基于機(jī)器學(xué)習(xí)的人工耳蝸植入術(shù)后兒童聽覺言語(yǔ)康復(fù)效果預(yù)測(cè)模型研究（附講解視頻

打開文本圖片集

中圖分類號(hào) R764.5 文獻(xiàn)標(biāo)識(shí)碼 A 文章編號(hào) 2096-7721（2025）04-0655-06

Prediction model based on machine learning for auditory and speech rehabilitation outcomes in children after cochlear implantation （with explanatory video）

BAI Jie，LI Ying， JIN Xin， YAN Meiling， LIU Haihong （DepartmentofOtolaryngogHeadandNeckSurgeryeingCdren’sHospital，CapitalMdicalUiversitNatioalCtefr Children'sHealth，Beijing10oo45，China）

AbstractObjective：To exploretheaplicationof machine learming techniques inpredictingauditoryand speech rehabilitation outcomesforchildrenaftercochlearimplantation.Methods：187childrenwhounderwentcochlearimplantationatBeijingChildren’s HospitalAfiliatedtoCapitalMedicalUniversityfromJanuaryO12toOctober2O24wereselectedDatafromheparents’evaluation ofauraloralpforaeofdenuestoirendcalincatosrecoltedatvicectiatiod1，，6d 36 monthsafteractivation.Machinelearningalgorithms （Support VectorMachine，RandomForest，andArtificialNeuralNetwork） wereused toconstructpredictionmodels，withfeatureselectionmethodsidentifyingkeyfactors influencingrehablitationoutcomes. Results：Theacuracyof predictionmodelsconstructedbyArtificialNeuralNetwork，RandomForest，and Support VectorMachine were 7 4 . 9 1 % 7 1 . 0 2 % ，and 6 8 . 2 0 % ，respectively.Feature selection revealed 7 significant predictors （ P <0.05）： usage time of CI， age at activation，ucaalveofayiidclaontlaalitydiid Conclusion：Machinelearing techniquescanefectivelypredictauditoryandspeechrehabilitationoutcomesinchildrenaftercochlear implantationhichprovidesanoveltolandtheoreticalsupportforpreciseclincalassessmentandpersonalzedinteetio. KeyWords Cochlear Implant； Machine Learning；Aural and Oral Performance； Children

世界衛(wèi)生組織在《世界聽力報(bào)告》中指出，全球超過15億人存在一定程度的聽力損失，其中至少4.3億人需要專業(yè)的聽力康復(fù)進(jìn)行干預(yù)。（剩余8311字）