The PAL (Personal  Assistant for healthy Lifestyle) project proposal for Horizon 2020 was “favourably evaluated”  and started on the 1st of March 2015 (EU grant is 4.5M Euro; ref. H2020-PHC-643783).  This 4 year project involves the research partners TNO (coordinator), DFKI, FCSR, Imperial and Delft University of Technology, next to end-users (the hospitals Gelderse Vallei and Meander Medical Center, and the Diabetics Associations of Netherlands and Italy), and SME’s (Mixel and Produxi).  PAL will use, refine and extend the knowledge-base and support models of ALIZ-E to improve child’s diabetes regimen by assisting the child, health professional and parent. The PAL system will be composed of a social robot (NAO), its (mobile) avatar, and an extendable set of (mobile) health applications (diabetes diary, educational quizzes, sorting games, etc.), which all connect to a common knowledge-base and reasoning mechanism.



Type 1 Diabetes Mellitus (T1DM) portraits a high need and challenge for self-management by young patients: a complex illness with a high and increasing prevalence, a regimen that needs adaptation to patient’s condition and activities, and serious risks for complications and reduced life expectations. This project  addresses this need by developing a Personal  Assistant for healthy Lifestyle (PAL) system, which supports  the children with T1DM (7-14 years of age), their families and the related medical staff. Overall, it will help the children to acquire the knowledge, skills and habits to adhere to their diabetes regimen, tailored to the child’s individual needs (health condition, developmental and behavioural change stage, abilities, gender, and social environment). The project will apply a user-centered co-design and test-process to establish consistent, long-term and personalized self-management support over various settings (i.e., in-and-outside medical settings) via mHealth applications, such as on-line diary and educational quizzes. PAL will also provide motivational support for the adoption of healthy lifestyles.


The PAL system will be composed of a social robot, its (mobile) avatar, and an extendable set of (mobile) health applications, which all connect to a common knowledge-base and reasoning mechanism. PAL is instructed and supervised by the health professionals (e.g., diabetologists, nutritionists, nurses, psychologists) who set self-management goals and tasks for the children and could monitor at the same time their developments through it. In turn, PAL helps the children to adopt the goals and perform the activities (together with their families) that will help them achieve the goals. The professionals also provide the relevant educational content for PAL to ensure high quality and alignment with the information provided during usual care.



The overall aim of the project is to develop a Personal Assistant for healthy Lifestyle (PAL), a system that will assist children with T1DM aged 7-14, health professionals and parents to advance the self-management of the disease), so that an adequate shared patient-caregiver responsibility for children’s diabetes regimen is established before adolescence. The project objectives can be summarized in the following points:

to assess user’s (child, parent, health professional) needs and determinants to support long-lasting self-management behavior of the child from childhood into early adolescence;

to develop an agent-based reasoning mechanism to set personalized  learning and behavioural goals, and engagement strategies for children;

to develop support tools for the caregivers, like an authoring & control module for the health professional and a monitor & inform module for the parents;

to develop consistent personalized multimodal natural interactions for the physical (robot) and virtual (avatar) embodied conversational agents (ECA), fostering long-term engagement in a range of educational health applications;

to further develop and integrate (mobile) health applications into an open infrastructure for comprehensive knowledge-based self-management support of children with diabetes;

to determine the costs and profits for the proposed self-management support.


Expected impact

Self-Management Behavior
The PAL system facilitates young patients and their parents to play a larger role in personal selection of behavioural goals, in their path of education and training, with the aim to increase young patients’ motivation, skills and confidence in managing their health.

Healthcare supporting tools
The PAL system, with its authoring and control tool, supports health professionals in the monitoring of young patients’ behaviours and health condition remotely, over time. Furthermore, the Authoring and Control tool provides concrete possibilities to adjust the coaching to improve its effect on young patients’ behaviour and health outcomes. In this way, PAL acts a human-in-the-loop decision support system, which facilitates patient management with additional attention to coaching and educating.

Collaborative Technology
To reap the full benefit of mHealth solutions in the future, PAL will set up a technology infrastructure, systems integration, and guidelines allowing rapid adaptation to changing technologies. This will take place through a modular mHealth-app extendable architecture and semi-automatic content acquisition from external sources, and continuous measurement of performance metrics. This will contribute to standardized knowledge-driven definitions and processes supporting a broad number of operational demands and design requirements.

Innovation Capacity
At the end of four years, based on the data collected and the experiences encountered by different users within the T1DM, we intend to obtain a versatile and really applicable set of services:

  • Training tools for children, based on edutainment models;
  • Planning tools for self-management (for caregivers and especially for the little patients) extendable also to other pediatric diseases.