• Aucun résultat trouvé

Knowledge-based modelling applied to synucleinopathies

N/A
N/A
Protected

Academic year: 2021

Partager "Knowledge-based modelling applied to synucleinopathies"

Copied!
9
0
0

Texte intégral

(1)

To link to this article: DOI:10.1016/j.eurger.2015.02.011

http://dx.doi.org/10.1016/j.eurger.2015.02.011

This is an author-deposited version published in:

http://oatao.univ-toulouse.fr/

Eprints ID: 14090

To cite this version:

Kamsu-Foguem, Bernard and Tiako, Pierre and Mutafungwa, Edward and

Foguem, Clovis Knowledge-based modelling applied to synucleinopathies.

European Geriatric Medicine. ISSN

1878-7649

O

pen

A

rchive

T

oulouse

A

rchive

O

uverte (

OATAO

)

OATAO is an open access repository that collects the work of Toulouse researchers and

makes it freely available over the web where possible.

Any correspondence concerning this service should be sent to the repository

administrator:

staff-oatao@listes-diff.inp-toulouse.fr

(2)

Technology

applied

to

geriatric

medicine

Knowledge-based

modelling

applied

to

synucleinopathies

B.

Kamsu-Foguem

a,

*

,

P.F.

Tiako

b

,

E.

Mutafungwa

c

,

C.

Foguem

d

aLaboratoryofProductionEngineering(LGP),EA1905,ENIT-INPT,UniversityofToulouse,47,avenued’Azereix,BP1629,65016Tarbescedex,France bCenterforITResearch,LangstonUniversity,OK73050,USA

cAaltoUniversitySchoolofElectricalEngineering,PL13000,00076Aalto,Espoo,Finland d

CenterforFoodandTastesciences(CSGA)–UMR6265CNRS–UMR1324INRA–UniversityofBurgundy,9E,boulevardJeanne-d’Arc,21000Dijon,France

1. Introduction

Thecurrentmedicaldemographyanditsunevendistribution, particularlyin somemedical disciplines,arecreatingsignificant challengesinensuringcontinuityof care.Thishasresultedina pressingneedformedicalfacilitiesinplaceswheretheshortageof specialistsisacute.Telemedicineisatoolthatenablesequalaccess tomedicalexpertiseregardlessofplaceofcare[1].Thispractice allows physicians of regional institutions to ensure access to competencefor differentmedical investigationsorcasesand to

benefit from the expertise of their colleagues from different

specializations (radiology, surgery, psychiatry or neurology)

[2].Indeed,telemedicinehasalloweddoctorshospitalsandclinics

tohavea network for accessingremoteresources and

comple-mentaryskills[3].Otherbenefitsoftelemedicineincludepatients whoarelesstiredandstressedandfamilieswhonolongerhaveto travellongdistancestovisittheirdoctors[4].Medicalpractitioners

now have in their offices or in their local hospitals capacity

identicaltothoseatmajorhospitals.Theseadvancesarepotential

safeguard measures to ensure the protection of some local

hospitals. In summary, telemedicine provides impact in three

keydimensions[5]:

medical impact through improved medical diagnosis and

treatment,aswellas,theincreasedcompetenceofpractitioners participatinginthenetwork;

territorialimpactbymaintainingskillsandspecializedservices inhospitalsandclinicsinmediumandsmallercities,especially inruralareas;

medico-economicimpactthrough reductioninthenumber of

unnecessarytransfersand theincreaseinthenumberof vital transferswithausefulgainforpatientswhilecontrollingcosts. Theeraoftechnologicalnetworksinmedicineisinevitableto

improve the quality, safety, and continuity of care, while

promotingequalaccesstohighqualitylocalcarebypromoting coordinationandcooperationofallstakeholders.Atthe

techno-logical level, further progress can be made in the field of

telemedicineifthemainobstaclesareovercome[6].Bydeploying

this technology in all remote hospitals or care centers, one

improvesconnectivitybysettingapplicationofqualitystandards andbuildingarelationshipoftrust.Telemedicineefficiencyshould

allow equitable management of patients. It allows sharing of

Keywords: Telemedicine Ontologicalknowledge Collaboration Semanticmodelling Geriatrics ABSTRACT

Theadoptionoftelemedicinetechnologieshasenabledcollaborativeprogramsinvolvingavarietyof links among distributed medical structures and health officials and professionals. The use for telemedicinefortransmissionofmedicaldataandthepossibilityforseveraldistantphysicianstoshare theirknowledge on given medical cases provides clear benefits,but also raises severalunsolved conceptualandtechnicalchallenges.Theseamlessexchangeandaccessofmedicalinformationbetween medicalstructures,healthprofessionals,andpatientsisaprerequisitefortheharmoniousdevelopment ofthisnewmedicalpractice.Thispaper proposesanewapproachofsemanticinteroperabilityfor enabling mutual understanding of terminologies and concepts used. The proposed semantic interoperabilityapproachisbasedonconceptualgraphtosupportcollaborativeactivitiesbydescribing howdifferent healthspecialists can applyappropriatestrategies to eliminate differential medical diagnosis.Intelligentanalysisstrategiesareusedtonarrowdownandpinpointmedicaldisorders.The modelproposedisfullyverifiedbyacasestudyinthecontextofelderlypatientsandspecificallydealing withsynucleinopathies,agroupofneurodegenerativediseasesthatincludeParkinson’sdisease(PD), dementiawithLewybodies(DLB),pureautonomicfailure(PAF)andmultiplesystematrophy(MSA).

* Correspondingauthor.Tel.:+33624302337;fax:+33562442708. E-mailaddress:Bernard.Kamsu-Foguem@enit.fr(B.Kamsu-Foguem).

(3)

qualityimageviewingstations(adapteddiagnostic),flexibleusage ofresources(possibilityofWebaccess),and,toensurethat the

benefitsof suchtelemedicine canbemutual, provides

opportu-nities for technology transfer and improved efficiency in the

healthcare sectors of partners institutions.The development of telemedicineisbasedonstrengtheningourinnovationcapabilities andrequiressustainedcooperationthatcutsacrossthefieldsof health, industry, research, and defence [7]. A tele-consultation

session canshow thevarious documents available:image of a

patientorphysician,radiographicimages,andotherclinicaldata. Insomecircumstances,remotebiotechnologytoolscanbeusedto performenricheddiagnosticsbymoleculartechniques,targeting ofpathogens,andidentificationofsensitivitiestodrugsinorderto enhancetreatment[8].

Therestofthepaperisstructuredasfollows.Section2exposes

thematerialandmethodswiththeconceptualgraphoperations

usedtoimplementthemodellingofexpertrulesincollaborative decision-makingprocesses.Section3presentstheresultswithan

illustrative case for the telemedicine management within the

geriatricsfieldispresented.Finally,section4providesadiscussion andsection5concludesanddiscusseslessonslearnedandfuture challenges.

2. Materialandmethods

2.1. Knowledgeformalizationwithconceptualgraphs

Theconceptualgraph(CG)formalismisaknowledge

represen-tationlanguage, which hasa well-definedsyntaxand a formal

semantics that allows one to reason from its representations

[9].Theconceptualgraphformalismisconsideredasacompromise

representation between a formal language and a graphical

language, because it is visual and has a range of reasoning

processes[10].Conceptualgraphscanbeusedinmanycomputer

science areas, including text analysis, web semantics, and

intelligentsystems[11].

A simple conceptual graph is a finite, connected, directed, bipartitegraph consistingofconceptnodes (denotedas boxes),

which are connected toconceptual relation nodes (denoted as

circles). In the alternative linear notation, concept nodes are writtenwithin []-brackets while conceptualrelation nodes are denotedwithin()-brackets.Theconceptssetandtherelationsset aredisjoint.

A concept is composed of a type and a marker [<type>: <marker>],forexample[Disease:IdiopathicParkinson’sdisease]. Thetypeofconceptrepresentstheoccurrenceofobjectclass.They aregroupedin a hierarchicalstructure calleda conceptslattice

showing their inherit relationships. The marker specifies the

meaningofaconceptbyspecifyinganoccurrenceofthetypeof concept.

Aconceptualrelationbindstwoormoreconceptsaccordingto thefollowingdiagram:

C1 ½  ðrelation0snameÞ C 2 ½ meaningthat00C 1 isrelatedtoC2 ð bythisspecificrelation00Þ

Intheanalysisoftelemedicinemanagement,themostcommon relationsaredependencyrelations,specifically,causal, condition-al,temporal,andBooleanconnectives,suchasAND,alternating-OR

and exclusive-ORrelations. An exampleof conceptual graph is

showninFig.1:amedicalactivityistheagentofatelemedicine serviceandits durationis influencedbythediagnosticcriteria.

The semantics of the core and extended CGs is defined by a

formal mapping to and from a common abstract syntax and

model-theoreticfoundationforafamilyoflogic-basednotations (ISO/IEC24707)[12].

Aderivationisafinitesequenceoftheseelementaryoperations thathaveaformalsemanticsbasedonalogicalinterpretation.As aresult,themeaningofgraphoperationsisdeterminedinlightof the derivation to be applied, based on a logical interpretation whichgivesfulleffecttothevisualreasoning[13].Thederivation hasoneofthreeconceivablepropertiesonthelogicalrelationship betweenastartinggraphuandtheresultinggraph

v

[14]: 2.1.1. Equivalence

Copyandsimplifyareequivalencerules,whichgenerateagraph

v

thatislogicallyequivalenttotheoriginal:theknowledgeofu isincludedin

v

andtheknowledgeof

v

isincludedinu(logical meaningu

v

and

v

u).

2.1.2. Specialization

Joinandrestrictarespecializationrules,whichgenerateagraph

v

thatimplies theoriginal:

v

contains morespecificknowledge thanu(logicalmeaning

v

u).

2.1.3. Generalization

Detachandunrestrictaregeneralizationrules,whichgeneratea graph vthat is implied by theoriginal:

v

contains less precise knowledgethan

v

(logicalmeaningu

v

).

Ontological knowledge provides a formal description of the

studied system [15] with associated experiences and lessons

learned[16,17].

2.2. Exploitationofconceptualgraphsrepresentationinreasoning

AformalknowledgemodelledbyCGsinexperiencefeedback

processescanbeaveryusefultoolforconveyingaccuratemeaning

to a collaborative workenvironment involving domainexperts

[18].Foragivenapplication,severalviewpointsofexpertisemay beengagedincombination.Forexample,someinvestigationsto improve the availability of a geriatric health care system can involveexpertknowledgeintele-expertiseandassociatedremote practices.

During theknowledge modelling phase of the telemedicine

rules,theuseofCGpropertieswillhelptoenrichthetelemedicine knowledgebaseinordertoeasetheiraccess,sharingandreuseby themembersofthetelemedicinemanagementintheirindividual andcollectivetasks.Furthermore,experiencegainedandlessons learnedfrominitialproblemsolvingdevelopmentswillbeapplied as soon as possiblein similar situations in othercollaborative telemedicine activities with temporal modelling considerations [19].

In conceptualstructures, the operations of visual reasoning

with semantic mapping form the bridge from perception to

differentformsofconceptualoperations,rangingfrom specializa-tionandgeneralizationtounification[20].Whentheconceptual

graphs operations are used in the visual reasoning, semantic

comparisonsaredeployedateverystep,andtheonlydifference betweendeductionandanalogiesisthenatureoftheorientations onthereasoning[21].Particularly,oneconceptualgraphissimilar toanotherifthereisasemanticmapping(graphhomomorphism) fromthefirstgraphtothesecondone.Inthiscontext,the case-basedreasoningcanbeengagedtosearchsomeunknownfeatures ofanewcasefromitsknownfeaturesandpreviouscasesstoredin thecasesbase.In analogicalreasoning,theconceptualstructure thatdescribesknownfeaturesofthenewcaseiscomparedwith thematchingfeaturesoftheconceptualstructuresassociatedto

previous cases [22]. The assessment takes into account the

determineddegreeofsimilarityandclassifiedalternativeoptions forothercases.Thecasethatprovidesthegreatestcorrespondence

(4)

maybeundertakenasthetopbasisofindicationforapproximating theunknownfeaturesofthenewcase.

3. Results

WeillustratetheproposedapproachusingCGswiththecase studyofsynucleinopathiesmostlyneurologicorgeriatricdiseases. Theaccommodationoftheagingpopulationisamajorconcernin healthcareandforfamilies[23].Thecostofmedicalinterventions fortheelderly,whoareoftenfrailandwithrecurringepisodesof chronicdiseases,isincreasing[24].Supportforthesevulnerable people,whoareoftenisolated,requiresthedeploymentofflexible

and effective systems to prevent hospitalizations sometimes

experiencedbyelderlyasatraumaticeventandenabletheelderly

to maintain their living place if possible [25]. Could new

technologiesprovidesomesolutions?Theexpectedbenefitsare

summarized by economic gain or improvement in the care of

elderlypatientsortheirqualityoflife.Alsoarehealthcareteams theyreadytoembracethesenewtechnologies?

3.1. Clinicaloutlineofthesynucleinopathies

Thisapplicationisinthecontextofdecisionsupportinhealth andrelatesparticularlytoneuroscienceandespecially synuclei-nopathies,agroupofneurodegenerativediseasescharacterizedby

fibrillary aggregates of alpha-synuclein protein (the major

componentsofLewybodies,dystrophic(Lewy)neuritis,andthe Papp-Lantosfilaments)inthecytoplasmofselectivepopulationsof

neurons and glia. These disorders include mainly Parkinson’s

disease(PD),dementiawithLewybodies(DLB),multiplesystem

atrophy (MSA), and also pure autonomic failure (PAF) and

Hallervorden-Spatz syndrome (HHS) [26]. Clinically, they are

characterized by a chronic and progressive decline in motor

(mainly Parkinsonism), cognitive, behavioral, and autonomic

functions, dependingon thedistributionofthelesions[27]. Al-though there are validated clinical and pathological consensus

criteria for PD, DLB, and MSA, because of clinical overlap,

differentialdiagnosisissometimesverydifficult[28].Moreover, early diagnosis of these diseases is also difficult [29]. Several approachesandnewbiomarkersarebeinginvestigatedtofacilitate

the early ante-mortem diagnosis, as the common hallmark of

synucleinopathies is the finding of alpha-synuclein protein on

brain biopsy.Amongthesepotentialnewbiomarkers,there are

myocardialmetaiodobenzyl guanidine(MIBG)scintigraphy[30],

functional cerebral imageries (reduced dopamine transporter

activity in some part of the brain), olfaction’s tests threshold revealinghyposmiaandolfactorypathwaypathology[31].Others

newdiagnosiscorefeaturesasRapidEyeMovementsleep(REM

sleep), behavior disorder, severe neuroleptic sensitivity, some clinical signs, symptoms and biological elements are assessing thestructureofthesefeaturesagainstthecriteriasetoutinthe guideline.However,therediagnosisaccuracyisnotoptimal,but inmostofcases,theycontributetoeliminatedifferentialdiagnosis. Itwillbeusefultoinvestigatednewsapproachesadaptedtothese newneedswithpossibilitytoimprovediagnosiscriteria.

InParkinson’sdisease(PD)forexample,non-motorsymptoms are (described in Table 1): olfactory dysfunction, depression, constipation, pain,genitourinary problems,sleepdisorders, and

cognitive impairments. These are often long ignored, and are

common [32]. They sometimes precede motor symptoms and

should be thoroughly investigated because they lead to a

Binar

y

-

Relation

Before During

Tempor

al-relation

Usual-rela

tio

n

Spatial-rela

tion

Log

ical-rela

tion

Agent

Characterization Object Implication Influence

Concept

Diagnosis Treatment

Medical Activity

Diagno

stic

Criteria

Sign Symptom Test result

Tele

medicin

e

Teleconsultation Teleexpertise Telemonitoring Teleassistance

Durati

on

Compete

ncy

Direction

Tool

Objec

t

Telemedicine

Medical Activity agent Usual-relation Duration

Diagnostic Criteria influence Outside

Inside

Teleexpertise

Diagnosis: Idiopathic Parkinson'sdisease agent characterization Duration

Test Result influence

Specializatio

n

Generalization

Patient

(5)

significantburden on the quality of life and have a significant contributiontothemorbidity ormortalityrates ofPD. Besides,

functional imaging using dopaminergic tracers with either

PositronEmissionTomography(PET)orSinglePositronEmission

Tomography(SPECT)canidentifydopaminedeficienciesbutmay

notreliablydifferentiatebetweenParkinson’sdiseaseandother akineticrigiddisorders.Inaddition,evenapathological examina-tioncannotclassifyclinicalsyndromeswithcertainty.Despitethe diagnosticcriteria, a diagnosis of certainty is oftendifficult to

establish because it requires a formal demonstration of the

characteristicfeaturesofthepresumptivedisease. Clinicopatho-logicalstudieshaveshownthattheaccuracyofaclinicaldiagnosis ofPD isless than 80%.More selecteddiagnosticcriteria would increasetheproportionoftruePDcasesidentifiedtomorethan 90%[33].

Misdiagnosisofasynucleinopathyasanotheroneistherefore

potentially extremely dangerous for these patients because of

thetherapeuticsimplications.Forexample,inpatientswithPDor

withdementia with Lewy bodies (DLB), typical neuroleptic or

antipsychoticdrugscouldleadtoneurolepticmalignantsyndrome (NMS),alife-threateningneurologicaldisordermostoftendueto adversereactionsofthesedrugs.NMStypicallyconsistsofmuscle rigidity,fever,autonomicinstability,andcognitivechangessuch

as delirium, and is associated with elevated plasma creatine

phosphokinase.

Morerecentstudiesadvocatethatlanguage,especially seman-tics,maybeanareaofcognitioncapableofdistinguishing

early-onset synucleinopathy patients from healthy controls and

discriminating between various types of synucleinopathies

[34].Particularly,languagedisturbancesin dementiahavebeen

factually attributed to the degradation of stored knowledge,

whereasitisfrequentlyassumedthatlanguagedeficitsinstroke aphasiamirror modality-specificimpairment ofaccesstointact

conceptual knowledge [35]. These deficits can be an acquired

disorderoflanguagecomprehension,production,and/orsymbolic

knowledge.In addition tomemory and language impairments,

assessment in other cognitive domains can also highlight the

influenceof semanticknowledge,for instance,ondecoding the

physico-chemical properties of an odorant [36]. Understanding thesemantics of cognitiveimpairmentsin synucleinopathiesis thusessentialforanumberofarguments.Identifyingsimilarities

and differences between synucleinopathies is the first step in

evolving tests that are differentially sensitive to the distinct conditions,thusprovidingappropriatescreeningteststosupport clinicaldiagnosis.Understandingthequalityofimpairmentsalso providessignificantinformationforpatients andcarers, helping physicians to elaborate better coping skills and care strategies. Besides,comparingthepropertiesofcognitiveimpairmentbetween

patient groups had often contributed to an improvement in a

semanticanalysisoftheprocessunderlyingexecutivecontrolfor understandingthenormalorganizationofcognitivefunctions[33]. 3.2. Visualmodellingofanalysisproceduresinsynucleinopathies

Wecanthink aboutthecontributionofartificialintelligence toolsasameansofanalysistosupportmedicaltestsfortheearly diagnosisanddifferentiationofthesepathologies.Particularlyin this context, operations of conceptualgraphscan be crucial to reasoningonknowledgewithvisualexplanations.Thisknowledge can provide evidence and analysis relevant to the activities of diagnosesanditisveryimportantformedicalresearchingeriatrics orneurosciences.Tothatend,weplantoincludetheengagement of reasoningtechniquesto determineby sequential association rules[37]themostsignificantrulestoassistintheestablishment of themost appropriate diagnosisand to eliminate differential diagnoses. Shared practice rules face the challenge of creating

a solid foundation to support the cognitive development of

collectiveintelligence.Theserulescanbeannotatedusingdomain

ontologies andevaluated byotherusers,who mightconsidera

form of suggestion using intelligent components based on the

annotationsassociatedwithasynucleinopathy.Forexample,given acollaborative actiononasynucleinopathy,decisionsregarding

Table1

Descriptionofnon-motorsymptomsassociatedwithIdiopathicParkinson’sdiseaseadaptedfrom[42].

Non-motorsymptomsassociatedtoIdiopathicParkinson’sdisease Supposedbraindamage Psychological,psychiatricand

cognitivesymptoms

Depression,anxiety,panicattacks,feelinghopeless Locuscoeruleus(norepinephrine),inferiorraphe nucleus(serotonin),amygdala

Apathy,anhedonia,inattention,vegetativesymptomsof depression

Uncertain Psychosis,inappropriatebehaviorandotheradversebehavioral

effectsdisorders,obsessive-compulsivedisorders,delirium

Limbiccortex,amygdala Parkinsonismdementia,confusion,hallucinations(iatrogenic

factor)

Temporallobe,hippocampus,locuscoeruleus, amygdala,nucleusbasalisofMeynert(acetylcholine) Sleepdisturbances Sleep-onsetinsomnia,trueinsomnia,nighttimehallucinations,

rapideyemovementsleepbehaviordisorder,daytime sleepiness,sleepattacks

Subcorticalnucleus(pedunculopontineand subcoerulusnucleus),hypothalamus Sleepfragmentation,sleepapnea(central(CSA),obstructive

(OSA),andcomplexormixedsleepapnea),restlesslegs syndrome(RLS)

Uncertain

Dysautonomicsymptoms Bladder-sphincterdysfunctions(urinaryfrequencyandurinary incontinence,dysuria),excessiveperspiration,abnormalsexual behavior(impotence,hypersexuality),xeropthalmia

Dorsalnucleusofvagusnerve

Orthostatichypotension,post-prandialhypotension Vagusnerve,stellateganglion(orcervicothoracic ganglionorinferiorcervicalganglion)

Gastrointestinalsymptoms Drooling,ageusia(tasteloss),swallowingdisorders,dysphagia, gastroesophagealreflux,vomiting,nausea,constipation,fecal incontinence

Dorsalnucleusofvagusnerve(adrenaline)

Sensorysymptoms Olfactorydisturbance Olfactorybulb

Pain,paresthesias Uncertain

Others Fatigue,seborrhea(skinandgreasyhair),excessive perspiration,weightgain,weightloss

(6)

thisactioncanbeautomaticallysuggestedbasedonthe annota-tions,providingthemosteffectivedecisionssemanticallyrelated

to this action. In addition, an adaptation rule is a form of

experientiallearning[38],insofarasitisstudiedintermsofhowto

respondtoamismatchbetweentheexpectedsituationand the

resultsobserved. This leadsto a learning semantic requiring a differenttypeofconceptualorganizationconsistentwithahigher levelofabstractiontoobtainabetterunderstandingoftheeffects ontherulesandknowledgemanipulated.

We consider now the conceptual graph describing the

collaborative expertise (as shown in Fig. 2). In this graph, the differentspecialistscanapplyappropriatestrategiestoidentify, localize,and(wherepossible)correcttheerrorsintheknowledge modelling.Theconceptualgraphspecifiestheuseofintelligent

analysis strategies to narrow down and pinpoint medical

disorders. Through the medical knowledge base, such crucial

expertdescriptionscanbesharedandreusedbythespecialistsin theirindividualandcollectivetasks.Asaresult,bymeansofthe disordersstrategies,fromwhichspecialistslearn,theyareableto

transfer the acquired knowledge and lessons learned easily to

another similar context, with the goal of preventing disease

consequencesorreducingthemtoaminimum.Theywillbeableto

determine whether a context is problematic, whether the

diagnosisor information flow is incorrect, or if theanalysis of thediseasecontextisdefective.

We can also use this experienced knowledge for dedicated

analysisofthespecificstudieddisease(e.g.,Parkinson’sdiseasein

Fig. 3). Thus, in order to assess, interpret, and verify the

reasonableness of the modeled knowledge,one would have to

ensurethatthevarioustypesoftargetedsituationsareconsistent byusingtheprojectionoperationofCGs.Furthermore,theanalysis shouldnotbeviewedastheproblemofoneexpertisemorethan anotherbutasaglobalproblem,whichallinvolvedmembersofthe collaborativeorganizationwouldaddress.

Weputforwardanontologicalmodelandconceptualstructure looselybasedonthevisualapproachusedtosupportteambased telemedicine collaboration. In the considered medical context,

healthcare involves a variety of specializedexperts in different

fields who are often geographically separated. They appreciate

collaborativeactionstofixaparticularcomplexproblemforwhich theirbackgroundandtrainingmakethemqualified.Inthiscase

study, telemedicine actually helps in the diagnostic decision

process,sinceityieldsimprovementintermsofthecostand/or

time neededto arriveat a decision. Research and progresson

telemedicinecouldbevaluable;especiallyweareactuallytesting itinarealtelemedicineenvironment.

4. Discussion

The mainstream eHealth interoperability enhancement

effortsintheECandkeystandardsdevelopmentorganizations

areroughlyclassifiedinto:legalinteroperability,organizational interoperability,technical interoperability,andsemantic inter-operability.Whilepaperobjectivestargetchallengesofsemantic

interoperability, the discussions therein also provide heavy

coverageonissuesoftechnicalinteroperability(ontelemedicine infrastructure)andtosomeextentonorganization interopera-bility.Furthermore,thereareongoingactivitiestodevelopand/ orharmonizeeHealthinteroperabilitystandards(ledbythelikes ofContinuaHealthAlliance,IHE,IEEE/ISO,ITUeHSCG,IHTSDO, etc.). There is a need forfurther research regarding organiza-tionalchange,incentives,liabilityissues,end-usersHIT compe-tencesandskills,structureandworkprocessissuesinvolvedin realizingthebenefitsfromhealthinformationtechnologies(HIT) [39].

Under the coordination of the health information systems

strategydelegation,aworkinggroupoftheFrenchNationalSteering

Committee of Telemedicine has developed a series of concrete

recommendationsfortheoperationalimplementationoftechnical systemsunderlyingthetelemedicineprojectsandactivities[40]:

to promote the implementation of a comprehensive and

coherent infrastructure to include the implementation of

telemedicineprojectsinacoherenturbanization;

Context: elderlypatient

description

Parkinson Synucleinopathies Component

2 1 2 1 Implication 2 Component

DementiawithLewybodies

Multiple system atrophy Component

1

2

2

Analysis: suggestives features

description

Olfactory Dysfunction 1 OR 2

OR

1 2

Cardiovascular dysfunction: {repeated falls, fainting} Language impairments Depression OR 1 2 OR 1 2 1

Analysis: supportivefeatures

description

Neurolepticsensitivity 1 OR 2

OR

1 2

L-dopa treatment ’s efficiency

Sleeps Disorders (REM) OR 1 2 OR 1 2

Analysis: Core features

description

Features of Motor Decline 1 OR 2

OR

1 2

Inadequate Behavioural Attitude; hallucinations

Autonomic Dysfunction Cognitive Impairment

OR 1 2 OR 1 2 Before 1 2 Before 1 Characterization

2 1 Oculomotor disorder (palsy) OR 2 1 Brain-imagingscans

(7)

to conduct a risk assessment relating to the security of informationsystemsthatmayaffectthesuccessful accomplish-mentoftheactivityconcerned;

todevelopaglobalandconsistentmanagementofthetechnical devicestoensurethattheirdiversityreallyisenriching; toprovidetraining,suitablesupportandanadaptedassistance:

supervisedstudyperiodsandtutoringservices;

to establish a conventional setting corresponding to the

contracts for the provision of updated technical services in conductingongoingdialoguewithtechnologicalthirdparties.

In practice, this mainly means the capacity to ensure an

effectivemanagementofpersonaldata,whileensuringcompliance withdata protection principlesand security of data exchanges

between different organizations that are concerned by the

telemedicine procedures. Secondly, it is important to prevent

risks threateningthe safety of operational devices. To do this,

operators need to carefully and constantly apply effective

methodologiesandfurtheradvancesinexplorationand develop-menttechniquestoincreasethelikelihoodofdetectingahazard affectingthesafetyofconsidereddevices.Someeventsmaycause

undesired operation (namely service interruption, fraudulent

interferenceonthepartofa thirdpartyorcomputervirusesor inappropriatetimingoftasksandimpairedsignalsordata)andwe shouldmonitorthesignificantoperationalrisksoftheimplement ofthetelemedicineprocedures,inorder,interalia,toidentifyatan

early stage unforeseen adverse effects and to have a look at

possiblesolutions(palliative,curativeandpreventiveoptions). Furthermore,itisimportanttoimproveasfaraspossiblecase managementatallcomponentsoftheproposedimplementationof thetechnicalaspectsoftelemedicinedevicesinaglobalframework basedonformalproceduresandfoundedonbestpractices.Inthis

context, it would ensure a sufficient level of comprehension,

accession and assimilation by the medical actors and health

professionalsusingtelemedicinedevicesforthefullregistrationof

the remote services in the everyday professional practices.

Therefore, it is essential to establish with technological third parties,intheframeworkpartnershipagreementssignedbetween

themandtheProjectManager,requirementlevelsconsistentwith theneedsidentifiedintheagreementswithbusinessstakeholders.

5. Conclusion

In this paper, we have shown that the use of knowledge

modelling and formal semantic techniques provide additional

supporttotelemedicinetasksbyimprovingtheuser understand-ingofthediseasesbeingtreated.Wemadeacasestudywiththe knowledgemodellingofsynucleinopathiesinelderly.Theresults ofthisstudygaverisetoa seriesofrecommendations,whichin turnwillformthefoundationofthecollaborativeactionplanin

response to telemedicine management. Particularly, non-motor

symptoms play an essential part in appropriate diagnosis of

synucleinopathies and a very insightful and knowledgeable

analysisoftheirsystemictemporaldevelopmentschemesshould

more consequently be taken into consideration within the

elaborationofdiagnosticprogrammesinthefieldofhealthpolicy.

However, while the motor-based disease (or even cognitive

disorder) diagnosis system is described in some detail, the

elementsoftheconsiderednon-motorsymptomsevaluationare

sketchy,in particular withregard toprocessand management.

Such facilities are currently an early stage and for instance, olfactorytests,whichweresupposedtobeautomated,hadtobe executedmanuallyinordertoensurecorrectnessof processing and reports on diagnosticevaluations. Aswell, these processes oftenareheldoveracoupleofhours,requiringtimeinvestments frompatients andhealth professionals.Thisdoes notallowthe medicalactorsresponsiblefortheregularoutpatientconsultations tovalidatesomemedical investigationsanddiagnosisfor acute

illness and preventive health care. We will achieve these

investigations through the close collaboration of ambulatory

carewithinterestedphysiciansandmedicalreferencecenters.It iscurrentlyassociatedwithamovementtoincludeafocusonthe healthofelderlypersonstohelptoverifythatequalityinaccessto healthcareismadeareality.Undercollaborativeactivitiesmadein telemedicine, medical organizationsarepooling their resources andstructurestoimplementasustainableandeffectiveinclusion

Context: elderlypatient description

Parkinson implication 1 2

description Bradykinesia Motorsymptoms description

Resting tremor

OR 2 1 OR 2 1 description Hypertony before2 1 description

Mood disorders: depression Nonmotor symptoms

description

Loss of sense of smell

OR 2 1 OR 2 1 description

Autonomic Dysfunction description

Olfactory Test Supportingfeatures

description Abnormal SPECT/PET OR 2 1 OR 2 1 description before2 1

Brain-imaging scan

OR 2 1 description L-dopa efficiency OR 2 1 description Postural instability OR 2 1 description REM

(8)

programmedesigned toguarantee maximumpossible coverage andequalconditionsasregardsaccessandtreatmentforpatients, regardlessoftheirageorplaceofresidence.

Relying on the modelling of expert knowledge through

conceptual graphs operations, we proposed an approach that

positivelyimpactsthetelemedicinemanagementplans:

abetteraccesstoavailablebestpracticesandmethodologiesas wellassupporttrainingandtheexchangeofinformationonnew practicaldevelopmentsrelatedtocriticalmedicalactivities. aframeworkofpracticalknowledgeandgoodpracticetoensure

modellingofneededinformation,qualitytutoringandtobring stakeholderstogetheratorganizationandgloballevels. apossibleconceptualmodellingwithreasoningmechanismsfor

theanalysisandexchangeofgoodpracticesonaccesstoservices.

To that end, good modelling practice on access to traces of

reasoningshouldbepromoted.

If the significant potentials of telemedicine to assist in the managementguidanceandoutpatientcarearetoberealized,then

research strategies need to be undertaken to improve disease

diagnosis and monitoring. However, the modalities of suchan

approach should be clarified so as to allow greater security,

flexibilityandergonomicfunctionalities[41]inrespondingtothe pragmaticneeds ofmedicalprocedures[42]and efficientuseof experiencedhealthcareproviders[43–51].

Disclosureofinterest

The authors declare that they have no conflicts of interest concerningthisarticle.

References

[1]SimonP,WilliattePellitteriL.Lede´cretfranc¸aisdete´le´me´decine:unegarantie pourlesme´decins.EurResTelemed2012;1(2):70–5.

[2]vandenBergN,SchumannM,KraftK,HoffmannW.Telemedicineandtelecare forolderpatients—Asystematicreview.Maturitas2012;73(2):94–114.

[3]EkelandAG,BowesA,FlottorpS.Effectivenessoftelemedicine:asystematic reviewofreviews.IntJMedInform2010;79(11):736–71.

[4]AdewaleD,OlumideSundayAdewale.Aninternet-basedtelemedicinesystem inNigeria.IntJInfManage2004;24(3):221–34.

[5]LarengL.TelemedicineinEurope.EurJInternMed2002;13(1):1–3.

[6]BensinkM,HaileyD,WoottonR.Asystematicreviewofsuccessesandfailures inhometelehealth:preliminaryresults.JTelemedTelecare2006;12:8–16.

[7]KrupinskiEA,PattersonT,NormanCD,RothY,ElNasserZ,AbdeenZ,etal. Successfulmodels fortelehealth.OtolaryngolClin NorthAm2011;44(6): 1275–88.

[8]BlackR,FavaF,MatteiN,RobertV,SealS,VerdierV.Casestudiesontheuseof biotechnologiesandonbiosafetyprovisionsinfourAfricancountries.J Bio-technol2011;156(4):370–81.

[9]SowaJ.Conceptualstructures:informationprocessinginmindandmachine. Thesystemsprogrammingseries.Boston,Massachusetts,USA: Addison-Wes-leyLongmanPublishingCo.,Inc;1984.p.481.

[10]CheinM,MugnierM-L.Graph-basedknowledgerepresentation: computa-tionalfoundationsofconceptualgraphs.Series:advancedinformationand knowledgeprocessing.London(UnitedKingdom):Springer;2008 [445p.; ISBN978-1-84800-285-2].

[11]HitzlerP,ScharfeH.Conceptualstructuresinpractice, 1sted,Chapmanand Hall/CRC;2009[425p.;ISBN-10:1420060627,ISBN-13:978-1420060621].

[12]SowaJF.Knowledgerepresentation:logical,philosophical,andcomputational foundations.PacificGrove,California(USA):BrooksColePublishingCo.;2000 [608p.;ISBN0-534-94965-7].

[13]Kamsu-FoguemB.Knowledge-basedsupportinnon-destructivetestingfor healthmonitoringofaircraftstructures.AdvEngInform2012;26(4):859–69.

[14]SowaJF.Chapter5:Conceptualgraphs.In:vanHarmelenF,LifschitzV,Porter B,editors.Handbookofknowledgerepresentation. Foundationsofartificial intelligence,3.Elsevier;2008.p.213–37.

[15]GruberTR.Towardprinciplesforthedesignofontologiesusedforknowledge sharing.IntJHumComputStud1995;43(4–5):907–28.

[16]GruberTR.Ontologyoffolksonomy:amash-upofapplesandoranges.IntJ SemantWebInformSyst2007;3:1–11.

[17]Kamsu-FoguemB,CoudertT,GenesteL,BelerC.Knowledgeformalizationin experiencefeedbackprocesses:an ontology-basedapproach.ComputInd 2008;59(7):694–710.

[18]Dieng-KuntzR,MinierD,RuzickaM,CorbyF,CorbyO,AlamarguyL.Building andusingamedicalontologyforknowledgemanagementandcooperative workinahealthcarenetwork.ComputBiolMed2006;36(7–8):871–92.

[19]Kamsu-FoguemB,DialloG,FoguemC.Conceptualgraph-basedknowledge representationforsupportingreasoninginAfricantraditionalmedicine.Eng ApplArtifIntell2013;26(4):1348–65.

[20]BagetJ-F,MugnierM-L.Extensionsofsimpleconceptualgraphs:the com-plexityofrulesandconstraints.JArtifIntellRes2002;16:425–65.

[21]BagetJ-F,Lecle`reM,MugnierM-L,SalvatE.Onruleswithexistentialvariables: walkingthedecidabilityline.ArtifIntell2011;175(9–10):1620–54.

[22]SowaJF,MajumdarAK.Analogicalreasoning.InternationalConferenceon ConceptualStructuresinDresden,Germany,inJuly2003. In:AldoA,LexW, GanterB,editors.Conceptualstructuresforknowledgecreationand commu-nication,LNAI2746.Springer-Verlag;2003.p.16–36.

[23]CombesC,AzemaJ.Clusteringusingprincipalcomponentanalysisapplied toautonomy–disabilityofelderlypeople.DecisSupportSyst2012.http:// dx.doi.org/10.1016/j.dss.2012.10.016[availableonline6October2012]. [24]PerezF,HelmerC,DartiguesJF,AuriacombeS,TisonF.A15-year

population-basedcohortstudyoftheincidenceofParkinson’sdiseaseanddementiawith Lewy bodiesinan elderlyFrenchcohort. JNeurol NeurosurgPsychiatry 2010;81(7):742–6.

[25]PengY,ZhangY,WangL.Artificialintelligenceinbiomedicalengineeringand informatics:anintroductionandreview.ArtifIntellMed2010;48(2–3):71–3.

[26]GalpernWR,LangAE.Interfacebetweentauopathiesandsynucleinopathies:a tale of two proteins. Ann Neurol 2006;59(3):449–58. http://dx.doi.org/ 10.1002/ana.20819[PMID1648960].

[27]RouchI,ThomasAnterionC,DauphinotV,KerlerouxJ,RocheF,BarthelemyJC, etal.Cognitivecomplaints,neuropsychologicalperformanceandaffective disorders in elderly community residents. Disabil Rehabil 2008;30(23): 1794–802.

[28]Martı´ MJ,TolosaE,CampdelacreuJ.Clinicaloverviewofthesynucleinopathies. MovDisord2003;18(Suppl.6):S21–7.

[29]AarslandD,LondosE,BallardC.‘‘Parkinson’sdiseasedementiaanddementia with Lewy bodies: different aspects of one entity’’. Int Psychogeriatr 2009;21(2):216–9.http://dx.doi.org/10.1017/S1041610208008612. [30]OrimoS.ClinicalandpathologicalstudyonearlydiagnosisofParkinson’s

diseaseanddementia withLewybodies.RinshoShinkeigaku2008;48(1): 11–24.

[31]Silveira-MoriyamaL,MathiasC,MasonL,BestC,QuinnNP,LeesAJ.Hyposmia inpureautonomicfailure.Neurology2009;72(19):1677–81.http://dx.doi.org/ 10.1212/WNL.0b013e3181a55fd2[10.1212].

[32]BerendseHW,RoosDS,RaijmakersP,DotyRL.Motorandnon-motor corre-latesofolfactorydysfunctioninParkinson’sdisease.JNeurolSci2011;310(1): 21–4.

[33]Metzler-BaddeleyC.Areviewofcognitiveimpairmentsindementiawith Lewybodiesrelativeto Alzheimer’sdiseaseandParkinson’sdisease with dementia.Cortex2007;43(5):583–600.

[34]ForbesK.Amulti-disciplinaryapproachtodiagnosisandassessmentin early-onsetdementia.Cortex2005;41(1):90–5.

[35]ReillyJ,RodriguezAD,LamyM,Neils-StrunjasJ.Cognition,language,and clinicalpathologicalfeaturesofnon-Alzheimer’s dementias:anoverview. JCommunDisord2010;43(5):438–52.

[36]PonceletJ,RinckF,ZiesselA,JoussainP,The´venetM,etal.Semanticknowledge influencesprewiredhedonicresponsestoodors.PLoSOne2010;5(11):e13878. http://dx.doi.org/10.1371/journal.pone.0013878.

[37]Kamsu-FoguemB,RigalF,MaugetF.Miningassociationrulesforthequality improvement of the production process. Expert Syst Appl 2013;40(4): 1034–45.

[38]KoskinenKU.Problemabsorptionasanorganizationallearningmechanismin project-basedcompanies:process-thinkingperspective.IntJProj Manage 2012;30:308–16.

[39]LluchM.Healthcareprofessionals’organizationalbarrierstohealth informa-tiontechnologies—Aliteraturereview.IntJMedInform2011;80(12):849–62.

[40]DGOS,TechnicalWorkingGroup/InformationSystems,FrenchMinistryof Employment,LabourandHealth.Recommendationsfortheimplementation ofatelemedicineproject.Technicaldeployment:urbanizationand infrastruc-ture2012.

[41]TiakoPF.Processmodelling,delegationandcontrolinglobalsoftware devel-opment.IntJComputApplTechnol2011;40(30).

[42]DoumbouyaMB,Kamsu-FoguemB,KenfackH,FoguemC.Telemedicineusing mobiletelecommunication:towardssyntacticinteroperabilityin teleexper-tise.TelematInform2014;31(4):648–59.

[43]Kamsu-FoguemB,Tchuente´-FoguemG,AllartL,ZennirY,VilhelmC,Mehdaoui H,etal.User-centeredvisualanalysisusingahybridreasoningarchitecturefor intensivecareunits.DecisSupportSyst2012;54(1):496–509.

[44]Kamsu-Foguem B. Systemic modeling in telemedicine.Eur Res Telemed 2014;3(2):57–65.

[45]Kamsu-Foguem B. Ontological view in telemedicine. Eur Res Telemed 2014;3(2):67–76.

[46]Kamsu-FoguemB,Tchuente´-FoguemG,FoguemC.Conceptualgraphoperations forformalvisualreasoninginthemedicaldomain.IRBM2014;35(5):262–70.

[47]Kamsu-FoguemB,Tchuente´-FoguemG,FoguemC.Usingconceptualgraphs forclinicalguidelinesrepresentationandknowledgevisualization.Inform SystFront2014;16(4):571–89.

[48]Kamsu-FoguemB,FoguemC.Couldtelemedicineenhancetraditional medi-cinepractices?EurResTelemed2014;3(3):117–23.

(9)

[49]DoumbouyaMB,Kamsu-FoguemB,KenfackH,FoguemC.Aframeworkfor decisionmakingonteleexpertisewithtraceabilityofthereasoning.IRBM 2015;36(1):40–51.

[50]Kamsu-FoguemB,FoguemC.AdversedrugreactionsinsomeAfricanherbal medicine:literaturereviewandstakeholders’interview.IntegrativeMedicine Research2014;3(3):126–32.

[51]Kamsu-FoguemB,Tchuente´-FoguemG,FoguemC.Verifyingamedical proto-colwithtemporalgraphs:Thecaseofanosocomialdisease.JournalofCritical Care2014;29(4):690.e1–9.

BernardKamsuFoguemHehasaPhDinComputerScienceandEngineeringfromthe UniversityofMontpellier2in2004.Hegotthe‘‘accreditationtosuperviseresearch’’, abbreviatedHDRfromUniversityofToulousein2013.Hiscurrentinterestsarein KnowledgeDiscoveryand DataMining,KnowledgeRepresentation,FormalVisual Reasoning,Ontology-basedSemanticAnalysis,KnowledgeExploitationfor Collabora-tion,DecisionSupportSystemsandIntelligentSystems.Applicationdomainsinclude ContinuousImprovementprocessandHealthInformationSystems.Heisareviewerfor alargenumberofinternationalscientificjournalssuchasComputersinBiologyand Medicine,KnowledgeManagementResearch&Practice,InteractingwithComputers, Sensors,EngineeringApplications ofArtificial Intelligence and Knowledge-Based Systems.Heisamemberofthethematicgroup:e-HealthofInterOP-VLab (Interna-tionalVirtualLaboratoryforEnterpriseInteroperability).

PierreF.TiakoHeistheDirectoroftheCenterforInformationTechnologyResearchat LangstonUniversity(USA)andanassistantprofessorofComputerScienceand Infor-mationSystem.HeworkedasavisitingprofessoratOklahomaStateUniversity(OSU) beforethecurrentposition.PriortoOSU,hetaughtcomputersciencecoursesanddid researchatUniversitiesofNancyandRennes(France),andalsoworkedasanexpert engineeratINRIA,theFrenchnationalinstituteforresearchininformationtechnology. Dr.Tiakohasauthoredmorethan50journalandconferencetechnicalpapersand co-editedfourproceedingsvolumes,resultingfromservicesasprogramchairforseveral internationalconferencesandworkshops.HeholdsaPhDinsoftwareandinformation systemsengineeringfromNationalPolytechnicInstituteofLorraine(France).Dr.Tiakois aseniormemberofIEEEandpastChairmanforIEEEOklahomaCityComputerSociety.

EdwardMutafungwaHeisaresearcherandprojectmanagerattheDepartmentof CommunicationsandNetworking(Comnet)oftheAaltoUniversitySchoolof Elec-tricalEngineering.HereceivedtheB.Eng.degreeinElectronicSystemsEngineering andtheM.Sc.degreeintelecommunicationsandinformationsystemsbothfromthe UniversityofEssex,Colchester,U.K.,in1996and1997,respectively,andtheDr.Sc. Tech.degreeinCommunicationsEngineeringfromtheHelsinkiUniversityof Tech-nology(TKK,nowAaltoUniversitySchoolofElectricalEngineering),Espoo,Finland, in2004.Foroveradecade,hehasalternativelybeenalecturer,researcherand projectmanagerinvariousnational(TEKES,AcademyofFinland)andinternational (EU,Celtic)projectsatComnet,AaltoUniversity.Hisresearchinterestsliewithinthe generalfieldsofbroadbandwirelesscommunications,opticalnetworking,ICTfor development(ICT4D)andpublicsafetycommunications.Intheareaoftelemedicine, hehasbeenstudyingtheuseofmobilebroadbandtechnologies(smallcells)for implementationofpersonaltelehealthsystems andemergencytelemedicinein indoorenvironments.

Clovis FoguemHe isanInternal Medicineand Geriatric medicaldoctorand has undertakenaPhDon‘OlfactionandElderly:studyoftheolfactory(CNI)andtrigeminal (CNV)sensitivitiesinteractionsinageriatricpopulation;constantsandpathological specificities’.He isalsoparticularlyinterestedinneurodegenerativediseases (as ParkinsondiseaseorLewyBodydementia),elderlyepilepsyandwhetherpathogenic inflammatoryorautoimmuneresponses cancontributetothesedisordersinthe elderly.Moreoverheisalsointerestedinmedicalknowledgerepresentationand medicalclinicdesignguidelines.Forhisworkon‘OlfactionandElderly’,DrC.Foguem waslaureateofHealthResearchAwardforemerginghealthresearchersfromthe corporatefoundation‘GroupePasteurMutualite´’in2011.Heisgroundedinmedical researchapplicationsofInformationandCommunicationsTechnology.FormerFaculty ofMedicine’sClinicalInstructor,heisnowHospitalPractitionerinFrance.Heis peer-reviewerofmanyscientistjournalsamongwhich:ClinicalInterventionsinAging; DegenerativeNeurologicalandNeuromuscularDisease;InternationalMedicalCase ReportsJournal;NeuroscienceandNeuroeconomics;ClinicalMedicineInsights; Jour-nalofthePancreas;International ScholarsJournals(ISJ);CancerTherapy; Indian JournalofCriticalCareMedicineand,AfricanJournalofEnvironmentalScienceand Technology.

Figure

Fig. 1. Examples of concepts/relations hierarchies and conceptual graph.
Fig. 2. A conceptual graph for knowledge modelling in synucleinopathies.
Fig. 3. A conceptual graph for knowledge modelling in Parkinson’s disease.

Références

Documents relatifs

After this transformation, NµSMV verifies the correctness of the model written in NµSMV language with temporal logic in order to verify the consistency of the

In particular, these two spaces are seen through the following types of knowledge resources: Proc- esses, which describe actual production activities; Documents, which are

[r]

The Canvas Manager manages the CLSD Component design, the concepts and their connectors, and the collaborative tools / awareness mechanisms required (Carl

Thus, by modelling the root node or each of the blank node as an object, which contains three primitive value lists, storing subnode URIs, literal values, and blank

The aim of our article is to overcome this deciency by the suggestion of lightweight formal method for the design of user interface by the GUI modelling based on the

To do that, we design the guidelines of use; we provide techniques to facilitate the use of the method; and we develop tools (prototypes built in the laboratory) to

In this section, we suggest three extensions to the current state of the art, namely: intro- ducing new temporal relations for the construction of semantic health graphs; a flexible