Titulo Estágio
Characterizing acceptance of Internet of Things solutions for Active and Healthy Ageing.
Local do Estágio
Life Supporting Technologies, Avenida Complutense 30, 28040, Madrid, Spain
Enquadramento
Digitalization of healthcare has the potential to alleviate the burden on national health system due to the ageing challenge. Users may abandon a technological application and solution at any time due to various reasons. This could reduce the effectiveness of the digital healthcare intervention, even increase the health problem or disease associated risks. In this context, to identify users with higher risks of getting disengaged from a solution, even predicting when could happen, is an invaluable resource, creating the opportunity to apply tailored intervention strategies aiming at recovering from disengagement. The main goal of this master thesis is to research and evidence the factors, barriers and needs of aged users’ relationships with the healthcare technologies that may contribute to the early detection of motivational, or unmet expectancies that increase disengaged risk. In particular, the goal is to research and develop models that 1) can detect early dropout patterns 2) to provide a profile-based explanation of this lack of engagement that allow to introduce tailored interventions that contribute better awareness of the benefits of the digital solutions.
Objetivo
Traditionally, the impact of health care solution is addressed from three dimensions: assessing the availability of the technological solution deployment, the quality of the solution itself to solve specific problems, and the acceptability and accessibility of the solution. From these 3 dimensions, traditionally, accessibility and acceptability are the dimension identified as main barrier for aged adults’ engagement with these solutions. Specifically, accessibility and acceptability are systematically evaluated following acceptance models and methodologies such as UTAUT, SUS and other well-known methodologies that provide a static vision of the acceptance in a specific moment. However, data mining techniques that are widely used in marketing, retail, and banking to detect users’ preferences, behaviour patterns and lack of engagement, are not used to aged adults’ technological acceptance studies. This research work will specifically address this lack of research evidence, applying techniques of data mining. The study will be supported on the ACTIVAGE Deployment Site Madrid database currently available in the UPM, that include the data of about 800 participants in the pilot, the assessment questionnaires and the usage data logs. New open database could be incorporated in the research in other to better understanding of the users’ context.
Plano de Trabalhos - Semestre 1
The detailed goals for the 1st semester are:
- Research and develop a model for detection of the early dropout patterns.
- Support better understanding of the medium- and long-term digital healthcare solutions acceptance and providing evidence of the early dropout causes.
- Develop a set of recommendations to apply intervention strategies aiming at recovering from disengagement.
Work program for the first semester:
- Acquire background information on digitalisation of healthcare and patient adherence to health technology
- Analyse the state of the art on patient dropout prediction solutions and patient adherence promotion strategies
- Analyse the state of the art in risk modelling and profile identification using data mining
- Research and develop a model that is able to identify early drop-out patterns
- Write interim documentation
Plano de Trabalhos - Semestre 2
In the second semester these activies will be carried out in the Madrid region, in the UPM settings. This way, the student will also conduct interviews and further meetings with endusers and stakeholders of the ACTIVAGE Madrid Deployment Site, with the idea of carrying out additional studies to confirm and complement the results from the model.
Work for the second semester
- Research and develop a model that is able to identify early drop-out interpretable patterns
- Research and develop a model for early drop-out risk prediction
- Assessment of the influence of individual features in medium and long-term acceptance of digital healthcare solutions
- Develop a set of recommendations to apply intervention strategies aiming at recovering from disengagement.
- Write the thesis
Condições
Access to offices, infrastructure, end-users offered by the Smart House Living Lab of the Life Supporting Technologies group
Observações
This thesis will be co-supervised by Dr. Patricia Abril from UPM and by Prof. Paulo de Carvalho and Prof. Jorge Henriques from DEI-FCTUC
Orientador
Giuseppe Fico
gfico@lst.tfo.upm.es 📩