MediaPipe for precise pose estimation. The trained model achieved high accuracy in classifying exercise postures, demonstrating reliable performance across different user scenarios. Traditional posture correction methods, such as personal trainers and wearable devices, often lack accessibility and precision. In contrast, our application offers a scalable, user-friendly tool that delivers actionable feedback, helping users optimize their workouts and reduce injury risks. The study highlights the potential of combining machine learning with mobile technology to enhance exercise safety and performance, setting a foundation for future improvements.
Download
Paper Nr: 68
Title:

A Streamlined Lesion Segmentation Method Using Deep Learning and Image Processing for a Further Melanoma Diagnosis
Authors:

Jinen Daghrir, Wafa Mbarki, Lotfi Tlig, Moez Bouchouicha, Noureddine Litaiem, Faten Zeglaoui and Mounir Sayadi
Abstract: Over the past two decades, the world has known a significant number of deaths from cancer. More specifically, melanoma which is considered as the deadliest form of skin cancer causes a remarkable percentage of all cancer deaths. Therefore, the health and disease management community has exceedingly invested in creating automated systems to help doctors better analyze such diseases. Correspondingly, we were interested in creating an automatic lesion detection task for further melanoma diagnosis. The lesion segmentation is considered to be a critical step in a pattern recognition system. Our proposed segmentation technique consists of finding lesions’ masks using a baseline, edge-based, and more sophisticated and state-of-the-art method: thresholding using Otsu’s technique, morphological snakes, and a fully CNN (Convolutional Neural Network) model based on the U-net architecture, respectively. These methods are commonly used when dealing with skin lesion segmentation, and each one of them has its advantages and drawbacks. The U-net architecture is improved by the use of the pre-trained encoder ResNet-50 on the ImageNet dataset. A majority voting is applied to generate the final segmentation map using these three methods. The experiments were conducted using a benchmark dataset and showed promising results compared to using these methods separately, the majority voting of the three methods can significantly improve the segmentation task by refining the borders of the masks issued by the Deep learning model.
Download
Paper Nr: 19
Title:

Early Detection of Chronic Stress Using Wearable Devices: A Machine Learning Approach with the WESAD Database
Authors:

Amaia Calvo, Julen Martin and Cristina Martin
Abstract: Stress disorders have experienced a significant increase in recent years, impacting individual health. This study explores the feasibility of detecting this mental condition through the analysis of physiological signals captured by wearable devices using machine learning algorithms. An exhaustive review of relevant public databases was conducted and WESAD database was identified as the most suitable one. A detailed examination was conducted using two different configurations for building AI models: in one approach, a single model was created using data from all participants, while in the other, personalized models were developed for each individual participant. This approach evaluated the effectiveness of different preprocessing methods and AI algorithms, as well as identified the physiological signals most informative about stress. Convolutional Neural Networks (CNN) achieved the highest accuracy in stress detection, with an overall accuracy of 99.8% for the single model configuration and 99.6% for personalized models. The analysis also highlighted electrocardiogram (ECG) and electrodermal activity (EDA) as the most informative signals for predicting stress.
Download
Paper Nr: 22
Title:

LogYourEatingHabits: A Dietary App Focusing on Eating Habits that Promotes Healthy Lifestyles
Authors:

Mohammad Safiul Alam Toaha and Way Kiat Bong
Abstract: Maintaining healthy eating habits is essential for the overall health and well-being across all ages. While mobile dietary applications offer assistance, their complexity of meal logging and often poor design limit widespread adoption. This study presents the development of a mobile application, named LogYourEatingHabits, which is designed to simplify meal logging and emphasize both meal content and eating patterns. Emphasis was also placed on ensuring high usability and accessibility in the application, making it usable by as many user groups as possible. Using a user-centered design approach, the application was iteratively developed and improved throughout feedback from 16 participants over five iterations. Each iteration provided new insights, leading to enhancements such as more consistent design and interaction of user interfaces, and increased intuitiveness and user-friendliness. The System Usability Scale (SUS) scores showed improvements across iterations, and together with observation and interview findings, they indicated overall high perceived usability. Future works include expanding the food database, optimizing the image recognition feature and providing personalized feedback based on data gathered within the app.
Download
Paper Nr: 43
Title:

Assessing Human Activity in Elderly People's Homes Using the Dempster-Shafer Theory
Authors:

Sanamjeet Singh Meyer, Sebastian Wilhelm and Florian Wahl
Abstract: An increase in the elderly population, particularly those living alone, coupled with caregiver shortages, has propelled advancements in Ambient Assisted Living. A recent trend in indirect monitoring methods utilizes smart meters and Non-Intrusive Load Monitoring to track the daily activities of the elderly. By analyzing smart meter data, these algorithms can pinpoint device-specific power usage, which serves as direct indicators of daily routines and well-being. Numerous studies have employed these methods to evaluate human activity and detect anomalies in daily behaviors.
Download