OpenClinical logo

Software Agents

Autonomous Agents and Multi-Agent Systems for Healthcare

 bullet  Properties of intelligent agents  bullet  Agent technologies in healthcare  bullet  Application projects  bullet  Issues  bullet  References: general  bullet  References: agents in healthcare  bullet  Links

An agent is a goal-directed, computational entity which acts on behalf of another entity (or entities). Agent systems are self-contained software programs possessing domain knowledge and an ability to behave with some degree of independence to carry out actions to achieve specified goals. They are designed to operate in dynamically changing or unstable environments.

Properties of intelligent agents
Software agents are an innovative technology designed to support the development of complex, distributed, and heterogeneous information systems. There is however no complete standard/consensus definition of an agent. As a result, agents tend to be characterised in terms of a number of their behavioural attributes.

Commonly cited main atributes of agents include the following:
  • Autonomy: the ability to act autonomously to some degree on behalf of users for example by monitoring events and changes within their environment.
  • Pro-activity: the ability to pursue their own individual set goals, including by making decisions.
  • Re-activity: the ability to react to and evaluate external events and consequently adapt their behaviour and make appropriate decisions to carry out the tasks to help them achieve their goals.
  • Communication and Co-operation: the ability to behave socially, to interact and communicate with other agents (in multiple agent systems (MAS)) i.e. exchange information, receive instructions and give responses and co-operate when it helps them fulfil their own goals.
  • Negotiation: the ability to conduct organized conversations to achieve a degree of co-operation with other agents
  • Learning: the ability to improve performance over time when interacting with the environment in which they are embedded.

Wooldridge and Jennings (see references and links below) provide detailed descriptions on the above and further characterisitics of software agents. A succinct overall view is provided by Fox, Beveridge and Glasspool [Fox et al, 2003]. This latter paper also discusses the potential of agent technologies to provide advanced platforms for building expert systems for healthcare.
Agent technologies in healthcare
Though the difficulties of implementing agent systems in clinical practice cannot be minimised, the potential for flexible and adaptable distributed intelligent computer systems appears to be considerable.

Current topics of research into the application of agents in healthcare include:
  • Distributed patient scheduling within a hospital.
  • Communication and co-operation between intelligent agents to improve patient management (flexible distributed agent systems have significant potential to improve workflow in healthcare organizations where failures of communication and co-ordination can be important sources of error).
  • Agents that provide remote or elderly care delivery.
  • Multi-agent systems for patient monitoring and diagnosis.
  • Multi-agent systems that improve medical training or education (e.g. tutoring systems).
  • Medical agent-based decision support systems.
  • Information agents that retrieve, compile and organise appropriate medical knowledge sourced from the Internet.
  • Co-ordination between hospitals for managing organs for transplant.
Although research into the application of software agents in health is essentially in its infancy, a number of methodological, technical, social, legal and ethical issues will need to be dealt with before much implementation can be considered. These include:

  • Social acceptance of agent-based systems
  • Lack of standard medical ontologies
  • Lack of centralised control
  • Communication standards
  • Integration with other types of legacy software
  • .
  • Legal and ethical issues (privacy, integrity and authentication ...) related to the use of agents in health care.
  • The security of the exchange of patient information between agents
  • projects

    A selection of agent-based projects in healthcare (all are referenced below).


    Carrel An agent-based system designed to help manage the allocation and delivery of human tissues and organs for transplantation. [Vazquez-Salceda et al, 2003].

    multi-agents/pharmacy Multi-agent system that uses agents to control the use of certain antibiotics within a hospital pharmacy department [Godo et al, 2003].
    Pilot Main component of an agent-based platform that provides mediation services between different applications to support patient management [Xu et al, 2003].
    AMPLIA A multi-agent intelligent learning environment designed to support training of diagnostic reasoning and modelling for domains with complex and uncertain knowledge. [Vicari et al, 2003].
    automated monitoring of clinical protocols Design of a secure and distributed architecture [Alsinet et al, 2003].


    references: general background

    Wooldridge, M. J. An Introduction to MultiAgent Systems. John Wiley & Sons Ltd, (Chichester, England) 2002.

    [Wiley]   [Teaching Resources for the book by Mike Wooldridge, University of Liverpool]

    Table of contents: Intelligent Agents. Deductive Reasoning Agents. Practical Reasoning Agents. Reactive and Hybrid Agents. Multiagent Interactions. Reaching Agreements. Communication. Working Together. Methodologies. Applications. Logics for Multiagent Systems.

    Jennings NR, Sycara K and Wooldridge M. A Roadmap of Agent Research and Development. Int. Journal of Autonomous Agents and Multi-Agent Systems, 1 (1), 7-38, 1998.

    []   [U Southampton]

    " This paper provides an overview of research and development activities in the field of autonomous agents and multi-agent systems. It aims to identify key concepts and applications, and to indicate how they relate to one-another. Some historical context to the field of agent-based computing is given, and contemporary research directions are presented. Finally, a range of open issues and future challenges are highlighted. "

    Wooldridge M, Jennings N. Intelligent agents: theory and practice. The Knowledge Engineering Review, 10(2), 115-152, 1995.

    []   [U. Liverpool]

    " The concept of an agent has become important in both Artificial Intelligence (AI) and mainstream computer science. Our aim in this paper is to point the reader at what we perceive to be the most important theoretical and practical issues associated with the design and construction of intelligent agents. For convenience, we divide these issues into three areas (though as the reader will see, the divisions are at times somewhat arbitrary). Agent theory is concerned with the question of what an agent is, and the use of mathematical formalisms for representing and reasoning about the properties of agents. Agent architectures can be thought of as software engineering models of agents; researchers in this area are primarily concerned with the problem of designing software or hardware systems that will satisfy the properties specified by agent theorists. Finally, agent languages are software systems for programming and experimenting with agents; these languages may embody principles proposed by theorists. The paper is not intended to serve as a tutorial introduction to all the issues mentioned; we hope instead simply to identify the most important issues, and point to work that elaborates on them. The article includes a short review of current and potential applications of agent technology. "

    Nwana HS, Wooldridge M. Software Agent Technologies. BT Technol Journal, vol. 4, 1996.

    []   [BT]

    " It is by now a cliché that there is no one, universally accepted definition of intelligent agent technology, but a number loosely related techniques. And yet there are certain themes that appear common to agent-based systems, and correspondingly, certain problems that must be addressed and overcome by all agent system builders. The aim of this paper is to briefly survey the tools and techniques that can be used to address these common issues, and that hence form a substrate for software agent systems. We begin with a review of agent communication languages, focusing particularly on the emerging standard known as KQML. We then present a thumbnail sketch of various programming languages for building agent-based systems, and go on to discuss support for ontologies, which allow agents to communicate using commonly-defined terms and concepts. We then consider other computing infrastructure support for agent-based systems, in particular, the use of client-server architectures and distributed object frameworks. Finally, we present some general comments and conclusions. "

    Fox J, Beveridge M and Glasspool D. Understanding intelligent agents: analysis and synthesis. AI Communications, 2003, vol 16, pp 139-152.

    []   [Advanced Computation Lab., CRUK]

    " According to Webster’s dictionary an agent is: 1. a person or thing that acts or brings about a certain result 2. one who is empowered to act for another The first part of the definition could include almost any software or hardware device and is not restricted to anything that the AI in Medicine community is interested in. The second part is more suggestive though the concept is not at all precise. Because the idea of an “agent” is somewhat vague it is now common to define agents in terms of their typical characteristics. Caglayan and Harrison identify the characteristic features of agents of the second type as entities that:

  • perform tasks (on behalf of users or other agents)
  • interact with users to receive instructions and give responses
  • operate autonomously without direct intervention by users, including monitoring the environment and acting upon the environment to bring about changes
  • show intelligence – to interpret monitored events and make appropriate decisions.
  • The first three criteria seem straightforward, but the requirement that an agent should “show intelligence” is more troublesome. Psychologists, educationalists and many others have found it difficult to come up with a precise definition of this everyday concept. ...

    Agent Technology Roadmap: Overview and Consultation Report. AgentLink III, December 2004.

    []   [AgentLink]

    " AgentLink has produced a consultation report outlining the current situation with respect to the status of agent technologies and indicating key directions for future development of the field. "

    references: agents in healthcare.

    Nealon, J.L., Moreno, A. The Application of Agent Technology to Health Care AgentCities Working Group on Health Care

    []   [AgentCities]

    " In this paper we briefly describe the initial work of the proposed AgentCities Working Group on Health Care. Issues that are particularly relevant to the adoption of an agentoriented approach to developing software systems in health care are discussed: the characteristics of health care domains, agent-based solutions, and the research and development challenges inherent in employing agents to solve problems in health care. We conclude that multi-agent systems do have an increasingly important role to play in health care domains in that they significantly enhance our ability to model, design and build complex, distributed health care software systems. "

    In: Nealon, J.L., Moreno, A. (2003) (eds.) Applications of Software Agent Technology in the Health Care Domain, Whitestein Series in Software Agent Technologies, Birkhäuser Verlag, Basel.

    Includes: Nealon, J.L. and Moreno, A. (2003) "Agent-Based Applications in Health Care" in Applications of Software Agent Technology in the Health Care Domain (eds Nealon, J.L and Moreno, A.), Whitestein Series in Software Agent Technologies, Birkhäuser Verlag, Basel, 3-18

    []   [springeronline]

    " Introduction.- Agent-Based Applications in Health Care.- Building an Agent-Based Community Care Demonstrator on a Worldwide Agent Platform.- Agent-Based User Interface Adaptivity in a Medical Decision Support System.- A Multi-Agent System for Organ Transplant Management.- and 8 further contributions. "

    Moreno A, Garbay C. (Editorial) Software agents in health care. Artif Intell Med. 2003 Mar;27(3):229-32.

    [PubMed]   [ScienceDirect]

    Other papers in this special issue:

    Alsinet T, Ansotegui C, Bejar R, Fernandez C, Manya F. Automated monitoring of medical protocols: a secure and distributed architecture. Artif Intell Med. 2003 Mar;27(3):367-92.


    Vicari RM, Flores CD, Silvestre AM, Seixas LJ, Ladeira M, Coelho H. A multi-agent intelligent environment for medical knowledge. Artif Intell Med. 2003 Mar;27(3):335-66.


    Amigoni F, Dini M, Gatti N, Somalvico M. Anthropic agency: a multiagent system for physiological processes. Artif Intell Med. 2003 Mar;27(3):305-34.


    Xu Y, Sauquet D, Degoulet P, Jaulent MC. Component-based mediation services for the integration of medical applications. Artif Intell Med. 2003 Mar;27(3):283-304.


    Godo L, Puyol-Gruart J, Sabater J, Torra V, Barrufet P, Fabregas X. A multi-agent system approach for monitoring the prescription of restricted use antibiotics. Artif Intell Med. 2003 Mar;27(3):259-82.


    Vazquez-Salceda J, Padget JA, Cortes U, Lopez-Navidad A, Caballero F. Formalizing an electronic institution for the distribution of human tissues. Artif Intell Med. 2003 Mar;27(3):233-58.


    " Multi-agent systems are one of the most exciting research areas in artificial intelligence (AI) at the moment. A multi-agent system is a collection of independent agents that communicate in order to co-operate in the joint resolution of a complex task. An agent may be defined as an autonomous software entity that receives inputs and interacts with its environment, performing tasks in the pursuit of a set of goals. Although there does not exist a universally accepted definition of the term agent, it is normally assumed that its behaviour should be autonomous (it must control its internal state and take its own decisions), flexible (it has to adapt dynamically to changes in its environment), proactive (it may take the initiative when appropriate and perform actions not explicitly required by the user) and intelligent (by applying AI reasoning and learning techniques). In the last 5 years there has been a growing interest in the application of agent-based systems in health care, and some specialised workshops in this topic are beginning to appear. ... "

    Kamel Boulos MN, Cai Q, Padget JA, Rushton G. Using software agents to preserve individual health data confidentiality in micro-scale geographical analyses. J Biomed Inform. 2005 Aug 10.

    [PubMed]   [ScienceDirect]

    " Confidentiality constraints often preclude the release of disaggregate data about individuals, which limits the types and accuracy of the results of geographical health analyses that could be done. Access to individually geocoded (disaggregate) data often involves lengthy and cumbersome procedures through review boards and committees for approval (and sometimes is not possible). Moreover, current data confidentiality-preserving solutions compatible with fine-level spatial analyses either lack flexibility or yield less than optimal results (because of confidentiality-preserving changes they introduce to disaggregate data), or both. In this paper, we present a simulation case study to illustrate how some analyses cannot be (or will suffer if) done on aggregate data. We then quickly review some existing data confidentiality-preserving techniques, and move on to explore a solution based on software agents with the potential of providing flexible, controlled (software-only) access to unmodified confidential disaggregate data and returning only results that do not expose any person-identifiable details. The solution is thus appropriate for micro-scale geographical analyses where no person-identifiable details are required in the final results (i.e., only aggregate results are needed). Our proposed software agent technique also enables post-coordinated analyses to be designed and carried out on the confidential database(s), as needed, compared to a more conventional solution based on the Web Services model that would only support a rigid, pre-coordinated (pre-determined) and rather limited set of analyses. The paper also provides an exploratory discussion of mobility, security, and trust issues associated with software agents, as well as possible directions/solutions to address these issues, including the use of virtual organizations. Successful partnerships between stakeholder organizations, proper collaboration agreements, clear policies, and unambiguous interpretations of laws and regulations are also much needed to support and ensure the success of any technological solution. "

    Koutkias VG, Chouvarda I, Maglaveras N. A multiagent system enhancing home-care health services for chronic disease management. IEEE Trans Inf Technol Biomed. 2005 Dec;9(4):528-37.

    [PubMed]   [IEEE]

    " In this paper, a multiagent system (MAS) is presented, aiming to enhance monitoring, surveillance, and educational services of a generic medical contact center (MCC) for chronic disease management. In such a home-care scenario, a persistent need arises for efficiently monitoring the patient contacts and the MCC's functionality, in order to effectively manage and interpret the large volume of medical data collected during the patient sessions with the system, and to assess the use of MCC resources. Software agents were adopted to provide the means to accomplish such real-time information-processing tasks, due to their autonomous, reactive and/or proactive nature, and their effectiveness in dynamic environments by incorporating coordination strategies. Specifically, the objective of the MAS is to monitor the MCC environment, detect important cases, and inform the healthcare and administrative personnel via alert messages, notifications, recommendations, and reports, prompting them for actions. The main aim of this paper is to present the overall design and implementation of a proposed MAS, emphasizing its functional model and architecture, as well as on the agent interactions and the knowledge-sharing mechanism incorporated, in the context of a generic MCC. "

    Haigh KZ, Kiff LM et al. The Independent LifeStyle Assistant: AI. Lessons Learned. IAAI 04, San Jose CA, July 25-29, 2004

    []   [Carnegie Mellon University]

    " The Independent LifeStyle Assistant (I.L.S.A.) is an agent-based monitoring and support system to help elderly people to live longer in their homes by reducing caregiver burden. I.L.S.A. is a multiagent system that incorporates a unified sensing model, situation assessments, response planning, real-time responses and machine learning. This paper describes the some of the lessons we learned during the development and six-month field study ... [From Conclusion:] I.L.S.A., in its form as an agent-based system, has been retired. Using an agent-based system, contrary to our expectations, significantly added to the development effort. I.L.S.A. had many capabilities that needed to be centralized, and therefore it is clear to us that pursuing a simpler route would have saved us time, money, and frustration—a singlethreaded, component-oriented architecture may have been a better approach...


    links - introductions to agents and portals
     bullet  Intelligent agents on BT Exact - BT's research, technology and IT operations business  bullet  Agents resources by Mike Wooldridge, University of Liverpool  bullet  Intelligent Agents Group, Department of Computer Science, Trinity College Dublin  bullet  AgentLink network  bullet  AgentCities network  bullet  Agents Portal: Agent and MultiAgent Technology Resources by two Reseachers at Canadian Universities, Sehl Mellouli and Houssein Ben-Ameur  bullet  Multiagent systems - edited by José M Vidal  bullet  UMBC AgentWeb (University of Maryland, Baltimore County)  bullet  Multi-Agent Systems Webliography: links to information on Multi-Agent Systems. From Worcester Polytechnic Institute, Waltham, Mass.
    page history
    Entry on OpenClinical: 21 February 2005
    Last main update: 06 March 2005

    Search this site

    Privacy policy User agreement Copyright Feedback

    Entry on OpenClinical: 21 February 2005
    Last modified:
    © Copyright OpenClinical 2002-2011