Search

The final chapter presents open-access educational products that supplement this book: case studies and a web application to simulate behaviour change support in persons with chronic disease. The former is of particular interest for academic educators, while the latter may interest students independently pursuing training outside the classroom. These products can also be useful for professionals aiming to enhance behaviour change competencies in practice.First, we address key aspects of product development , including hallmarks such as the incorporation of behaviour change science and transnational co-production with users. Then, the main features of case studies and the web application with 2D virtual humans are described.

This chapter describes the development of a theory-driven and evidence-based digital intervention to facilitate self-care in older adults with Type 2 Diabetes (T2D) and, additionally, its contribution to healthy aging and the individual care plan. T2D is highly prevalent in older adults. Difficulties in adopting and maintaining desirable self-care behaviors is associated with lack of glycemic control and subsequent complications, which significantly burden patients, their families, and the health system. The VASelfCare (Virtual Assistant Self-Care) intervention is a software application that provides an interface with a 3D anthropomorphic virtual assistant targeting three key self-care behaviors: medication-taking, physical activity, and a healthy diet. Other VASelfCare elements are intended for nurses providing diabetes consultations, including a web-based back-office with a patient data dashboard, which streamlines integration of care. The application prototype has been co-produced with older adults with T2D, primary care health professionals, and other stakeholders.

Submitted by ines Almaca (ce3c@fc.ul.pt) on 2022-02-04T15:12:01Z No. of bitstreams: 1 1-s2.0-S1877050921022511-main.pdf: 1278327 bytes, checksum: 93b8557dabc57c0b081007c6eed6ce1d (MD5) Approved for entry into archive by ines Almaca (ce3c@fc.ul.pt) on 2022-02-04T16:14:24Z (GMT) No. of bitstreams: 1 1-s2.0-S1877050921022511-main.pdf: 1278327 bytes, checksum: 93b8557dabc57c0b081007c6eed6ce1d (MD5) Approved for entry into archive by ines Almaca (ce3c@fc.ul.pt) on 2022-02-04T16:14:42Z (GMT) No. of bitstreams: 1 1-s2.0-S1877050921022511-main.pdf: 1278327 bytes, checksum: 93b8557dabc57c0b081007c6eed6ce1d (MD5) Made available in DSpace on 2022-02-04T16:50:42Z (GMT). No. of bitstreams: 1 1-s2.0-S1877050921022511-main.pdf: 1278327 bytes, checksum: 93b8557dabc57c0b081007c6eed6ce1d (MD5) Previous issue date: 2022-01 info:eu-repo/semantics/publishedVersion

BACKGROUND Conversational agents, which we defined as computer programs that are designed to simulate two-way human conversation by using language and are potentially supplemented with nonlanguage modalities, offer promising avenues for health interventions for different populations across the life course. There is a lack of open-access and user-friendly resources for identifying research trends and gaps and pinpointing expertise across international centers. OBJECTIVE Our aim is to provide an overview of all relevant evidence on conversational agents for health and well-being across the life course. Specifically, our objectives are to identify, categorize, and synthesize—through visual formats and a searchable database—primary studies and reviews in this research field. METHODS An evidence map was selected as the type of literature review to be conducted, as it optimally corresponded to our aim. We systematically searched 8 databases (MEDLINE; CINAHL; Web of Science; Scopus; the Cochrane, ACM, IEEE, and Joanna Briggs Institute databases; and Google Scholar). We will perform backward citation searching on all included studies. The first stage of a double-stage screening procedure, which was based on abstracts and titles only, was conducted by using predetermined eligibility criteria for primary studies and reviews. An operational screening procedure was developed for streamlined and consistent screening across the team. Double data extraction will be performed with previously piloted data collection forms. We will appraise systematic reviews by using A Measurement Tool to Assess Systematic Reviews (AMSTAR) 2. Primary studies and reviews will be assessed separately in the analysis. Data will be synthesized through descriptive statistics, bivariate statistics, and subgroup analysis (if appropriate) and through high-level maps such as scatter and bubble charts. The development of the searchable database will be informed by the research questions and data extraction forms. RESULTS As of April 2021, the literature search in the eight databases was concluded, yielding a total of 16,351 records. The first stage of screening, which was based on abstracts and titles only, resulted in the selection of 1282 records of primary studies and 151 records of reviews. These will be subjected to second-stage screening. A glossary with operational definitions for supporting the study selection and data extraction stages was drafted. The anticipated completion date is October 2021. CONCLUSIONS Our wider definition of a conversational agent and the broad scope of our evidence map will explicate trends and gaps in this field of research. Additionally, our evidence map and searchable database of studies will help researchers to avoid fragmented research efforts and wasteful redundancies. Finally, as part of the Harnessing the Power of Conversational e-Coaches for Health and Well-being Through Swiss-Portuguese Collaboration project, our work will also inform the development of an international taxonomy on conversational agents for health and well-being, thereby contributing to terminology standardization and categorization. INTERNATIONAL REGISTERED REPORT DERR1-10.2196/26680

Background Conversational agents, which we defined as computer programs that are designed to simulate two-way human conversation by using language and are potentially supplemented with nonlanguage modalities, offer promising avenues for health interventions for different populations across the life course. There is a lack of open-access and user-friendly resources for identifying research trends and gaps and pinpointing expertise across international centers. Objective Our aim is to provide an overview of all relevant evidence on conversational agents for health and well-being across the life course. Specifically, our objectives are to identify, categorize, and synthesize—through visual formats and a searchable database—primary studies and reviews in this research field. Methods An evidence map was selected as the type of literature review to be conducted, as it optimally corresponded to our aim. We systematically searched 8 databases (MEDLINE; CINAHL; Web of Science; Scopus; the Cochrane, ACM, IEEE, and Joanna Briggs Institute databases; and Google Scholar). We will perform backward citation searching on all included studies. The first stage of a double-stage screening procedure, which was based on abstracts and titles only, was conducted by using predetermined eligibility criteria for primary studies and reviews. An operational screening procedure was developed for streamlined and consistent screening across the team. Double data extraction will be performed with previously piloted data collection forms. We will appraise systematic reviews by using A Measurement Tool to Assess Systematic Reviews (AMSTAR) 2. Primary studies and reviews will be assessed separately in the analysis. Data will be synthesized through descriptive statistics, bivariate statistics, and subgroup analysis (if appropriate) and through high-level maps such as scatter and bubble charts. The development of the searchable database will be informed by the research questions and data extraction forms. Results As of April 2021, the literature search in the eight databases was concluded, yielding a total of 16,351 records. The first stage of screening, which was based on abstracts and titles only, resulted in the selection of 1282 records of primary studies and 151 records of reviews. These will be subjected to second-stage screening. A glossary with operational definitions for supporting the study selection and data extraction stages was drafted. The anticipated completion date is October 2021. Conclusions Our wider definition of a conversational agent and the broad scope of our evidence map will explicate trends and gaps in this field of research. Additionally, our evidence map and searchable database of studies will help researchers to avoid fragmented research efforts and wasteful redundancies. Finally, as part of the Harnessing the Power of Conversational e-Coaches for Health and Well-being Through Swiss-Portuguese Collaboration project, our work will also inform the development of an international taxonomy on conversational agents for health and well-being, thereby contributing to terminology standardization and categorization. International Registered Report Identifier (IRRID) DERR1-10.2196/26680

E-learning courses offer, nowadays, opportunities for everyone to study wherever they are. However, asynchronous communication between students and teachers, and the lack of social engagement, leads frequently to a sense of abandonment and, in the limit, to withdrawal, as a consequence. To avoid this phenomenon, we developed an interface prototype with an anthropomorphic 3D virtual tutor in the Moodle’s e-learning platform of Universidade Aberta (https://portal.uab.pt/). This virtual tutor helps students finding information in the page of the course, delivers speech, exhibits facial expressions and is able to answer questions about the course. This paper describes the approach used to implement this Q&A functionality. Having all the course information represented in an ontology, the idea is to transform the original question in a SPARQL query that, when executed on the defined ontology, returns the desired answer.

Background Osteoarthritis (OA) is one of the most prevalent chronic rheumatic diseases (24% in Portugal, according to the Portuguese Society of Rheumatology) accounting for significant years of disability. Optimal management of OA requires active patient participation. A recent systematic review concluded that more effective information strategies are needed to respond to the needs of OA patients.1 Interactive computational simulation with Virtual Humans (VH) has been used with the purpose of educating or promoting lifestyle change in healthy people or in the management of chronic illnesses, such as diabetes treatment, including good users’ acceptance and an increase in their knowledge.2 Knowledge acquisition is generally seen as a necessary condition for behavioral change. Applications with virtual humans offer a dynamic, interactive and easily accessible approach to enhance users’ knowledge. We did not find published literature on the use of virtual humans to educate people with OA. Objectives To develop a web application to support education of caregivers and people with OA. Methods This is a proof of concept study, which builds on our previous experience with virtual assistant applications. For example, “Virtual Pharmacy”4 is intended to improve self-medication consultation skills between students/pharmacy professionals and community pharmacy clients, whilst “VASelfCare”3 aims to facilitate self-care of older people with type 2 diabetes (REF?). The main principle underpinning the development of our application is the use of gamification embedded in a narrative with a double purpose of maintaining user engagement and enhancing the play experience. This option has in consideration that OA is more prevalent among the seniors and is supported by a study showing that embedding narratives in mobile games enhances the play experience of this age group.5 In our approach, the narrative comprises dialogues aiming to ease and stimulate the search for new knowledge, and to educate for disease management and health promotion. Results So far, we have developed NOA, a virtual assistant that interacts with users through speech (voice and subtitles) plus facial and body animations. NOA is a 2D cartoon female model that plays the role of a character who suffers from OA and provides information about her own experiences with the disease. At the end of each dialogue, a quiz tests users’ knowledge. Awarding points and digital badges for correct answers, or showing the right answers when the user fails, are expected to motivate users to play and learn more. This application will be placed in the “Portuguese League Against Rheumatic Diseases” website to convey easy access. Conclusion Development of a virtual assistant web application to promote education on OA, resorting to a narrative approach and gamification principles, is on-going. Future work includes testing the application with experts and patients. References [1] Chou, L., et al. (2018). Patients’ perceived needs of osteoarthritis health information: A systematic scoping review. PloS one, 13(4), e0195489 [2] Finkelstein, J., & Bedra, M. (2014). Avatar-based Interactive Diabetes Education in Older Adults. Journal of the American Geriatrics Society, 62(S1), S64 [3] http://vaselfcare.rd.ciencias.ulisboa.pt/ [4] Claudio, A. P., et al. (2016). Virtual Humans Playing the Role of Patients in Self-medication Consultations: Perspectives of Undergraduate Pharmacy Students. GRAPP 2016, pp 296-303 [5] Yee, S. L. C. Y., et al. (2010). Investigating narrative in mobile games for seniors. CHI 2010, pp 669-672 Disclosure of Interests None declared

Introduction: Engaging undergraduate students in faculty-led research is documented as a mutually valuable experience [1,2]. The VASelfCare project started in January 2018 (http://vaselfcare.rd.ciencias.ulisboa.pt); it aims to develop and test a software prototype with a virtual assistant, to facilitate self-care of older people with type 2 diabetes. The project entails the involvement of undergraduate nursing students at the consortium’s lead Institution (ESEL). The purpose of this paper is to describe the strategy for students’ participation and present its first results. Materials and methods: The implementation strategy was informed by prior experience of the research team and relevant literature. A call for applications was launched within ESEL, targeting 2nd to 4th year students. The call provided information about the project, the required student profile and the selection process. In this early phase, participation consisted of expanding the literature review on features of virtual assistant softwares. After an initial meeting, each student was assigned a specific task. Students worked in pairs and presented their work in two meetings with the multidisciplinary research team, scheduled over the course of roughly two months. Students’ opinion was ascertained at the end of this phase by means of an anonymous questionnaire, comprised by four open questions and five closed questions. Results: All the 12 applications were selected. There was a predominance of 3rd year students (n = 5). Of the 11 students who completed this phase, six responded to the questionnaire and consented to the use of data in publications related to the project. Participation was described in one word using terms such as “challenging” and “interesting”. Students perceived their involvement as an opportunity to contact with research and innovation, to develop competencies and to network with students with different background. Views on less positive aspects pertained mainly to the small exposure to research. Students’ expressed willingness to be involved in more phases of the project and to be informed about its results. They unanimously agreed (6/6) that participation contributed to improving their understanding of novel situations in a different scientific area and to the development of skills in scientific literature analysis. Discussion and conclusions: Thorough recruitment, assigning specific tasks, peer support and regular meetings were an effective strategy for involving students. This is in line with previous findings [2], and may be of help to researchers in other institutions and disciplines. Overall, students’ opinion on their experience were favourable. Future perspectives include awarding course credit for students’ participation, to enable more in-depth involvement without overloading their schedule and to further stimulate their interest in research.

Diabetes has significant clinical, economic and humanistic implications, both at a national and global level. Type 2 diabetes (T2D) is highly prevalent in older people. This paper describes a first prototype of an application intended to facilitate self-care of older people with T2D, supplementing appointments with healthcare professionals. The application is based on a virtual assistant with an anthropomorphic representation. The virtual assistant is capable of speaking and expressing emotions through facial and body animations; it has been designed to act as a relational agent, developing long-term relationships with users. It targets adherence to medication, physical activity and diet, tailoring the intervention to users’ needs and characteristics. The Behavior Change Wheel was chosen as the theoretical approach to behaviour change and supports dialogue content. Built for Android devices, the architecture of the application first prototype includes a core component, a dialogue creator, a speech generator and a database. The first tests on the application contents and usability were conducted in a sample of ten academic nurses with expertise in primary care. Overall, these tests yielded a positive opinion, as well as suggestions for improvement. On-going work includes testing the first prototype with older people with T2D plus health professionals in primary care units of the Portuguese National Health Service, and incorporating a rule-based context-sensitive dialogue manager, which is expected to convey a more flexible dialogue flow.