前庭导水管综合征儿童声能传递特点及机器学习模型构建  

Wideband acoustic immittance characteristics and machine learning-based diagnostic model for children with large vestibular aqueduct syndrome

作　　者：木怡 蒋雯 林欢 岳昱宏 乔月华 刘稳 MU Yi;JIANG Wen;LIN Huan;YUE Yuhong;QIAO Yuehua;LIU Wen(The Otolaryngology Department of the Affiliated Hospital of Xuzhou Medical University,Xuzhou,221000,China;The Medical Technology College of Xuzhou Medical University;Jiangsu Artificial Hearing Engineering Laboratory;The Second Clinical Medical College of Xuzhou Medical University)

机构地区：[1]徐州医科大学附属医院耳鼻咽喉科,江苏徐州221000 [2]徐州医科大学医学技术学院 [3]江苏省人工听觉工程实验室 [4]徐州医科大学第二临床医学院

出　　处：《临床耳鼻咽喉头颈外科杂志》2024年第3期207-211,216,共6页Journal of Clinical Otorhinolaryngology Head And Neck Surgery

基　　金：江苏省研究生科研与实践创新计划项目(No:KYCX23_2940)。

摘　　要：目的探讨大前庭导水管综合征(large vestibular aqueduct syndrome,LVAS)儿童的声能传递特点,以及基于宽频声导抗(wideband acoustic immittance,WAI)和机器学习(machine learning,ML)技术的LVAS诊断模型构建。方法回顾性分析38例(76耳)LVAS儿童和44例(88耳)听力正常儿童的病史、听力检查、颞骨CT扫描和WAI测试结果。对WAI可解释变量进行统计分析,并构建多变量诊断模型。结果2组在耳别、性别、年龄等因素上差异均无统计学意义(P>0.05)。LVAS组在1000~2519 Hz的吸收率显著低于对照组,而在4000~6349 Hz的吸收率显著高于对照组(P<0.05)。WBA在5039 Hz的环境压力下具有一定的诊断价值(AUC=0.767)。多变量诊断模型具有较高的诊断价值(AUC>0.8),其中K-Nearest Neighbor(KNN)模型表现最佳(AUC=0.961)。结论LVAS儿童的声能传递特点与正常儿童有显著差异,基于WAI和ML技术的诊断模型具有较高的准确性和可靠性,为WAI测试的智能化诊断提供了新思路和方法。Objective This study was to investigate the wideband acoustic immittance(WAI)characteristics of children with large vestibular aqueduct syndrome(LVAS)and to construct a diagnostic model for LVAS based on WAI and machine learning(ML)techniques.Methods We performed a retrospective analysis of the data from 38 children(76 ears)with LVAS and 44 children(88 ears)with normal hearing.The data included conventional audiological examination,temporal bone CT scan and WAI test.We performed statistical analysis and developed multivariate diagnostic models based on different ML techniques.Results The two groups were balanced in terms of ear,gender,and age(P>0.05).The wideband absorbance(WBA)of the LVAS group was significantly lower than that of the control group at 1000-2519 Hz,while the WBA of the LVAS group was significantly higher than that of the control group at 4000-6349 Hz(P<0.05).WBA at 5039 Hz under ambient pressure had a certain diagnostic value(AUC=0.767).The multivariate diagnostic model had a high diagnostic value(AUC>0.8),among which the KNN model performed the best(AUC=0.961).Conclusion The WAI characteristics of children with LVAS are significantly different from those of normal children.The diagnostic model based on WAI and ML techniques has high accuracy and reliability,and provides new ideas and methods for intelligent diagnosis of LVAS.

关 键 词：大前庭导水管综合征 宽频声导抗 机器学习 

分 类 号：R322.9[医药卫生—人体解剖和组织胚胎学]