Agent Technology and Healthcare: Possibilities, Challenges and Examples of Application - Computational Intelligence in Healthcare: Advanced Methodologies - page 40

mistake is to focus first on the “medical” functionalities of the system and delay “add-
ing” the security aspects until the end of the project. This will hamper the reliability
of the prototype system and the introduction of security related mechanisms may
require a redesign of already working modules.
The maintenance of the healthcare system once it is deployed is also a very basic
issue that is often overlooked. This aspect is critical, since usually the personnel in the
computer science unit of the hospital do not know about agent technology, and they
can't probably handle the maintenance of the system. Intuitive system management
tools should be also developed in order to tackle this aspect.
The use of personalisation techniques and mobile devices should be enhanced, as
they clearly help to reduce the usual reluctance that healthcare practitioners (and pa-
tients) may have to introduce new technologies in their daily workflow, which on the
other hand, bring many advantages in promoting the remote access to healthcare ser-
vices and in managing Home Care processes.
From the agent community point of view, it would be very interesting to promote
the reusability of different parts of these agent-based healthcare systems, so that re-
searchers do not have to start from scratch every time they engage in a project in this
field (which is the present situation). FIPA provides standards in order to facilitate
this interoperability and re-usability.
In summary, although agent technology is certainly a very promising approach to
be used when addressing healthcare problems, in opinion of the authors, there is still
much work to be done before agent-based systems are routinely used in medical
environments.
Acknowledgements
The work has been supported by a URV grant, and partially supported by the EU
funded project K4Care (IST-2004-026968) and the Spanish-funded project Hygia
(TIN2006-15453-C04-01).
The authors would also like to acknowledge the work performed by other members
of the K4Care project consortium, especially the medical partners, led by Dr. Fabio
Campana, and Dr. David Riaño (project co-ordinator and designer of the SDA*
formalism).
References
[1] Bakker, A.R.: Healthcare and ICT, partnership is a must. Int. J. Med. Inf. 66(1-3), 51-57
(2002)
[2] Batet, M., Gibert, K., Valls, A.: The Data Abstraction Layer as Knowledge Provider for a
Medical Multi-Agent System. In: Riaño, D., Campana, F. (eds.) K4CARE 2007. LNCS
(LNAI), vol. 4924, pp. 87-100. Springer, Heidelberg (2007)
[3] Beer, M., Hill, R., Huang, W., Sixsmith, A.: An agent-based architecture for managing
the provision of community car - the INCA (Intelligent Community Alarm) experience.
AI Commun. 16(3), 179-192 (2003)
[4] Bellazzi, R., Zupan, B.: Predictive data mining in clinical medicine: Current issues and
guidelines. Int. J. Med. Inf. 77(2), 81-97 (2008)