




版权说明:本文档由用户提供并上传,收益归属内容提供方,若内容存在侵权,请进行举报或认领
文档简介
SpecificsofMedicalDataMiningforDiagnosisAid:ASurvey
SarahItania,b,*,FabianLecronc,PhilippeFortempsc
aFundforScientificResearch-FNRS(F.R.S.-FNRS),Brussels,Belgium
bFacultyofEngineering,UniversityofMons,DepartmentofMathematicsandOperationsResearch,Mons,Belgium
cFacultyofEngineering,UniversityofMons,DepartmentofEngineeringInnovationManagement,Mons,Belgium
Abstract
Dataminingcontinuestoplayanimportantroleinmedicine;specifically,forthedevelopmentofdiagnosisaidmodelsusedinexpertandintelligentsystems.Althoughwecanfindabundantresearchonthistopic,cliniciansremainreluctanttousedecisionsupporttools.Socialpressureexplainspartlythislukewarmposition,butconcernsaboutreliabilityandcredibilityarealsoputforward.Toaddressthisreticence,weemphasizetheimportanceofthecollaborationbetweenbothdataminersandclinicians.Thissurveylaysthefoundationforsuchaninteraction,byfocusingonthespecificsofdiagnosisaid,andtherelateddatamodelinggoals.Onthisregard,weproposeanoverviewontherequirementsexpectedbytheclinicians,whoareboththeexpertsandthefinalusers.Indeed,webelievethattheinteractionwithcliniciansshouldtakeplacefromtheveryfirststepsoftheprocessandthroughoutthedevelopmentofthepredictivemodels,thusnotonlyatthefinalvalidationstage.Actually,againstacurrentresearchapproachquiteblindlydrivenbydata,weadvocatetheneedforanewexpert-awareapproach.Thissurveypaperprovidesguidelinestocontributetothedesignofdailyhelpfuldiagnosisaidsystems.
Keywords:DataMining;Medicine;DiagnosisAid;ExplainableArtificialIntelligence
1.Introduction
Asoneofthetrendiestresearchtopicsofourcentury,DataMining(DM)makeskeycontribu-tionstothescientificandtechnologicaladvanceinaconsiderablenumberoffields(
Gupta
,
2014
;
PhridviRajandGuruRao
,
2014
).Coinedduringthenineties,thedisciplineissubjecttoatoughcompetitionforthedevelopmentofalgorithmsalwaysmorepowerful,whichaimatprocessingdata
*Correspondingauthor.UniversityofMons,DepartmentofMathematicsandOperationsResearch,RuedeHoudain,9,7000Mons,Belgium.
Emailaddresses:sarah.itani@umons.ac.be(SarahItani),fabian.lecron@umons.ac.be(FabianLecron),philippe.fortemps@umons.ac.be(PhilippeFortemps)
2
Numberofpublications
1200
1000
800
600
400
200
0
199019952000200520102015
Year
Figure1:EvolutionoftheannualnumberofpublicationsrelatedtomedicaldataminingintheScopusdatabase(Sco
-
pus
)onaquarterofacentury,from1990to2015
toinfersomeknowledgeintheformofpatternsand/orrelationships(
BellazziandZupan
,
2008
).TheassociatedtechniquesarederivedfromthefieldsofbothstatisticsandMachineLearning(ML),thelatterwhichaimsatdevelopingcomputationalmethodsabletoextractgeneralizationsfromasetofdata(
Giudici
,
2005
).
MedicalapplicationsfeatureamongtheconcernsoftheDMcommunity,withasignificantin-creaseinresearchinterestoverthelastyears(seeFigure
1
).Thisinteractioncomesindifferentdisciplines(
Bellazzietal.
,
2011
):atthecellularandmolecularlevel(bioinformatics);atthetis-sueandorganlevel(imaginginformatics);atthesinglepatientlevel(clinicalinformatics);atthepopulationandsocietylevel(publichealthinformatics).
Forhalfacenturynow,diagnosispredictionhasbeenaveryactiveresearchareaofclinicalinformatics(
Wagholikaretal
.,
2012
).Inthisregard,withtheadventofDM,researchhasprogres-sivelyshiftedawayfromthestatisticalapproachlongconsideredasastandardpractice.Actually,underahypothetico-deductiveprocess,statisticalanalysesaredriventocheckahypothesisstatedbeforehandanddatasamplesarecollectedforthisspecialpurpose(
Yooetal.
,
2012
).Thisstatis-ticalapproachissurelyadaptedtoraisedifferencesbetweenpathologicalandcontrolgroups,butnottosetanindividualassessment,i.e.aclinicalexaminationpersubject.Incontrast,enrichedbyMLtechniques,DMinductivelyprocessesavoluminousamountofdata,tobothextractknowledgeanddeveloppredictivemodelsabletohelpindiagnosingpathologies(
Vieiraetal.
,
2017
;
Yooetal.
,
2012
;
BellazziandZupan
,
2008
).Insuchaprocess,statisticsmayfinditsplaceinfeatureengineer-
3
ing,beforethestageofmodelbuildingwhichismainlybasedonMLmethodsofclassificationorregression(
Esfandiarietal.
,
2014
).
Inthatrespect,itisthroughdataminingthatrecentworksweredevotedtotheearlydetectionofcancer,e.g.see
LyuandHaque
(
2018
);
Aliˇckovi´candSubasi
(
2017
);
Cichoszetal.
(
2016
);
Nahar
etal.
(
2016
);
Esfandiarietal.
(
2014
);
Krishnaiahetal.
(
2013
);
Parvinetal.
(
2013
);
Guptaetal
.(
2011
).Otherpathologies,suchascardiacandpulmonarydiseases,diabetes,hypertension,meningi-tisformbesidesasignificantpartoftheresearchformoreprecisediagnoses(
Esfandiarietal.
,
2014
).Severalpsychiatricdisorders,suchasAttentionDeficitHyperactivityDisorder(ADHD)(
Itanietal.
,
2018a
;
Abrahametal.
,
2017
;
Milhametal.
,
2012
),Alzheimer(
Papakostasetal
.,
2015
),autism(
Kos-
mickietal
.,
2015
),schizophrenia,depressionandParkinson(
Wooetal.
,
2017
)arealsotheobjectofextensiveinvestigation.
Asprobablyperceivedbymostofresearchers,andcertainlybytheauthorsofthepresentpaper,diagnosticdecisionsupportsystemsthathavebeenproposedsofararenotunanimouslyapprovedbyclinicians(
Wagholikaretal
.,
2012
).Suchsystems,andtheunderlyingpredictivemodels,arenotablyfoundasbeingfarfromthefieldreality.Itisthusmostlikelythatdataminersarenotenoughattentivetothespecificsofmedicaldiagnosticdecisionsupport.Inparticular,thoughtheDMcommunitywassensitizedaboutthedistinctivenatureofmedicalapplications(
CiosandMoore
,
2002
),thepredictiveperformanceremainspracticallythelonelyparameterwithinthescopeofdataminers,whichencouragescompetition.Thistrendhasbeenaccentuatedwiththegreateravailabilityofopenmedicaldatabases,sharedbydifferentmedicalandresearchcentersworldwide(
DiMartino
etal.
,
2017
;
Wooetal.
,
2017
;
DiMartinoetal.
,
2014
;
Esfandiarietal.
,
2014
;
Mennesetal.
,
2013
;
Ihleetal.
,
2012
;
Kerretal.
,
2012
;
Milhametal.
,
2012
;
Polineetal.
,
2012
).Someofthesedatasetswerelaunchedattheoccasionofofficialcontests,e.g.theADHD-200collection(
Milhametal.
,
2012
).Infocusingalmostexclusivelyonperformance,theseresearchworks(1)misschallengesofbetterperceivingandunderstandingtheissuespropertothemedicalfield,(2)areexposedtotheriskofyieldinginconsistentmodels,sincenotably,recentstudiesshowedthattheremaybenologicbehindthepredictionsofaccuratemodels(
Ribeiroetal.
,
2016
).
Itisourstrongconvictionthattheclinicianshavetobeinvolvedinthewholedevelopmentprocessoftheirdecisionsupportsystems.Indeed,theybringexpertiseandknowledgetocontributetointelligentandexpertsystems.Thatiswhy,inthepresentpaper,wewillshedlightuponthespecificsofmedicaldataminingfordiagnosisaidandraisetherelateddatamodelinggoals.Forsuchapurpose,wewilladdressthefollowingquestions.
4
(1)Howcandecisionsupportmodelsbemoreattractivetoclinicians?Whataretheexpressedrequirementsinthisregard?
(2)Whataretheobjectivescorrespondingtosuchrequirementsintermsofmathematicalmod-eling?
(3)Inwhatwaymedicaldata,particularlyinthiseraofopenmedicaldataproliferation,makesdataminingmorechallenging?
(4)Towhatextentarethecurrentdataminingtechniquesabletosatisfytheclinicians’needsandtohandletheparticularnatureofmedicaldatasimultaneously?
Inansweringthesequestions,weareledtodescribeacomprehensiveexpert-awareapproachwhichstandsoutfromtheexistingliterature,throughthreemaincontributionsexposedbelow.
·Becauseofthelimitedeffectivenessofsomemodels,
Karpatneetal
.(
2017
)pushforatheory-
guideddatascience.SuchDMmodelsaregroundedintheoreticalbases,inthedomainsofPhysicsandChemistrymainly.Inthecontextofmedicaldiagnosis,wecanadoptasimilarapproach,notguidedbytheory,butratherbytheexperts’domainknowledge.Ourpaperlaysthebasesforsuchanapproach,inbuildingakindofbridgebetweenboththemedicalanddataminingdomains.
·Wenotonlyexpressthattheissueofdiagnosisaidisofaparticularnature,wealsopropose
thetranslationoftheassociatedspecificsintomodelinggoals.Indeed,mostofthepapersthathaveinterestonthespecificsofthemedicaldomainhaveawidescope,andarethusnotspecificallyfocusedondiagnosis,butalsoonprognosisandmonitoringnotably,whichinvolvesthatmodelingisnotdiscussedwithenoughdepth(
BellazziandZupan
,
2008
;
Cios
andMoore
,
2002
;
Lavraˇc
,
1999
).Besides,webringamorerecentpointofviewcomparedtothepapersthatspecificallyaddressedaidedmedicaldiagnosis(
Wagholikaretal
.,
2012
;
Kononenko
,
2001
).
·WedonotprovideanoverviewofDMtechniquesandtherelatedworks;thiswaswidelyproposedinprevioussurveys(
Kalantarietal.
2018
;
Kourouetal.
2015
;
Esfandiarietal.
2014
;
Wagholikaretal
.
2012
;
Yooetal.
2012
).WeratherquestiontheexistingDMtechniques,giventhemodelinggoalsraisedfollowingtheunderstandingoftheproblemanddata.Thisallowsustoraisesomesolidfutureresearchdirections.
5
PREDIcTEDAs>
N
P
Negative(N)
TN
FP
Positive(P)
FN
TP
Figure2:Confusionmatrix
Thepaperisorganizedasfollows.Insection
2
,weexposethematerialsweconsideredtostructureandmakeoursurvey.Theresultsarepresentedinsection
3
anddiscussedinsection
4
.Finally,weconcludethisreportinsection
5
.
2.Materials
2.1.Terminology
Medicaldiagnosisistheresultofachallengingtaskwhichconsistsofcollectingandconciliatingdifferentinformation(
Donner-Banzhoffetal.
,
2017
;
HommersomandLucas
,
2016
;
Miller
,
2016
).Thelatterincludethesymptoms(subjectivedata)andthesigns(objectivedata)ofthetroubleprovidedbyclinicalexaminationsandlaboratorytests.Inquestofexplanationsforthesesymptomsandsigns,theclinicianscometotheconclusionoftheexistence/absenceofatrouble,i.e.thediagnosis.
Atestisoneamongotherelementsthatmotivatesadiagnosis(
Gordis
,
2014
;
CiosandMoore
,
2002
).Thepredictionsofaclinicaltestareofseveraltypes.Apatientwith(respectivelywithout)thediseaseDpredictedassuchisdesignatedastruepositive(resp.truenegative).Incaseofwrongpredictions,thepatientsarefalsepositivesorfalsenegativesrespectively.LetTP(resp.TN)denotethenumberofTruePositives(resp.TrueNegatives)andFP(resp.FN)thenumberofFalsePositives(resp.FalseNegatives);thesequantitiesareusuallyexposedinamatrixofconfusion(seeFigure
2
)(
Wittenetal.
,
2005
).DifferentscalarmetricsarecomputedfromTP,TN,FPandFNtoassesstheperformanceofclinicaltests;theyareexposedinTable
1
(
LalkhenandMcCluskey
,
2008
;
Akobeng
,
2007a
,
b
).Letusnotethatpositiveandnegativepredictivevaluesdependontheprevalenceofthedisease(
Akobeng
,
2007a
):theyareeasilydeducedfromtheknowledgeofsensitivityandspecificity,whicharefreefromsuchaninfluence.
Whenseveraltestsarerequiredtocheckthepresenceofamedicalcondition,thesetestsmaybeassessedgloballyintermsofnetsensitivityandnetspecificity.Thevaluesoftheseindicatorsdependonthewayinwhichthetestswereadministered,i.e.sequentiallyorsimultaneously(
Gordis
,
2014
).Figures
3
and
4
presentthemechanismsofsequentialandparalleltesting.Forillustration
6
Test2(tp2,tn2)
Positive
Test2
(tp2,tn2)
Test2
(tp2,tn2)
METRIc
DEFINITIoN
FoRMuLA
Accuracy(A)
Rateofsuccessfulpredictions
A=TP+TN
TP+FP+TN+FN
Sensitivityor
truepositiverate(tp)
>Abilitytodetectpatientswithagivendisease.
>Probabilitythatapatientwithdis-easetestspositive.
tp=
Specificityor
truenegativerate(tn)
>Abilitytodetectpatientswithoutagivendisease.
>Probabilitythatapatientwithoutdiseasetestsnegative.
tn=
PositivePredictiveValue(PPV)
Chancethatapatient,predictedashavingagivendisease,istrulyso.
PPV=
NegativePredictiveValue(NPV)
Chancethatapatient,predictedasfreefromagivendisease,istrulyso.
NPV=
Table1:Performancemetricsofscreeningtests
Negative
Test1
(tp1,tn1)
Figure3:Sequentialtesting
Positive
Negative
Test1
(tp1,tn1)
NegativeNegative
Negative
Test1
(tp1,tn1)
PositiveNegative
Positive
Figure4:Paralleltesting
7
purposes,theexamplepresentsthecaseoftwotests;theassociatedreasoningmaybegeneralizedtosituationsinvolvingmoretests.Incaseofsequentialtesting,apatientissubmittedtoanotherroundofexaminationifhe/shetestedpositive,inordertosettledefinitelyhis/hermedicalcondition.Ifthepatienttestspositivefollowingasecondroundofexamination,thesubjectisdiagnosedwiththediseaseinquestion.Thus,ifoneofbothtestspresentsanegativeresult,thepatientisconsideredasdisease-free.Theassociatednetsensitivityandspecificityareexpressedas:
tp=tp1.tp2andtn=tn1+tn2-tn1.tn2.
Incontrast,incaseofparalleltesting,apatientisconsideredasnegativeoncealltestsconfirmthisconditionsimultaneously.Inthiscase,theassociatednetspecificityandsensitivityaregivenby:
tn=tn1.tn2andtp=tp1+tp2-tp1.tp2.
Inthesamewaythatacliniciancanaskfortheopinionofanexpertconfrere,he/shecanresorttomodelsfordiagnosisaid.Theonlydifferencebetweenbothscenariosrestsontheexternalnatureofthediagnosticsupport,eitherhumanorcomputerized.Thedataofoneorseveraltest(s)arepotentialinputsfordiagnosisaidmodels.Itshouldbenotedthatnon-interpretedoutcomesoftesting(e.g.acholesterollevel,ascan)constitutethemodelinputs,andnotthevalueofthetest(s),i.e.positiveornegative.Actually,itistheroleofthepredictivemodeltodetermineapatient’smedicalconditioninoutput.
Inlightoftheforegoing,inthepresentsurvey,whatwerefertoasamodelisdifferentfromatest,thelatterbeingapotentialinputoftheformer.Amodelprovidesarecommendationofdiagnosis;atestprovidesaresultthatallows,amongotherpotentialinformation,tomakeadiagnosis.
2.2.Theknowledgediscoveryprocess
TheextractionofknowledgeforthepurposeofdiagnosisaidfitsintoaKnowledgeDiscoveryProcess(KDP).Sinceitspioneerformalizationby
Fayyadetal
.(
1996
),alternativemodelswereproposed,eitheracademically-orindustrially-minded(
KurganandMusilek
,
2006
).Inparticular,theKDPwasadaptedformedicalapplicationsandillustratedfortheissueofdiagnosisaidby
Cios
etal.
(
2007
,
2000
).Theassociatedstepsaresummarizedbelow.
UnderstandingoftheproblemTheprocessisinitiatedbytheproblemstatement,thedefini-tionoftheobjectives,andthesufficientappropriationofadomain-specificvocabulary.Obvi-
8
ously,interactionswithdomainexpertsareessential.Atthislevel,thechoiceofdataminingtechniquesispartiallyforeseengiventheexpressedrequirements.
UnderstandingofthedataThisstepconsistsofcollectingandexploringdata,i.e.observingandanalyzingtheinformation.
PreparationofthedataThecreationoftargetdatasets(
Fayyadetal
.,
1996
)involvesnotablynoiseremovalaswellascheckingthecompletenessandconsistencyofdata.Then,dataareprocessedthroughengineering,selectionandpossiblereductionofpertinentfeatures.
DataminingThisprocessreceivestheprepareddatasets,andextractsknowledge,i.e.patterns,relationships(
BellazziandZupan
,
2008
).
EvaluationofthediscoveredknowledgeTheresultsarecloselyconsidered:theyareexpectedtobringnewandinterestingelements,tobeunderstoodandtomakesense.Here,domainexpertshavetoplayanimportantroleintheirabilitytointerpretandassesstheresults.
UseofthediscoveredknowledgeItcanleadtoactiontaking,decisionmakingorsystemsde-ployment(
Fayyadetal
.,
1996
).
TheKDPisnotstrictlyaone-wayprocessasitisnotexcludedtoreconsidertheworkofpreviousstages:thisallowstoreinforcetheconsistencyoftheresults(
Ciosetal.
,
2007
).Forexample,thefinalevaluationmayaskforrefiningtheresults.Ortobetterunderstandthedata,are-understandingoftheproblemmaystrengthenthedomain-specificknowledge.
2.3.Acceptancecriteria
OnedifficultyrelatedtomedicalDMisthatitmaytargetdifferentpublicswiththeresultingnecessitytoaddressdifferentexpectations.
Actually,aDMapproachmayberequestedinthemedicalfieldbyresearchersandspecialistsinordertostudyagivenpathologythroughtheidentificationofexplanatoryfactors.Inthatcase,theextractedknowledgeisvalidatedifitcarriesacertainlevelofcredibility,measuredbymeansofcriteriarelatedtostatisticalpowernotably.Ifendorsedbythescientificcommunity,suchresultsmaybetakenintoconsideration(directlyorindirectly)bycliniciansfacedwithadiagnosistask.
Assuggestedinsection
2.2
,theextractedknowledgemayalsobedeployedintheformofacomputerizeddiagnosisaid.Despitetheyarethelonelyusersofsuchtechnologies,thecliniciansareinfluencedintheirexpectations,e.g.bythepatientswhoplacealotofhopeinafairdiagnosis.
9
Differentmodelsweredevelopedinanefforttoexplainhowaclinicianmayacceptatechnologyandintegrateittohis/herworkingpractices(
Andargolietal
.,
2017
;
Ketikidisetal.
,
2012
;
Holden
andKarsh
,
2010
;
YarbroughandSmith
,
2007
).ThemostpopularistheTechnologyAcceptanceModel(TAM),introducedby
Davisetal.
(
1989
)andrevisedby
VenkateshandDavis
(
2000
)(TAM2).Enjoyedforitsconcisestructure,themodeldepictsthepsychologicalprocesswhich,influencedbymaterialandsocialfactors,leadstotheintentionofusingacomputerizedapplicationindifferent
contexts(
YarbroughandSmith
,
2007
).
VenkateshandDavis
(
2000
)reportthattheacceptanceoftechnologyisacquiredinpracticeonceitsusefulnessandeaseofusearebothperceivedbytheuser.Moreover,theeaseofuseisoneofthefactorsinfluencingtheuser’sperceptionoftheusefulnessoftheapplication.Theperceptionofusefulnessrestsalsoonsocialfactors:thesubjectivenorm,i.e.theuser’s(professionalorprivate)surroundings’opinionregardinghis/herdecisiontoadopt(ornot)theapplication,andtheimage,i.e.thesocialstatustheapplicationprovidestotheuser(
Munetal.
,
2006
;
Chismarand
Wiley-Patton
,
2002
).
Thesubjectivenormimpactsdirectlytheintentionofuse.Thisinfluenceisexertedontheclini-cianbyhis/herpatientsbutalsobytheprofessionalenvironment.Indeed,thephysicianissensitivetotheopinionofconfreres,particularlyofreferencepeopleinthedomain,eventhoughthisopinionmaybecontrarytothephysician’sbeliefs(
Munetal.
,
2006
).Asfortheinfluenceofthepatients,thestudyof
Shafferetal.
(
2013
)showstheyoftentendtodemonizecomputerizeddiagnosticsupport.Conversely,noncomputer-assistedpracticesareperceivedasapledgeofprofessionalism;maytheclinicianresorttotheopinionofanexpertconfrereisevenperceivedasanintelligentact.Yetinbothlastcases,thecliniciansmightbasetheirdecisiononelementsprovidedintheliteratureandextractedfromaDMapproach.Thus,theinvolvementofcomputinginthediagnosticprocess,ifonlytohaveanadvice,wouldinitselfleadthephysician’simagetotakeahittowardscolleaguesand/orpatients(
Munetal.
,
2006
).
Inthepresentsurvey,wewillhighlightthespecificsofDMtodevelopdiagnosticdecisionsupportmodelswhichmeettherequirementsoftheclinicians.WewilldealwithhowtomakecomputerizeddiagnosisaidfulfillcriteriaofoutputqualityandresultsdemonstrabilityadvocatedbyTAM.Nev-ertheless,itmustberecognizedthatadoptingasuitableapproachofmodelingdoesnotguarantee
exclusivelytheacceptanceofthemodelssincesomerelatedfactors(e.g.subjectivenorm)donotfallwithinDMconcerns.
10
cKnowledgeDiscoveryProcessc
NatureofMedicalData
OverviewofDMTechniques
PerformanceEvaluation
SpecificsofMedicalDM
√
√
√
√
√√
√√
√
√
√
√
√
√
√
√
√√
Selectedtechniquesfordatamininginmedicine
Machinelearningformedicaldiagnosis:history,stateoftheartandperspective
Theuniquenessofmedicaldatamining
Predictivedatamininginclinicalmedicine:currentissuesandguidelines
Introductiontotheminingofclinicaldata
Clinicaldatamining:a
温馨提示
- 1. 本站所有资源如无特殊说明,都需要本地电脑安装OFFICE2007和PDF阅读器。图纸软件为CAD,CAXA,PROE,UG,SolidWorks等.压缩文件请下载最新的WinRAR软件解压。
- 2. 本站的文档不包含任何第三方提供的附件图纸等,如果需要附件,请联系上传者。文件的所有权益归上传用户所有。
- 3. 本站RAR压缩包中若带图纸,网页内容里面会有图纸预览,若没有图纸预览就没有图纸。
- 4. 未经权益所有人同意不得将文件中的内容挪作商业或盈利用途。
- 5. 人人文库网仅提供信息存储空间,仅对用户上传内容的表现方式做保护处理,对用户上传分享的文档内容本身不做任何修改或编辑,并不能对任何下载内容负责。
- 6. 下载文件中如有侵权或不适当内容,请与我们联系,我们立即纠正。
- 7. 本站不保证下载资源的准确性、安全性和完整性, 同时也不承担用户因使用这些下载资源对自己和他人造成任何形式的伤害或损失。
最新文档
- 消息主体的写作新闻宣传文书50课件
- 胸痛病人健康教育
- 地理-西亚课件-2024-2025学年七年级地理下学期(人教版2024)
- 2025年农村消费金融市场拓展与业务布局策略分析报告
- Q/GYKB-BJSP 0001-2023保健食品流通服务评价技术规范第1部分:杜仲叶胶囊
- 气切的护理及注意事项
- 浅谈糖尿病的饮食护理毕业答辩
- 肾上腺皮质功能减退的护理
- 大班活动:我的牙齿
- 人文素养课件
- 2023年科技特长生招生考试试卷
- 超声波清洗机日常点检表
- 无刷双馈电机的功率因数控制
- 公司员工借款合同
- 国家开放大学《财务管理#》章节测试参考答案
- 记账凭证的填制方法和要求教案
- 光伏电站组件清洗方案说明
- DL-T 2226-2021 电力用阀控式铅酸蓄电池组在线监测系统技术条件
- GB/T 5650-1985扩口式管接头空心螺栓
- GB/T 39239-2020无损检测超声检测不连续的特征和定量
- GB/T 24610.1-2019滚动轴承振动测量方法第1部分:基础
评论
0/150
提交评论