基于纯音听力曲线的夸大聋与噪声聋分类识别及关键特征分析的机器学习方法研究
A study on machine learning methods for classifying and identifying exaggerated deafness and noise-induced deafness based on pure tone audiograms and analyzing key features
姜博;王星;王建新
1:中国人民大学应用统计科学研究中心
2:中国听力医学发展基金会噪声防控专委会
3:北京绿创声学工程股份有限公司
4:中国人民大学统计学院
摘要关键词基金项目(Foundation):作者参考文献[1] 全国信息与文献标准化技术委员会.职业性噪声聋的诊断：GBZ 49-2014[S].北京：中国标准出版社，2014:1-3.
[2] 王建新，康庄，高建华.《职业性噪声聋诊断标准》的修订[J].中华劳动卫生职业病杂志，2008,26(3):181-183.
[3] 冯鸿义，燕梅.一起群体夸大性职业性噪声聋诊断鉴定案例分析[J].中国工业医学杂志，2014,27(4):315-316.
[4] 郑倩玲，刘移民，杨爱初，等.246例疑似职业性听力损伤的临床诊断分析[J].中国热带医学，2007,7(11):2039-2041.
[5] 吴东燕，陈贤明.伪聋及夸大性耳聋患者听力检查的护理分析[J].南方护理学报，2004,11(1):30-31.
[6] 曹永茂.非器质性听力损失的评估.见：刘博.诊断听力学[M].北京：人民卫生出版社，2022:227-232.
[7] 姜泗长，顾瑞.临床听力学(第二版)[M].北京：北京医科大学中国协和医科大学联合出版社，1999:400-406.
[8] 朱卫元，刘凡，仇海华，等.法医学中伪聋鉴定的常用方法[J].医药卫生科技，2012,18(24):4178-4180.
[9] 何兴丽，冉文婧，王永义，等.主客观听力检测相关性研究进展[J].中国工业医学杂志，2017,30(1):29-32.
[10] 姜晓琴，顾明华，章敏华.客观听力组合测试在噪声聋诊断中鉴别伪聋和夸大性聋的应用初探[J].中国工业医学杂志，2017,30(1):73-76.
[11] CRUICKSHANKS K J,NONDAHL D M,FISCHER M E,et al.A novel method for classifying hearing impairment in epidemiological studies of aging:the wisconsin age-related hearing impairment classification scale[J].Am J Audiol,2020,29(1):59-67.
[12] 张华.听力师职业资格考试培训教材[M].北京：人民卫生出版社，2019:113-114.
[13] MUSIBA Z.Classification of audiograms in the prevention of noise-induced hearing loss:a clinical perspective[J].S Afr J Commun Disord,2020,67(2):e1-e5.
[14] SONG X D,WALLACE B M,GARDNER J R,et al.Fast,continuous audiogram estimation using machine learning[J].Ear and Hearing,2015,36(6):E326-E35.
[15] DOU Z,LI Y,DENG D,et al.Pure tone audiogram classification using deep learning techniques[J].Clin Otolaryngol,2024,49(5):595-603.
[16] CROWSON M G,LEE J W,HAMOUR A,et al.AutoAudio:deep learning for automatic audiogram interpretation[J].J Med Syst,2020,44(9):163.
[17] RAJA SANKARI V M,SNEKHALATHA U,RAJALAKSHMI T.Design and implementation of a portable automated audiometer for hearing classification using machine learning approaches[J].Biomed Eng Appl Basis Commun,2022,34(5):2250035.
[18] ELKHOULY A,ANDREW A M,RAHIM H A,et al.Data-driven audiogram classifier using data normalization and multi-stage feature selection[J].Sci Rep,2023,13(1):1854.
[19] ZHAO Y,LI J,ZHANG M,et al.,Machine learning models for the hearing impairment prediction in workers exposed to complex industrial noise:a pilot study[J].Ear Hear,2019,40(3):690-699.
[20] 王建新.职业性噪声聋诊断标准的正确理解和实施[J].职业卫生与应急救援，2008,26(3):132-135.
[21] CHARIH F.Machine learning in audiology:applications and implications[D].Ottawa,Ontario:Carleton University,2018.
[22] 宁津，苏彦祥.职业性噪声聋发病机制及防治的研究进展[J].黑龙江医学，2023,47(24):3066-3069.
[23] HARO S,SMALT C J,CICCARELLI G A,et al.Deep neural network model of hearing-impaired speech-in-noise perception[J].Frontiers in Neuroscience,2020,14:588448.