資源描述：
《Artificial Neural Networks Improve the Accuracy of Cancer Survival Prediction》由會(huì)員上傳分享，免費(fèi)在線閱讀，更多相關(guān)內(nèi)容在學(xué)術(shù)論文-天天文庫(kù)。
1、857Arti?cialNeuralNetworksImprovetheAccuracyofCancerSurvivalPredictionHarryB.Burke,M.D.,Ph.D.1BACKGROUND.TheTNMstagingsystemoriginatedasaresponsetotheneedforPhilipH.Goodman,M.D.,M.S.2anaccurate,consistent,universalcanceroutcomepredictionsystem.SincetheDavidB.Rosen,Ph.
2、D.1TNMstagingsystemwasintroducedinthe1950s,newprognosticfactorshaveDonaldE.Henson,M.D.3beenidenti?edandnewmethodsforintegratingprognosticfactorshavebeen4developed.ThisstudycomparesthepredictionaccuracyoftheTNMstagingsystemJohnN.Weinstein,M.D.,Ph.D.FrankE.Harrell,Jr.,5
3、withthatofarti?cialneuralnetworkstatisticalmodels.Ph.D.6METHODS.For5-yearsurvivalofpatientswithbreastorcolorectalcarcinoma,JeffreyR.Marks,Ph.D.7theauthorscomparedtheTNMstagingsystem'spredictiveaccuracywiththatofDavidP.Winchester,M.D.8arti?cialneuralnetworks(ANN).Thear
4、eaunderthereceiveroperatingcharacteris-DavidG.Bostwick,M.D.ticcurve,asappliedtoanindependentvalidationdataset,wasthemeasureofaccuracy.1BioinformaticsandHealthServicesResearch,RESULTS.FortheAmericanCollegeofSurgeons'PatientCareEvaluation(PCE)DepartmentofMedicine,NewYor
5、kMedicalCol-dataset,usingonlytheTNMvariables(tumorsize,numberofpositiveregionallege,Valhalla,NewYork.lymphnodes,anddistantmetastasis),thearti?cialneuralnetwork'spredictions2DepartmentofMedicine,UniversityofNevadaofthe5-yearsurvivalofpatientswithbreastcarcinomaweresign
6、i?cantlymoreSchoolofMedicine,Reno,Nevada.accuratethanthoseoftheTNMstagingsystem(TNM,0.720;ANN,0.770;P3DivisionofCancerPreventionandControl,Na-0.001).FortheNationalCancerInstitute'sSurveillance,Epidemiology,andEndtionalCancerInstitute,Bethesda,Maryland.Resultsbreastcar
7、cinomadataset,usingonlytheTNMvariables,thearti?cial4neuralnetwork'spredictionsof10-yearsurvivalweresigni?cantlymoreaccurateDivisionofCancerTreatment,NationalCancerInstitute,Bethesda,Maryland.thanthoseoftheTNMstagingsystem(TNM,0.692;ANN,0.730;P0.01).ForthePCEcolorectal
8、dataset,usingonlytheTNMvariables,thearti?cialneural5DepartmentofHealthEvaluationSciences,network'spredictionsofthe5-yearsurv
