目的：探讨机器学习技术在人工耳蜗（CI）植入术后儿童听觉言语康复效果预测中的应用。方法：选取 2012 年 1 月— 2024 年 10 月首都医科大学附属北京儿童医院行 CI 植入术的 187 例儿童，收集其在开机时及开机后第 1、3、6、12、24、36 个月 的父母评估儿童听说能力表现问卷数据及临床相关指标。运用机器学习算法（支持向量机、随机森林和人工神经网络）进行建模， 并利用特征选择方法筛选影响听觉言语康复效果的重要影响因素。结果：人工神经网络、随机森林和支持向量机三种机器学习 方法构建预测模型的准确率分别为 74.91%、71.02%、68.20%。经特征筛选，CI 使用时间、开机月龄、性别、主要看护人受教 育程度、居住地、干预方式、术前助听器使用史共 7 个特征具有显著性（P<0.05）。结论：机器学习技术可有效预测 CI 植入 术后儿童听觉言语康复效果，为临床精准评估和个性化干预提供了新的工具与理论支持。

Objective: To explore the application of machine learning techniques in predicting auditory and speech rehabilitation outcomes for children after cochlear implantation. Methods: 187 children who underwent cochlear implantation at Beijing Children’s Hospital Affiliated to Capital Medical University from January 2012 to October 2024 were selected. Data from the parents’ evaluation of aural/oral performance of children questionnaire and clinical indicators were collected at device activation and 1, 3, 6, 12, 24, and 36 months after activation. Machine learning algorithms (Support Vector Machine, Random Forest, and Artificial Neural Network) were used to construct prediction models, with feature selection methods identifying key factors influencing rehabilitation outcomes. Results: The accuracy of prediction models constructed by Artificial Neural Network, Random Forest, and Support Vector Machine were 74.91%, 71.02%, and 68.20%, respectively. Feature selection revealed 7 significant predictors (P<0.05): usage time of CI, age at activation, gender, educational level of primary caregiver, residence location, cochlear implant laterality, and preoperative hearing aid use. Conclusion: Machine learning techniques can effectively predict auditory and speech rehabilitation outcomes in children after cochlear implantation, which provides a novel tool and theoretical support for precise clinical assessment and personalized intervention.

基金项目：国家重点研发计划项目（2023YFF1203504）；北京市自然科学基金（7232059）；高层次公共卫生技术人才建设专项（2022-3-016） 

Foundation Item: National Key R & D Plan Project of China (2023YFF1203504); Natural Science Foundation of Beijing (7232059); Highlevel Public Health Technical Personnel Construction Project(2022-3-016) 

引用格式：白杰，李颖，金欣，等 . 基于机器学习的人工耳蜗植入术后儿童听觉言语康复效果预测模型研究（附讲解视频）[J]. 机器人外科 学杂志（中英文），2025，6（4）：655-659，666. 

Citation: BAI J, LI Y, JIN X, et al. Prediction model based on machine learning for auditory and speech rehabilitation outcomes in children  after cochlear implantation (with explanatory video) [J]. Chinese Journal of Robotic Surgery, 2025, 6(4): 655-659, 666. 

通讯作者（Corresponding Author）：刘海红（LIU Haihong），Email：haihongliu6@aliyun.com

[1] World Health Organization. World report on hearing[R/OL]. Geneva: WHO, 2021[2021-04-30]. https: //www.who.int/publications/i/item/worldreport-on-hearing. 

[2] Olusanya B O, Neumann K J, Saunders J E. The global burden of disabling hearing impairment: a call to action[J]. Bull World Health Organ, 2014, 92(5): 367-373. 

[3] Nordvik Ø, Laugen Heggdal P O, Brännström J, et al. Generic quality of life in persons with hearing loss: a systematic literature review[J]. BMC Ear Nose Throat Disord, 2018. DOI: 10.1186/s12901-018-0051-6. 

[4] Shield B. Evaluation of the social and economic costs of hearing impairment[R/OL]. A report for Hear, 2006[2021-04-30]. https: //www. hear-it.org/de/multimedia/Hear_It_Report_October_2006.pdf. 

[5] Carlyon R P, Goehring T. Cochlear implant research and development in the twenty-first century: a critical update [J]. Journal of the Association for Research in Otolaryngology: JARO, 2021, 22(5): 481-508. 

[6] Cosetti K, Waltzman S B. Outcomes in cochlear implantation: variables affecting performance in adults and children [J]. Otolaryngologic Clinics of North America, 2012, 45(1): 155-171. 

[7] Frosolini A, Franz I, Caragli V, et al. Artificial intelligence in audiology: a scoping review of current applications and future directions [J]. Sensors (Basel), 2024, 24(22): 7126. 

[8] Beam A L, Drazen J M, Kohane I S, et al. Artificial intelligence in medicine [J]. The New England Journal of Medicine, 2023, 388(13): 1220-1221. 

[9] 魏兴梅 , 薛书锦 , 高振橙 , 等 . 人工智能在人工耳蜗植入中的应用 [J]. 首都医科大学学报 , 2024, 45(6): 931-937. 

[10] 郭倩倩 , 陈雪清 , 孟超 , 等 . 常用听觉能力评估问卷临床应用比较 [J]. 中国耳鼻咽喉头颈外科 , 2018, 25(9): 485-489. 

[11] Ching T Y, Hill M. The Parents’ Evaluation of Aural/Oral Performance of Children (PEACH) scale: normative data [J]. Journal of the American Academy of Audiology, 2007, 18(3): 220-235. 

[12] 中华耳鼻咽喉头颈外科杂志编辑委员会 , 中华医学会耳鼻咽喉头 颈外科学分会 , 中国残疾人康复协会听力语言康复专业委员会 . 人 工耳蜗植入工作指南 (2013) [J]. 中华耳鼻咽喉头颈外科杂志 , 2014, 49(2): 89-95.

[13] Shafieibavani E, Goudey B O, Kiral I, et al. Predictive models for cochlear implant outcomes: performance, generalizability, and the impact of cohort size[J]. Trends in Hearing, 2021. DOI: 10.1177/23312165211066174. 

[14] Wilson B S, Tucci D L, Moses D A, et al. Harnessing the power of artificial intelligence in otolaryngology and the communication sciences [J]. Journal of the Association for Research in Otolaryngology: JARO, 2022, 23(3): 319-349. 

[15] Carlson M L, Carducci V, Deep N L, et al. AI model for predicting adult cochlear implant candidacy using routine behavioral audiometry [J]. American Journal of Otolaryngology, 2024, 45(4): 104337. 

[16] LU S, XIE J, WEI X, et al. Machine learning-based prediction of the outcomes of cochlear implantation in patients with cochlear nerve deficiency and normal cochlea: a 2-year follow-up of 70 children[J]. Frontiers in Neuroscience, 2022. DOI: 10.3389/fnins.2022.895560. 

[17] Feng G, Ingvalson E M, Grieco-calub T M, et al. Neural preservation underlies speech improvement from auditory deprivation in young cochlear implant recipients [J]. National Academy of Sciences (US), 2018, 115(5): E1022-E1031. 

[18] Tan L, Holland S K, Deshpande A K, et al. A semi-supervised support vector machine model for predicting the language outcomes following cochlear implantation based on pre-implant brain fMRI imaging [J]. Brain and Behavior, 2015, 5(12): e00391. 

[19] WENG J, XUE S, WEI X, et al. Machine learning-based prediction of the outcomes of cochlear implantation in patients with inner ear malformation [J]. European Federation of Oto-Rhino-Laryngological Societies, 2024, 281(7): 3535-3545. 

[20] Black J, Hickson L, Black B, et al. Prognostic indicators in paediatric cochlear implant surgery: a systematic literature review[J]. Cochlear Implants International, 2011, 12(2): 67-93. 

[21] Wieringen A V, Wouters J. What can we expect of normally-developing children implanted at a young age with respect to their auditory, linguistic and cognitive skills? [J]. Hearing Research, 2015. DOI: 10.1016/ j.heares.2014.09.002. 

[22] 冀飞 , 郗昕 , 洪梦迪 , 等 . 语前聋人工耳蜗植入患者听觉和言语康复 效果的问卷分级评估 [J]. 中华耳鼻咽喉科杂志 , 2004, (10): 12-16. 

[23] Goehring T, Bolner F, Monaghan J J, et al. Speech enhancement based on neural networks improves speech intelligibility in noise for cochlear implant users[J]. Hearing Research, 2017. DOI: 10.1016/ j.heares.2016.11.012. 

[24] Gajeck T, Nogueira W A. Fused deep denoising sound coding strategy for bilateral cochlear implants [J]. IEEE Transactions on Bio-medical Engineering, 2024, 71(7): 2232-2242. 

[25] Wathour J, Govaerts P J, DeggouJ N. From manual to artificial intelligence fitting: two cochlear implant case studies[J]. Cochlear Implants Int, 2020, 21(5): 299-305.