Community Research and Development Information Service - CORDIS


PAL Report Summary

Project ID: 643783
Funded under: H2020-EU.3.1.

Periodic Reporting for period 2 - PAL (Personal Assistant for healthy Lifestyle (PAL))

Reporting period: 2016-03-01 to 2017-08-31

Summary of the context and overall objectives of the project

The growing burden of chronic illness on health and health care has globally led to health policy responses increasingly referring to self-management. This applies to the increasing number of children and adolescents in Europe with a chronic illness. For example, the incidence of childhood type 1 diabetes mellitus (T1DM) is rising rapidly, with a doubling time of less than 20 years. T1DM is associated with serious complications, which may appear sooner or later, cause high morbidity and mortality, affect the quality of life, and increase health-care costs. Complications can be prevented by performing self-management (e.g., monitoring blood glucose, recognising symptoms and injecting insulin). However, self-management is not an easy goal to attain for young patients, since it requires motivation and long-term perseverance, in order to become a way of life. Self-management in children and adolescents is strongly affected by a diversity of personal and environmental factors, such as the child’s developmental stage, parents’ support and health-care professionals (HCPs).
Furthermore, children need not only to learn to self-manage their lifestyle-related diseases to improve their situated health-related habits, but also to be prepared for the physical and social changes at adolescence. mHealth technology could play an important role in supporting self-management for children with a chronic condition such as T1DM.
The overall aim of the project is to develop a Personal Assistant for healthy Lifestyle (PAL), a system that will assist the child, health professional and parent to advance the self-management of children with type 1 diabetes aged 7 - 14, so that an adequate shared patient-caregiver responsibility for child’s diabetes regimen is established before adolescence. PAL will be composed of a social robot, its (mobile) avatar, and an extendable set of (mobile) health-education applications, which connect to a set of (selectable) self-management objectives, an ontological knowledge-base and reasoning mechanisms.

Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far

The overall goals for WP1 are 1 to ensure that user needs, human factors knowledge and technological opportunities are addressed well throughout the development process and 2 to develop and maintain a reusable, evidence-based, design knowledge-base on these functions and their effect on self-management.

In this second period these goals were made concrete in the different WP-specific objectives: continue to involve the end-users, refine PAL design specifications from the domain and human factors analyses
refine the requirements and claim, process the experiment and feature requests, establish important need, values and demarcations of parents and children, refine the ontology and evaluate (interim) PAL prototypes with end-users.

WP2 is responsible for the behaviour of the PAL System in relation to the learning goals of the child. In the 2nd period we 1. investigated the question if children can perceive differences in robot educational style and
2. evaluated (with children and healthcare professionals) the PAL Control tool developed last year, our health care professional authoring tool 3. we have shown in an experiment at a diabetes Autumn camp.

The overall objective of the WP3 is to personalize the behaviour of the PAL. During this second period of the project, the main focus of this period was on the development and integration of user models featuring input from sentiment and interaction mining. These new user models have been evaluated with experimental date from the Y1 experiments and are currently being integrated in the PAL system to increase its personalization according to the specificities of the users. In addition to these two lines of work, we have also created the basis for allowing the users to enrich PAL with new actions.

The objective of WP4 is to support the goals set for a patient using the PAL system by developing the means to conduct verbal communication, and to analyse textual data and extract relevant information. In the second year, we have improved our modules for multimodal generation and adapted them to new tasks, as well as adding modules that give comments or praise the child’s usage of the different facilities in the pal system to increase user motivation and adherence to the protocols.

WP5 5 activities focus on:

• The design and development of the overall Software Platform Architecture and of its main data flows;
• The definition of the interaction protocols and of the synchronization mechanism;
• The management of the integration process of the several software modules that build up the PAL IT project.

The main results achieved within WP5 in Y2 are 1. Update and optimization of the IT architecture and data flow 2. Real NAO interaction developments and updates, 3. MyPAL Apps updates.

For the timeframe of this second reporting period, the work carried out in WP6 has been focused on Stage 2, where the preliminary research findings have to be communicated and the proper communication channels and auditors categories strengthened. In fact, among the possible beneficiaries of the PAL System, the most strategic audience is confirmed to be represented by children with T1DM, their families and their in/formal caregivers: relatives, Healthcare Professionals (e.g.: the hospital staff), or assistive associations, school staff, coaches, etc. In addition to that, different networking contacts have been made with the Healthcare world thanks to the diabetes associations belonging to the Consortium and the hospitals involved.

Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far)

The PAL project aims at impact on different dimensions. Concerning child’s health outcomes, we expect a reduction in number of glucose dysregulation episodes (short-term), and a reduction of diabetes complications and extremities, and improved HbA1c (long-term). Concerning child’s competence and mental state, we expect improved knowledge, attitude and mood. For the self-management behaviour we expect improved and persistent goal-based self-management (e.g., •observing symptoms, counting carbs, pricking insulin), tailored to individual values.

Concerning the caregivers, we expect a reduction in stress and overprotection of parent and a reductions in health-care time spent for the caregivers in general.
For the AI and software domain, we expect further collaborative technology development, by creating a mHealth-app extendable architecture. For science, the project will provide and combine enhanced behaviour change models that are validated in “the wild”.

In this second period, we worked intelligent system functions that are expected to have the impact on the dimensions of above. The individual mapping of a personal objective space on educative games and the personal bonding with the pal or buddy are expected to have a large effect on most of the impact dimensions. The content of the PAL system is increasing: on one side, concerning the models, learning algorithms, (long-term evolving) self-management behaviour and child conditio and on the other side, concerning the learning material and games. Next year, the content will substantially increase and could be of value in itself.

A rich set of dissemination activities were performed; participation at international conferences, organized two child-robot interaction evaluation workshops, showed the project to SMEs, and were present during camps and world-diabetes day meetings where children, parents and caregivers came.

Related information

Follow us on: RSS Facebook Twitter YouTube Managed by the EU Publications Office Top