Periodic Reporting for period 3 - PAL (Personal Assistant for healthy Lifestyle (PAL))
Reporting period: 2017-09-01 to 2019-02-28
The incidence of childhood type 1 diabetes mellitus (T1DM) is rising rapidly, with the number of reported cases doubling every 20 years. Insufficient adherence to the daily diabetes regime has serious outcomes at the short term (hypo or hyper) and at the long term (e.g. damaged capillaries and related organs). When children with T1DM enter puberty, diabetes management problems suddenly increase due to physical and social changes. The Personal Assistant for a healthy Lifestyle (PAL) system was developed to prevent these problems by helping children with T1DM (age range of 7 to 14) to develop the required self-management competency and responsibility that is needed during puberty. This system consists of three components. First, an Embodied Conversational Agent (i.e. a humanoid NAO robot and its avatar) assists the child as a “pal” in informative, motivational and social conversations. The robot is present at the hospital and diabetes camps, whereas its avatar is present at a mobile device at home (e.g. for maintaining child’s time-line). Second, the child and caregiver can make a personal selection of objectives that relate to specific agent-mediated educative tasks on a mobile device (e.g. tablet, touch table). Third, dashboards provide information and control options for the children, parents and caregivers, to monitor progress and set the learning and disease management objectives. In a last evaluation, care with PAL was compared with “care as usual” for child’s diabetes management. PAL proved to enhance children’s knowledge, and PAL usage time correlated positively with this knowledge. In addition, PAL proved to increase children’s self-care assessment (particularly for the younger children), and to improve their diabetes related quality of life assessment.
The PAL project took a cyclic –human-centered, iterative and incremental– development process, called Socio-Cognitive Engineering (SCE). The end-users have been involved in all design and evaluation phases to address their needs and integrate their knowledge in the PAL system. Part of expert’s tacit knowledge was made explicit in a formal (logically correct) model, i.e. an ontology, which is interpretable by the relevant human stakeholders and the PAL system. It resulted in an extendable set of self-management objectives (focusing on learning) and related task content, with a coherent and concise structure. Further, social and cognitive theories have been integrated into the PAL ontology, as a transparent and verifiable foundation of PAL’s supportive behaviors (e.g. affect, memory, agreement and explanation). PAL acts as a partner for child’s disease management by the setting of joint objectives, entering into agreements, sharing of experiences, personalized action selection, provision of feedback and explanations, and showing appropriate learning styles. For each of these partner functions, the research provided scientific and technological results that have been or will be published. For example, specific experience-sharing, explanation and learning methods were developed for which, subsequently, specific user responses and preferences were identified in evaluations. As a second example, the Predictive User Model (for knowledge-level tracing and gaze estimation) and the aspect-based Sentiment Mining Module proved to out-perform state of the art technology. The final summative evaluation of the 3rd design-test cycle compared child’s self-management with the PAL-system versus “care as usual”, for a period of twice 3 months (with children aged 7-14y, in the Netherlands and Italy). PAL proved to partially support the three human basic needs that affect the development and habituation of human behaviors in a social environment, such as disease self-management (Self-Determination Theory). First, PAL enhanced the acquisition of competencies (knowledge and skills) for diabetes self-management. Second, children liked the PAL-robot and were motivated to continue the robot-mediated tasks (“relatedness”). Third, PAL enhanced child’s subjective self-care and diabetes related quality of life assessment, which may indicate progress in autonomy development. The re-usable PAL design rationale, ontological models and Co-design for Child-Computer Companionship (C4) suite are maintained and accessible in the Socio-Cognitive Engineering Tool.
Worldwide, there has been made substantial progress in technologies that provide new opportunities for personalized support of disease self-management, such as Artificial Intelligence, Robotics, Conversational Agents, Mobile Gaming, Virtual Reality and Cloud Computing. We combined these technologies to develop a “Personal Assistant for a healthy Lifestyle” (PAL), which supports preadolescent children with their parents and health-care professionals to learn to self-manage diabetes type 1 (T1DM). Furthermore, as a best practice of advanced “blended care”, the support was integrated, used and tested in two Dutch hospitals and one Italian hospital for two times three months. The system was continuously up and running after the launch of its first version (for almost three years), accessible via Internet (e.g. from home, diabetes camps and the hospital). Three unique selling points of this PAL-system are (1) the situated goal-based personalized support of social, cognitive and affective processes in child’s self-management, (2) the provision of harmonized support for the child (as “primary” user) and the caregivers (health-care professional and parent), and (3) the continuing recording of measurements of changes in health conditions with the related circumstances, patient behaviours and intervention methods. The next valorisation step is to implement (parts of the) PAL system in the education and care processes of children with T1DM (hospital ZGV already deploys a “PAL-derivative”, called Ziggi). Three key exploitable results (KERs) have been identified: The MyPAL app suite, the Ontology models & reasoning rules, and the C4 suite (i.e. co-design tools). For the integrated PAL system, we will connect to the European Digital Innovation Hub network in Healthcare Robotics.