以頭夾肌肉肌電圖分析實現(xiàn)重郁癥之電腦輔助診斷Part

Computer-aidDiagnosisonMajorDepressiveDisorderBasedon

EMGfromtheSplenius

CapitisMuscle

以頭夾肌肉肌電圖分析實現(xiàn)重鬱癥之電腦輔助診斷(Part2)

2010AnnualSymposiumonBiomedicalEngineeringandTechnology沈祖望Tsu-WangShen1劉芳芷Hsin-FangLi1陳紹祖WilliamShao-TsuChen21慈濟大學(xué)醫(yī)學(xué)資訊學(xué)系DepartmentofMedicalInformatics,TzuChiUniversity2花蓮慈濟醫(yī)院身心醫(yī)學(xué)科DepartmentofPsychiatry,BuddhistTzu-ChiGeneralHospitalPresenter:Tzu-YuHuangAdvisor:Dr.Yen-TingChenDate:12.29.20101Anartificialneuralnetwork(ANN)ArtificialintelligenceMathematicalmodelLearningsystemComputer-aiddiagnosisMethodsandMaterialsAnartificialneuralnetwork(ANN):類神經(jīng)網(wǎng)路2MethodsandMaterialsBackpropagationneuralnetwork(BPNN)SupervisedneuralnetworkBackpropagationneuralnetwork(BPNN):倒傳遞類神經(jīng)網(wǎng)路f1234kLf123451234abcdekLInputlayerHidden

layerOutputlayer3MethodsandMaterialsBackpropagationneuralnetwork(BPNN)Input-to-hiddenWeight

Activationfunction:

sigmoidBlue

a=2Red

a=1Green

a=0.5kLf+x4MethodsandMaterialsBackpropagationneuralnetwork(BPNN)Hidden-to-outputWeightActivationfunction:pure-linearYjhHYhjhYjHWnetq+?=f+x5MethodsandMaterialsBackpropagationneuralnetwork(BPNN)AdjustweightsOutputlayerEFHidden

layer1234abcdekLInputlayer6MethodsandMaterialsBackpropagationneuralnetwork(BPNN)Adjustweights

7MethodsandMaterialsSupportvectormachine(SVM)ClassificationStatisticsHyperplaneoptimalseparatinghyperplane(OSH)supporthyperplane

MarginOSH:最佳分割超平面Supporthyperplane:支持超平面8ResultsT.O.V.AMDD

HigheromissionratesHighermeanresponsetimesMorevariabilityEMGfeaturesMDDLowerEAandRMSvaluesHigherMFandMPFvalues9ResultsT.O.V.ACompareEMGComparisonbygroupsduringrest

GroupsMeanSDPEA(uv)MDD22.2034.840.001Control56.5953.51RMS(uv)MDD0.120.160.000Control0.280.25MDF(PSD)MDD80.407.310.000Control73.117.77MPF(PSD)MDD84.984.190.000Control80.514.14*p<0.0510ResultsT.O.V.ACompareEMGComparisonbygroupduringTOVAGroupsMeanSDPEA(uv)MDD28.4638.270.013Control65.0188.40RMS(uv)MDD0.140.180.010Control0.320.40MDF(PSD)MDD80.836.590.000Control72.796.45MPF(PSD)MDD85.223.970.000Control80.433.31*p<0.0511ResultsAccuracyAccuracyRestTOVATrainTestTrainTestBPNN92.06%76.67%87.67%76.67%SVM100%83.33%98.33%83.56%12ConclusionandDiscussionMDDbecomesmoredistinguishablewhenrestingHealthcontrolshavewiderrangeofEAandMFMDDpatientshavethelowercapabilityonphysiologicalregulationHopefully,thesystemcanbeusedtodetectandtocontroltheMDDdisorderinthefuture.13References[1]J.M.DonohueandH.A.Pincus,Reducingthesocietalburdenofdepression:areviewofeconomiccosts,qualityofcareandeffectsoftreatment,Pharmacoeconomics25(2007)7.[2]P.Sobocki,B.Jonsson,J.Angst,C.Rehnberg.CostofdepressioninEurope.JMentHealthPolicyEcon9(2006)87.[3]AmericanPsychiatricAssociation,Diagnosticandstatisticalmanualofmentaldisorders(AmericanPsychiatricAssociation,Washington,DC,2000).[4]R.C.Kessler,P.Berglund,O.Demler,R.Jin,D.Koretz,K.R.Merikangas,A.J.Rush,E.E.Walters,P.S.Wang;NationalComorbiditySurveyReplication,Theepidemiologyofmajordepressivedisorder:resultsfromtheNationalComorbiditySurveyReplication(NCS-R),JAMA289(2003)3095-105.[5]G.E.Simon,M.VonKorff,Recognitionandmanagementofdepressioninprimarycare,ArchFamMed4(1995)99-105.[6]W.KatonandP.Ciechanowski,Impactofmajordepressiononchronicmedicalillness.JPsychosom

Res53(2002)859-63.[7]E.J.Perez-Stable,J.Miranda,R.F.Munoz,Y.W.Ying,Depressioninmedicaloutpatients.Underrecognitionandmisdiagnosis,ArchInternMed.150(1990)1083-8.[8]R.M.Carney,B.A.Hong,S.Kulkarni,A.Kapila,AcomparisonofEMGandSCLinnormalanddepressedsubjects.ThePavlovianjournalofbiologicalscience,16:4(1981)212-216.[9]A.Erfanian,etal.,EvokedEMGinelectricallystimulatedmuscleandmechanismsoffatigue,inEngineeringinMedicineandBiologySociety(1994)341-342.[10]E.ParkandS.G.Meek,Fatiguecompensationoftheelectromyographicsignalforprostheticcontrolandforceestimation,BiomedicalEngineering,IEEETransactionson40(1993)1019-1023.[11]Z.K.Moussavi,etal.,TheeffectoftreatmentformyofascialtriggerpointsontheEMGfatigueparametersofshouldermuscles,EngineeringinMedicineandBiologySocietyProceedingsofthe19thAnnualInternationalConferenceoftheIEEE3(1997)1082-1085.[12]S.Haykin,NeuralNetworksandLearningMachines(3rded.):PrenticeHall(2008).[13]J.F.Greden,N.Genero,H.L.Price,Agitation-increasedelectromyogramactivityinthecorrugatormuscleregion:apossibleexplanationofthe"Omegasign"?,AmJPsychiatry142(1985)348-51.[14]S.H.Woodward,M.J.Friedman,D.L.Bliwise,Sleepanddepressionincombat-relatedPTSDinpatients,BiologicalPsychiatry39(1996)182-92.[15]L.O'Brien-Simpson,P.Di

Parsia,J.G.Simmons,