 |
The Tenth International Conference on ICDS 2016 April 24 - 28, 2016 - Venice, Italy |
| Tutorials |
T1. Big data for Personalized and Persuasive Coaching via Self-monitoring Technology
Lisette van Gemert-Pijnen, University of Twente-Enschede, the Netherlands
Annemarie Braakman, University of Twente-Enschede, the Netherlands
Olga Kulyk, University of Twente-Enschede, the Netherlands
Liseth Siemons, University of Twente-Enschede, the Netherlands
Floor Sieverink, University of Twente-Enschede, the Netherlands
T2. Big Data: Processing Anatomy
Petre Dini, Concordia University, Canada | IARIA, USA
T5. Where Data Lives: Centricity with Complex Data and Advanced Computing
Claus-Peter Rückemann, Leibniz Universität Hannover / Westfälische Wilhelms-Universität Münster / North-German Supercomputing Alliance (HLRN), Germany
T4. Brain, Child, Self and Toy Robots: Enrobotment
Irini Giannopolu, Pierre Marie Curie University in Paris, France
DETAILS
T1. Big data for Personalized and Persuasive Coaching via Self-monitoring Technology
Prof. Dr. Lisette van Gemert-Pijnen, University of Twente-Enschede, the Netherlands
Prof. Dr. Annemarie Braakman, University of Twente-Enschede, the Netherlands
Prof. Dr. Olga Kulyk, University of Twente-Enschede, the Netherlands
Dr. Liseth Siemons, University of Twente-Enschede, the Netherlands
PhD Candidate Floor Sieverink, University of Twente-Enschede, the Netherlands
Big Data, often defined according to the 5V (volume, velocity, variety, veracity and value) model, is seen as the key towards personalized healthcare. However, it also confronts us with new technological and ethical challenges. What are the hopes, challenges and dangers for using big data to develop personalized and persuasive coaching systems? The aim of this tutorial is to demonstrate a vision on big data to personalize healthcare, using views and ideas from experts and tutorial participants.
The use of Big Data for analysis and decision making requires a change of thought from knowing “why” to knowing “what”. Where we would have focused on small, exact datasets and causal connections (i.e. knowing “why”) in the past; now we focus on gathering or linking a large amount of (noisy) data with which we can demonstrate the presence of (unexpected) correlational connections (i.e. knowing “what”) [1]. As a result, we will obtain (and apply) new insights that we did not have before. Insights that can not only be lifesaving, but that can also open the door towards more personalized medicine to tailor medical decisions, medications and/or products to the individual’s personal profile instead of to what is best for a group of patients. For example, the use of genetic biomarkers in pharmacogenetics can be used to determine the best medical treatment for a patient or the analysis of data from thousands of patients that have been treated in the past can be used to determine what treatment best fits the individual patient that is under treatment now, e.g. in terms of expected treatment effects and the risk for severe side-effects given the patient’s personal characteristics like age, gender, genetic features, etc.. This shift towards more personalized healthcare is reflected in the change of focus from a disease-centered approach towards a patient-centered approach, empowering patients to take an active role in the decisions about their own health. As a result, an increasing number of technologies (e.g. Personal Health Records) are being launched by (insurance) companies to support chronically ill people in the development of self-management skills. Furthermore, the past decades have shown a rapid growth in the amount of (personal) data that is digitally collected by individuals via wearable technologies and that may or may not be stored on online platforms for remote control and shared via other online sources like social media. Social media have become socially accepted and used by a growing group of people. They use it, for example, to share data collected by activity trackers or sleep apps on a variety of online platforms (such as Facebook, Twitter, blogs or forums). This data provides new opportunities for personalizing and improving healthcare. The information gleaned from social media has the potential to complement traditional survey techniques in its ability to provide more fine-grained measurement over time while radically expanding population sample sizes. Furthermore, the combination of clinical data with personal data on, for instance, eating and sleeping patterns, life style or activity level, can be used to tailor the treatment and coaching purposes to the needs of patients even better and are therefore seen as the key towards a future with optimal medical help. However, it also confronts us with new technological and ethical challenges that require more sophisticated data management tools and data analysis techniques. Concerns have been raised about security, purpose limitation, liability, safety, profiling, and data ownership, to mention just a few , but perhaps the most well-known concern bears upon our privacy . For a great deal, these privacy concerns are associated with potential misuse of data by, for instance, insurance companies . If these privacy concerns are not dealt with appropriately, the public’s trust in technological applications might diminish severely [8].
To better understand how Big Data impacts healthcare this paper aims to generate new ideas and thoughts , via the eTelemed tutorial, to build on and strengthen the use of Big Data to personalize health care.
Tutorial persuasive and personalized coaching using self-monitoring data
To gain a more in depth picture about the pros and cons of using big data in personalized healthcare, a focus group was organized with a multidisciplinary panel consisting of 6 experts in big data and quantified self-monitoring from different scientific disciplines: psychology, philosophy, computer science, business administration, law, and data science. The issues that arose from this focus group, discussed below, will be used to set the agenda for Big data-research and will be discussed more into depth using submitted ideas of the tutorial participants from eTelemed conference 2016.
The tutorial will be organized by Lisette van Gemert-Pijnen and Annemarie Braakman, Olga Kulyk, Floor Sieverink, Liseth Siemons
We work at the university of Twente, the Netherlands. Lisette van Gemert-Pijnen Coordinates the Center for EHealth Research & wellbeing and the lab Persuasive Health technology:
https://www.utwente.nl/igs/ehealth/research/persuasive-health-technology
The speakers participate in the center Persuasive Health technology
T2. Big Data: Processing Anatomy
Petre Dini, Concordia University, Canada | IARIA, USA
Summary:
- Big/small/linked/open data
- Data collection/filtering/storing
- Data retrieval/selection/interpretation
- Data domains
- Data/Support types
- Data correlation
- Data source
- Retrieval
- Data processing challenges
- Data storage
- Autonomic computing
- Detailed case study: Syslog reporting events
- Syntax, semantic, timestamps
- ALLDATA event series
T3. Where Data Lives: Centricity with Complex Data and Advanced Computing
Claus-Peter Rückemann, Leibniz Universität Hannover / Westfälische Wilhelms-Universität Münster / North-German Supercomputing Alliance (HLRN), Germany
Data and computing are interlinked in many ways. The more extravagant data becomes, the more specialised solutions are required. For example, the different types of Big Data may prefer different high end solutions. Different High Performance Computing applications prefer different data handling.
It is beneficial to take a closer look at the details of the respective relations and conditions. Centricity, as in "data-centric", "knowledge-centric", and "computing-centric", is a significant aspect for understanding, choosing, and creating advanced solutions.
This tutorial focuses on aspects of data as well as of computing.
Examples are:
- Different types of data and organisation,
- Different types of computing and storage architectures,
- Different methods,
- Different goals.
The tutorial presents and discusses real examples of advanced implementations worldwide, introduces in architectures and operation, and tries to discuss consequences and solutions.
Some focus questions are:
- What means centricity?
- Which architectures can be considered?
- Which major scenarios exist?
- From discipline/users' view, are there choices and how?
- Why is it important to think about centricity details?
- Why should users take a closer look at their data and workflows?
- Can Big Data be data-centric?
- What are the consequences of centricity?
- How to handle issues like long-term relevant data, complexity, portability, and what are benefits and tradeoffs?
It is intended to have a concluding dialogue with the participants on practical scenarios and experiences.
This tutorial is addressed to all interested users and creators of data, disciplines, geosciences, environmental sciences, archaeology, social and life sciences, as well as to users of advanced applications and providers of resources and services for High End Computing. There are no special informatics prerequisites or High End Computing experiences necessary to take part in this tutorial.
T4. Brain, Child, Self and Toy Robots: Enrobotment
Irini Giannopolu, Pierre Marie Curie University in Paris, France
Development is the result of a complex process with three foci at least, one in the central nervous system, one in the mind and one in the child’s dynamic interactions with the natural vs. artificial environment, which are toy robots. Requiring flexible, powerful, and synergistic dialogues in a coordinated manner, nonverbal/verbal cognition, emotion and consciousness, i.e., the self, develop at the interface between neural processes. Toys have a central role. Toys seem provide an interesting account of “how” physical objects (artificial or not) are able to act as support for the symbolic play of children. They refer to how children embed information to develop knowledge representations. Recent advances in toy robots and human brain development have set the stage to greatly expand collaboration between engineers and neuroscientists. Based on the internalised “object” and using cognitive, clinical, neuro-functional and engineering arguments, this tutorial will analyze the concept of “enrobotment”. Playing with objects/toys robots (including the imperceptible part, i.e., the shadow) implies that the objects/toys are part of the external environment, i.e., the “other”. The enrobotment signifies that object’s internalisation not only reflects the impact of the environment on child’s development but it also reverberates the echo of child’s representations. An intermediate object (including shadow) is conceived in mind by the child him/herself. Having a high emotional value and forming an implicit/explicit autobiographical continuum in memory, it ensures the continuity between the “self” and “other”, it authorises subjectification. The correlated representations allow the invention of ideas and concepts; motor and verbal actions including their intention prosper. Intention attribution to objects/toys constitutes a precursor of self-consciousness, as this intention, a specific anticipation, helps children to understand what it signifies to have a perspective. Recognizing what it implies to be a “self” is a parcel of envisioning mental states of “other”. At the antipode, autism can be considered as an antithesis of self-consciousness. Children with autism cannot mirror the triadic relationship of “object-self-other”.
