adaptive health care information for consumers group: csh partners

22
Adaptive Health Care Information for Consumers Group: CSH Partners

Post on 19-Dec-2015

220 views

Category:

Documents


0 download

TRANSCRIPT

Adaptive Health Care Information for

Consumers

Group: CSH Partners

Group Members• Butt, Salman

• MOT Model: Domain/Goal Maps• LAG Strategies• Researching adaptation in healthcare

• Fernando, Charith• MOT Model: Domain/Goal Maps• LAG Strategies• Researching adaptation in healthcare

• Yang, Hui• Researching Healthcare information• Domain Model

Index• Motivation for the chosen topic• Related Research• Main Findings• Adaptive Information for Consumers• Demonstration• Further Research• Conclusions• Questions• References

Motivation• Internet has provided new opportunities

for new generation of users, “the health information consumers”.

• Can bring real benefits and have a big impact on the lives of consumers

• Growing need for adaptive healthcare information.

Related Research• Adaptive user interfaces for health care

applications, IBM [5]• Techniques of Adaptive Hypermedia [6]• Providing personalized accurate healthcare

information [7]

Main Findings• Generic health information has a less

impact than health information tailored to the individual

• An increasing number of people are now using the Internet to support their healthcare.

• The amount of information available on the web continues to grow.

• Web based interventions to provide knowledge can have more impact than non web-based interventions

Health Education Goals• To Inform, to enable decision making or to

persuade • Adapt to the needs of the patients both

emotional and informational and adjust content accordingly.

• To make sure the patients follow prescribed medical plan.

• Educate patients on medications and its side effects.

What needs to be captured (User Modelling)• Medical condition and the state of the

patient • Current treatments• Patient's current mental and emotional

state• Different types of personality

How to Capture the Information• Existing patient records.• Standardized questionnaires: Personality,

Stage of change, anxiety level• Psychological sensors: Emotional state and

stress, Motivation levels.

User Modelling• State of change model - The model

assumes that people progress through very distinct stages of change on their way to improve health• Pre-contemplation - people see no problem

with their behaviour and don’t intend to change.

• Contemplation – people understand the problem and its causes and start to take action.

• Preparation – planning to take action and putting together a plan.

• Action – in process of making changes• Maintenance – health behaviour continues on

regular basis.• Termination – no problem or threat presented.

Techniques for Adaptation• Page Variant Approach – Different

versions of each page.• Versions have to be written in advance • At runtime most appropriate page will be

displayed.• Fragment-Variant approach –

Constructed by combining appropriate set of fragments. • Fragments refers to a self contained

information element eg. Text paragraph or picture

• Page Constructed by selecting and combining an appropriate set of fragments.

Techniques for Adaptation Cont...• Natural Language Generation(NLG)

• Natural Language Generation (NLG) is the natural language processing task of generating natural language from a machine representation system such as a knowledge base or a logical form.

• It involves: • Content planning; deciding what content is

most relevant to the current user.• Content Presentation; deciding how to most

effectively adapt the presentation of the selected content to the user.

Evaluation• Usability of the overall system• Evaluate whether the content presented

according to the system goals• Anxiety levels• Level of Compliance• State of Health

• Validity of the content presented• How privacy is maintained when it comes

to patient data

Evaluation Techniques• Questionnaires: Rate & Compare systems• Monitoring usage of the system (if

permitted)• Randomized evaluation

• Patients are randomly assigned and results monitored

• Cannot always draw conclusions• Costly approach• Usually used to decide benefits of various

treatments and monitor behavioral towards different systems (web vs. non-web or tailored vs. generic data)

Issues with Health Care Information• Privacy, security and trust.• Patient’s emotional state and attitude• Updating the user model

Demonstration of our system• Adaptive Healthcare Information system

adapted in two main strategies• Monitor user behaviour to identify the

medical condition of the user/patient• Enable the user to adapt the system to its

medical condition and the state.

Adaptive Behavior• Show articles on different health conditions

• Capture the user’s condition by this• Show educational articles and medication

details according to the user’s identified condition

• Let the user configure the system on medical condition and the state• Show medical condition related articles and the

educational material according to the user’s preferences

• Show medications according to the state of the health condition

Conclusions• We learned that

• There is a growing interest in health care applications

• The system not only educate patients but also assists health professionals

• Promotes better communication between both health professionals and between patients and their health care team

• Provides diagnostic tools and assists in health care provision

Further Research• How to capture patients emotional states• Measuring anxiety levels• Detecting the current mental state of the

patient• Better communication between patients

and health care professionals

Questions & Comments

References1) Buchanan, B., Carenini, G., Mittal, V., Moore, J.: Designing computer-based

frameworks that facilitate doctor-patient collaboration. Artificial Intelligence in Medicine 12 (1995) 171–193

2) Gena, C., Weibelzahl, S.: Usability engineering for the adaptive web. In Brusilovsky, P.,Kobsa, A., Niejdl, W., eds.: The Adaptive Web: Methods and Strategies of Web Personalization. Volume 4321 of Lecture Notes in Computer Science. Springer-Verlag, Berlin Heidelberg New York (2007)

3) Grol, R.: Personal paper: Beliefs and evidence in changing clinical practice. British Medical Journal 315 (1997) 418–421

4) Mittal, V., Carenini, G., Moore, J.: Generating patient specific explanation in migraine. In: Proceedings of the 18th Annual Symposium on Computer Applications in Medical Care, Washington DC, McGraw-Hill Inc. (1994) 5–9

5) Krish Ramachandran, Adaptive user interfaces for health care applications, IBM, http://www.ibm.com/developerworks/web/library/wa-uihealth/ (2009)

6) Peter Brusilovsky, Methods and techniques of adaptive hypermedia, User Modeling and User Adapted Interaction, 1996, v 6, n 2-3, pp 87-129

7) Kees van Hee, Helen Schonenberg, Alexander Serebrenik, Natalia Sidorova and Jan Martijn van derWerf Adaptive Workflows for Healthcare Information Systems BPM 2007 Workshops, LNCS 4928, pp. 359–370

References8) Cawsey, A., Jones, R., Pearson, J.: The evaluation of a personalised health

information system for patients with cancer. User Modeling and User-Adapted Interaction 10(1) (2001) 47–72

9) Bellazzi, R., Montani, S., Riva, A., Stefanelli, M.: Web-based telemedicine systems for home-care: technical issues and experiences. Computer Methods and Programs in Biomedicine 64 (2001) 175–187

10)Hirst, G., DiMarco, C., Hovy, E., Parsons, K.: Authoring and generating health-education documents that are tailored to the needs of the individual patient. In Jameson, A., Paris, C., Tasso, C., eds.: Proceedings of the Sixth International Conference on User Modeling (UM’97), Sardinia, Springer Wien New York (1997) 107–119

11)McKeown, K.: The TEXT system for natural language generation: An overview. In: Proceedings of the 20th Annual Meeting of the ACL (ACL’82). (1982) 113–120

12)McKeown, K.: Discourse strategies for generating natural-language text. Artificial Intelligence 27(1) (1985) 1–42

13)Reiter, E., Dale, R.: Building applied natural-language generation systems. Journal of Natural-Language Engineering 3 (1997) 57–87

14)Reiter, E., Osman, L.: Tailored patient information: some issues and questions. In: roceedings of the ACL-1997 Workshop on From Research to Commercial Applications: Making NLP Technology Work in Practice. (1997) 29–34