LECTURE 12: Applications of MAS at URV (II) Artificial Intelligence II – Multi-Agent Systems Introduction to Multi-Agent Systems URV, Winter-Spring 2010
May 19, 2015
LECTURE 12: Applications of MAS at URV (II)
Artificial Intelligence II – Multi-Agent Systems
Introduction to Multi-Agent Systems
URV, Winter-Spring 2010
Outline of the talk
Rationale for applying agents in health careSome specific projects developed by the members of ITAKA
Management of data of palliative patientsWeb-based platform for providing home care services
Research and development challengesFinal thoughts
http://deim.urv.cat/~itaka
Information and Communication Technologies
End of 20th century: enormous development of information technologies
Mobile phonesPersonal and portable computersPersonal Digital Assistants (PDAs)Internet
Information SocietyEasy, flexible and cheap access to information
ICT and MASRecent trend: join the intelligent performance of multi-agent systems with the flexible access to information through new technologiesFuture scenario: ambient intelligence, inwhich ubiquitous agents communicate wirelessly to provide intelligent services to users
In particular, AmI@Medicine
Health Care problemsDistributed knowledge
E.g. different units of a hospitalCoordinated effort
E.g. receptionist, general and specialised doctors, nurses, tests personnel, ...
Complex problemsE.g. organ transplant management
Great amount of informationE.g. medical information in Internet
MAS applied in Health Care
Summary of main motivationsMAS are inherently distributedAgents can coordinate their activities, while keeping their autonomy and local dataDynamic and flexible distributed problem solvingmechanismsUse of personalisation techniques
Example: national organ transplant coordination
Fields of application
Patient schedulingPatient monitoringAgent-based decision support systemsInformation agents in InternetCommunity care, home care, care of old/disabled peopleAccess to medical informationManagement of distributed processes
Outline of the talk
Rationale for applying agents in health careSome specific projects developed by the members of ITAKA
Management of data of palliative patientsWeb-based platform for providing home care services
Research and development challengesFinal thoughts
PalliaSys Project
Integration of Information Technologies and Multi-Agent Systems to improve the care given to palliative patientsSpanish research project, 2004-05Work conducted between the Research Group on Artificial Intelligence at URV and the Palliative Care Unit of the Hospital de la Santa Creu i Sant Pau of Barcelona
Palliative care
Palliative patients are in a very advanced stage of a fatal disease. The aim of their care is to ease their painThese patients may be located in hospitals(Palliative Care Units-PCU, or other units of the hospital), specialised hospice centres or at their own homes
Aims of the PalliaSys project
To improve the process of collecting information from the palliative patientsTo improve the access to this information bypatients and doctorsTo monitor the state of the patientsTo apply intelligent data analysis techniques on the data of the PCU
WAPServer Simul.
WebServer
DB Wrapper
Doctor
Doctor
Patient
Patient
PCU Database
DataAnal.
PCU Head
PALLIASYSArchitecture
Multi-AgentSystem
InformationTechnologies
Web interface
Web interface
Alarm management
Information collectionPatients have to send periodically non-technical information relative to their health stateFill in a form with 10 items to be valued in the [0-10] intervalIn the developed prototype forms could be sent
through a Web page, orwith a mobile phone via WAP (simulated)
Information accessAll the data of the palliative patients arestored in a central Data Base at the PCU of the hospital
Personal information, family data, auto-evaluations, health record
Patients and doctors may make queries on the stored information
Patient queries are made directly on the DB (via Web or WAP-simulated interface)Doctor queries are made through agent communication (the Doctor Agent requesting the information from the DB Wrapper)
Data Base at the PCU / Security
There is an agent that controls the access to the Data Base (the DataBase Wrapper)The whole system includes security mechanisms to protect the privacy of themedical data
User authentication (private-public keys)Encrypted messages (SSL)Access through login/passwordPermissions associated to user types
WAPServer Simul.
WebServer
DB Wrapper
Doctor
Doctor
Patient
Patient
PCU Database
DataAnal.
PCU Head
PALLIASYSArchitecture
Multi-AgentSystem
InformationTechnologies
Web interface
Web interface
Alarm management
Patient agentsThere is a patient agent associated to each palliative patientIt has to continuously monitor the status of the patient, and send alarms to the doctorassociated to the patient if something goes wrong
Doctor agents
A doctor agent is an agent associated to eachdoctor of the PCU, which would be running inthe doctor’s desktop computerIt provides a graphical interface to help:
Request information about his patientsDefine alarm situationsReceive alarm signals from patient agents
Classes of alarmsGeneral alarms
They are defined by the PCU head (through his Doctor Agent), and they have to be applied to all the patients of the unit
Doctor-specific alarmsA doctor can define personal alarms, and he can assign them
to a single patient, orto all his patients
Patient auto-evaluation
There are 10 differents aspects in patient’s auto-evaluation forms (weakness, pain, anxiety, hunger, etc)Each of the aspects has to be evaluated by the patient with an integer number from 0 to 10.Each patient has to send an auto-evaluation form every 2-3 weeks
Alarm types (I)
Alarms defined on a single auto-evaluation(Weakness >7) and (Pain > 8) : extreme_weakness(Hunger < 3) and extreme_weakness: dangerous_weaknessExtreme_weakness => patients 1, 3 and 4Dangerous_weakness => patients 2, 3 and 7
Basic alarms can be combined with and/or/not operators to define more complex alarms
Alarm types (II)Alarms defined on a sequence of auto-evaluations
(Last 2 evaluations a,b) Weaknessb-Weaknessa > 2 : fast_weakness_increase(Last 4 autoevaluations a,b,c,d) Paind-Paina > 3: extreme_pain_increase(Evaluations received in the last 3 weeks) Increase of pain degree > 4
These types of alarms may be defined on the last n evaluations or on the evaluations received in a certain amount of time
The use of Boolean operators and the definition of complex alarm situations are also allowed
Alarm management
Alarms are defined by doctors through their Doctor AgentsWhen an alarm is defined, it is automatically sent to the corresponding Patient Agent (or set of agents)When a new auto-evaluation is stored on the DB, the associated Patient Agent gets a signal, and then it checks all the alarms associated to that patientIf any alarm situation is detected, a message is sent to the Doctor Agent that defined it with an explanation of why the alarm has been activated
WAPServer Simul.
WebServer
DB Wrapper
Doctor
Doctor
Patient
Patient
PCU Database
DataAnal.
PCU Head
PALLIASYSPresent State
Multi-AgentSystem
InformationTechnologies
Web interface
Web interface
Alarm management
Data Analyser: main tasks
To apply Data Mining and Machine Learning techniques to analyse the information of the DBTo provide general statistics on the data, which are useful to the PCU head to fill in the annual report
Available medical data
Input data: sequence of treatment episodesPatient location (home, PCU, socio-sanitary centre)Length of stay (days)Medication received by the patientMedical tests and procedures made on the patientGeneral patient health status
Intelligent Data Analysis
Generation of patient circuits (circuit graph)Automatic detection of patient states
Clustering techniques, unsupervised learningGeneration of models of patient evolution (state graph)Generation of decision structures (decision trees, set of rules)
Possibility of making predictions on future states and anticipate and prevent undesired situations
Circuit graph
State graph
Conclusion – PalliaSys main ideasInformation technologies and Intelligent agents may be used to build useful systemsin the Health Care domainMost of the ideas underlying this project might also be applied in elderly care or home care
Use of Information TechnologiesAutomated patient monitoringIntelligent data analysis
Outline of the talk
Rationale for applying agents in health careSome specific projects developed by the members of ITAKA
Management of data of palliative patientsWeb-based platform for providing home care services: K4Care
Research and development challengesFinal thoughts
© K4Care, 2006
KnowledgeKnowledge--Based Based HomeCareHomeCare eServices eServices
ffor an Ageing Europeor an Ageing Europe
Project Presentation K4CARE Consortium
A Project funded by the European Community under the Sixth Framework Programme for Research and Technological Development
Contract no IST-026968
K4Care basic facts
March 2006 – March 2009 (3 years)Extended until September 2009
EC funding: 3.130.000 €
Coordinator: University Rovira i Virgili
13 Partners from 7 countries
K4Care project
The aim of the K4Care European project is to provide a Home Care model, as well as design and develop a prototype system, based on Web technology and intelligent agents, that provides the services defined in the model
Basic features: a) actors are members of well defined organizations, with
different roles and allowed activitiesb) there is extensive domain knowledge to be considered
(e.g. standard clinical guidelines)c) coordination of tasks in daily care
Clinical Guidelines (CGs)
Indications or principles to assist health care practitioners with patient care decisions Applicable in diagnostic, therapeutic, or other clinical procedures for specific clinical circumstances
CGs: benefits
Consistent clinical practice, avoidance of errorsReutilisation and tailoringRapid dissemination of updates and changesConsideration of appropriate knowledge at appropriate timeUse of formal representation languages
CGs: barriers in daily use
Lack of awarenessLack of familiarityInertia of previous behaviours
No integration with standard practices
Lack of time or resources
Automatic management and enactment of guidelines
Use of CGs in Home Care
Problem: patients in health care usually suffer from several pathologies, and it is not possible to apply the guidelines directlyChallenge: take into account the recommendations of existing guidelines, but adapt their application to the personal circumstances of each individual patient
K4Care Model: Structure1 Nuclear Structure + n Accessory Services
...
THE K4CARE MODEL
HCNS
Actor Service
Action Procedure Data/Information
K4Care Model: Actors and Teams
Knowledge layer
K4Care Knowledge structures
EHCR: Electronic Health Care RecordAPO: Actor Profile OntologyCPO: Case Profile OntologyProcedures FIP: Formal Intervention PlanIIP: Individual Intervention Plan
DBs, Electronic Health Care Record
Data Base: with information about the K4Care actors as users of the K4Care Platform (e.g. contact information)EHCR: with the data about the Home-Care processes performed within the K4Care Platform
Medical documents stored in XML
K4Care Ontologies (I)
Actor Profile Ontology (APO)Types of actorsActions that each actor can performPlatform servicesProceduresDocuments...
K4Care Ontologies (II)
Case Profile Ontology (CPO) DiseasesSyndromesSigns and symptomsSocial issuesAssessment testsInterventions...
K4Care FIPsFormal Intervention Plans (FIPs) are formal structures representing the health care procedures to assist patients suffering form particular ailments or diseasesFIPs are represented with the SDA* formalism
StatesDecisionsActions
The SDA* formalism is used to representK4CARE Service ProceduresK4CARE Formal Intervention PlansK4CARE Individual Intervention Plans
FIP for the management
of hypertension
Procedures
Formal specifications, in the SDA* language, of the way in which an administrative service(e.g. admit a new patient to the Home Care service) has to be implemented
Definition of an Individual Intervention Plan
Input: patient data (EHCR), result of comprehensive assessment, general K4Care knowledge structures (APO, CPO, FIPs)Output: Individual Intervention Plan to be applied on a patientProcess:
Select set of applicable FIPs (diseases, syndroms, symptoms)Merge FIPsAdapt the resulting SDA* structure to the individual characteristics of the patient
K4Care platform features Agent-based Web-accessible platform that provides a set of basic Home Care services
Definition of IIPsApply IIP to the patient
The most relevant aspect of this knowledge-drivenarchitecture is the separation of the knowledgedescription from the software realization Key elements of the architecture
declarative and procedural knowledgeinteraction between agents and end-usersagent-oriented execution of patient-centred plans
Interaction between agents and users
Multi-agent system
1 Actor Agent for each user, permanently runningWhen the user logs in, a Gateway Agent is dynamically created
Two-way communication Web-servlet-GA-AAWhen an Actor Agent has to manage the execution of a procedure/IIP, it creates dynamically a SDA-executor Agent
Transparency between knowledge and its use
Agent-based execution of IIPs (I)
Agent-based execution of IIPs (II)
Agent-based execution of IIPs (III)
Agent-based execution of IIPs (IV)
K4Care main conclusions
KnowledgeIndividual Intervention Plans allow practitioners to implement accurate and personalised sequencesof actions for a particular patient’s treatment
UseThe architecture allows implementing agent-based coordination methods between the actors relevant in Home Care, which adapt their behaviour dynamically depending on the knowledge available in the platform
Outline of the talk
Rationale for applying agents in health careSome specific projects developed by the members of ITAKA
Management of data of palliative patientsWeb-based platform for providing home care services
Research and development challengesFinal thoughts
Some research topics on the use of MAS in Health Care
Communication standardsMedical ontologiesSecurity mechanismsImplementation of agents in mobile devicesPersonalised access to information
Less social and professional reluctance to adopt agent technology
Legal issues
General research topics on MASService description, discovery, compositionStandard agent communication languages and protocolsNegotiation, coordination, cooperation techniquesAgent-Oriented Software EngineeringTrustHuman-agent interactionIntegration with legacy software...
Outline of the talk
Rationale for applying agents in health careSome specific projects developed by the members of ITAKA
Management of data of palliative patientsWeb-based platform for providing home care services
Research and development challengesFinal thoughts
Some general thoughts (I)It is difficult to work with doctors
Very busy, unaware of technical details, change requirements…However, they may end up being happy with a rather simple system (e.g. a well-organised DB, statistics for annual report)
It is difficult to sell “agents” to hospital computer units
Understanding, maintenance, …Information systems are hospital-wide, centralised
Some general thoughts (II)
Security is a matter of degree …Sometimes “real life” technical issues make it unsuitable to use agents
Use of previous prototypes or programming languages
The frontier between “agents” and “non-agents” seems to be difficult to define
Extra material for this week
Many papers on the ITAKA web site on these projects