Predicting Acoustic Hearing Preservation Following Cochlear Implant Surgery Using Machine Learning
Corresponding Author
Daniel M Zeitler MD
Neuroscience Institute, Virginia Mason Franciscan Health, Seattle, Washington, USA
Department of Otolaryngology-Head Neck Surgery, Section of Otology/Neurotology, Virginia Mason Franciscan Health, Seattle, Washington, USA
Send correspondence to Daniel M. Zeitler, MD FACS, Division of Otology & Neurotology, Department of Otolaryngology-Head and Neck Surgery, Virginia Mason Franciscan Health, 1100 Ninth Avenue, Mailstop X10-ON, Seattle, WA 98101, USA. Email: [email protected]
Search for more papers by this authorQuinlan D Buchlak MD
School of Medicine, University of Notre Dame Australia, Sydney, New South Wales, Australia
Department of Neurosurgery, Monash Health, Melbourne, Victoria, Australia
Search for more papers by this authorSavindi Ramasundara BSc
School of Medicine, University of Notre Dame Australia, Sydney, New South Wales, Australia
Search for more papers by this authorFarrokh Farrokhi MD
Neuroscience Institute, Virginia Mason Franciscan Health, Seattle, Washington, USA
Department of Neurosurgery, Virginia Mason Franciscan Health, Seattle, Washington, USA
Search for more papers by this authorNazanin Esmaili PhD
School of Medicine, University of Notre Dame Australia, Sydney, New South Wales, Australia
Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, New South Wales, Australia
Search for more papers by this authorCorresponding Author
Daniel M Zeitler MD
Neuroscience Institute, Virginia Mason Franciscan Health, Seattle, Washington, USA
Department of Otolaryngology-Head Neck Surgery, Section of Otology/Neurotology, Virginia Mason Franciscan Health, Seattle, Washington, USA
Send correspondence to Daniel M. Zeitler, MD FACS, Division of Otology & Neurotology, Department of Otolaryngology-Head and Neck Surgery, Virginia Mason Franciscan Health, 1100 Ninth Avenue, Mailstop X10-ON, Seattle, WA 98101, USA. Email: [email protected]
Search for more papers by this authorQuinlan D Buchlak MD
School of Medicine, University of Notre Dame Australia, Sydney, New South Wales, Australia
Department of Neurosurgery, Monash Health, Melbourne, Victoria, Australia
Search for more papers by this authorSavindi Ramasundara BSc
School of Medicine, University of Notre Dame Australia, Sydney, New South Wales, Australia
Search for more papers by this authorFarrokh Farrokhi MD
Neuroscience Institute, Virginia Mason Franciscan Health, Seattle, Washington, USA
Department of Neurosurgery, Virginia Mason Franciscan Health, Seattle, Washington, USA
Search for more papers by this authorNazanin Esmaili PhD
School of Medicine, University of Notre Dame Australia, Sydney, New South Wales, Australia
Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, New South Wales, Australia
Search for more papers by this authorThe authors have no funding, financial relationships, or conflicts of interest to disclose.
Abstract
Objectives
The aim of the study was to train and test supervised machine-learning classifiers to predict acoustic hearing preservation after CI using preoperative clinical data.
Study Design
Retrospective predictive modeling study of prospectively collected single-institution CI dataset.
Methods
One hundred and seventy-five patients from a REDCap database including 761 patients >18 years who underwent CI and had audiometric testing preoperatively and one month after surgery were included. The primary outcome variable was the lowest quartile change in acoustic hearing at one month after CI using various formulae (standard pure tone average, SPTA; low-frequency PTA, LFPTA). Analysis involved applying multivariate logistic regression to detect statistical associations and training and testing supervised learning classifiers. Classifier performance was assessed with numerous metrics including area under the receiver operating characteristic curve (AUC) and Matthews correlation coefficient (MCC).
Results
Lowest quartile change (indicating hearing preservation) in SPTA was positively associated with a history of meningitis, preoperative LFPTA, and preoperative SPTA. Lowest quartile change in SPTA was negatively associated with sudden hearing loss, noise exposure, aural fullness, and abnormal anatomy. Lowest quartile change in LFPTA was positively associated with preoperative LFPTA. Lowest quartile change in LFPTA was negatively associated with tobacco use. Random forest demonstrated the highest mean classification performance on the validation dataset when predicting each of the outcome variables.
Conclusions
Machine learning demonstrated utility for predicting preservation of residual acoustic hearing in patients undergoing CI surgery, and the detected associations facilitated the interpretation of our machine-learning models. The models and statistical associations together may be used to facilitate improvements in shared clinical decision-making and patient outcomes.
Level of Evidence
3 Laryngoscope, 134:926–936, 2024
BIBLIOGRAPHY
- 1Blamey P, Artieres F, Başkent D, et al. Factors affecting auditory performance of postlinguistically deaf adults using cochlear implants: an update with 2251 patients. Audiol Neurootol. 2013; 18(1): 36-47.
- 2Moberly AC, Bates C, Harris MS, Pisoni DB. The enigma of poor performance by adults with cochlear implants. Otol Neurotol. 2016; 37(10): 1522-1528.
- 3Kim H, Kang WS, Park HJ, et al. Cochlear implantation in postlingually deaf adults is time-sensitive towards positive outcome: prediction using advanced machine learning techniques. Sci Rep. 2018; 8(1):18004.
- 4Crowson MG, Dixon P, Mahmood R, et al. Predicting postoperative cochlear implant performance using supervised machine learning. Otol Neurotol. 2020; 41(8): e1013-e1023.
- 5Leung J, Wang NY, Yeagle JD, et al. Predictive models for cochlear implantation in elderly candidates. Arch Otolaryngol Head Neck Surg. 2005; 131(12): 1049-1054.
- 6van Dijk JE, van Olphen AF, Langereis MC, Mens LHM, Brokx JPL, Smoorenburg GF. Predictors of cochlear implant performance. Int J Audiol. 1999; 38(2): 109-116.
10.3109/00206099909073010 Google Scholar
- 7Kiefer J, von Ilberg C, Reimer B, et al. Results of cochlear implantation in patients with severe to profound hearing loss—implications for patient selection. Audiology. 1998; 37(6): 382-395.
- 8Plant K, McDermott H, Van Hoesel R, Dawson P, Cowan R. Factors predicting postoperative unilateral and bilateral speech recognition in adult cochlear implant recipients with acoustic hearing. Ear Hear. 2016; 37(2): 153-163.
- 9Roditi RE, Poissant SF, Bero EM, Lee DJ. A predictive model of cochlear implant performance in postlingually deafened adults. Otol Neurotol. 2009; 30(4): 449-454.
- 10Holden LK, Finley CC, Firszt JB, et al. Factors affecting open-set word recognition in adults with cochlear implants. Ear Hear. 2013; 34(3): 342-360.
- 11Wanna GB, Noble JH, Carlson ML, et al. Impact of electrode design and surgical approach on scalar location and cochlear implant outcomes. Laryngoscope. 2014; 124(Suppl 6 (6)): S1-S7.
- 12Adunka OF, Dillon MT, Adunka MC, King ER, Pillsbury HC, Buchman CA. Hearing preservation and speech perception outcomes with electric-acoustic stimulation after 12 months of listening experience. Laryngoscope. 2013; 123(10): 2509-2515.
- 13Gfeller K, Turner C, Oleson J, et al. Accuracy of cochlear implant recipients on pitch perception, melody recognition, and speech reception in noise. Ear Hear. 2007; 28(3): 412-423.
- 14Dorman MF, Gifford RH, Spahr AJ, McKarns SA. The benefits of combining acoustic and electric stimulation for the recognition of speech, voice and melodies. Audiol Neurotol. 2008; 13(2): 105-112.
- 15Dunn CC, Noble W, Tyler RS, Kordus M, Gantz BJ, Ji H. Bilateral and unilateral cochlear implant users compared on speech perception in noise. Ear Hear. 2010; 31(2): 296-298.
- 16Perkins E, Lee J, Manzoor N, et al. The reality of hearing preservation in cochlear implantation: who is utilizing EAS? Otol Neurotol. 2021; 42(6): 832-837.
- 17Mamelle E, Granger B, Sterkers O, et al. Long-term residual hearing in cochlear implanted adult patients who were candidates for electro-acoustic stimulation. Eur Arch Otorhinolaryngol. 2020; 277(3): 705-713.
- 18Gifford RH, Davis TJ, Sunderhaus LW, et al. Combined electric and acoustic stimulation with hearing preservation: effect of cochlear implant low-frequency cutoff on speech understanding and perceived listening difficulty. Ear Hear. 2017; 38(5): 539-553.
- 19Shew M, New J, Wichova H, Koestler DC, Staecker H. Using machine learning to predict sensorineural hearing loss based on perilymph micro RNA expression profile. Sci Rep. 2019; 9(1):3393.
- 20Buchlak QD, Milne MR, Seah J, et al. Charting the potential of brain computed tomography deep learning systems. J Clin Neurosci. 2022; 99: 217-223.
- 21Crowson MG, Ranisau J, Eskander A, et al. A contemporary review of machine learning in otolaryngology–head and neck surgery. Laryngoscope. 2020; 130(1): 45-51.
- 22Buchlak QD, Esmaili N, Leveque JC, et al. Machine learning applications to clinical decision support in neurosurgery: an artificial intelligence augmented systematic review. Neurosurg Rev. 2020; 43(5): 1235-1253.
- 23Buchlak QD, Esmaili N, Leveque JC, Bennett C, Farrokhi F, Piccardi M. Machine learning applications to neuroimaging for glioma detection and classification: an artificial intelligence augmented systematic review. J Clin Neurosci. 2021; 89: 177-198.
- 24Montazeri M, Montazeri M, Montazeri M, Beigzadeh A. Machine learning models in breast cancer survival prediction. Technol Heal Care. 2016; 24(1): 31-42.
- 25Rahimy E. Deep learning applications in ophthalmology. Curr Opin Ophthalmol. 2018; 29(3): 254-260.
- 26Bur AM, Shew M, New J. Artificial intelligence for the otolaryngologist: a state of the art review. Otolaryngol Head Neck Surg. 2019; 160(4): 603-611.
- 27Crowson MG, Lin V, Chen JM, Chan TCY. Machine learning and cochlear implantation - a structured review of opportunities and challenges. Otol Neurotol. 2020; 41(1): E36-E45.
- 28Song Q, Qi S, Jin C, et al. Functional brain connections identify sensorineural hearing loss and predict the outcome of cochlear implantation. Front Comput Neurosci. 2022; 16:825160.
- 29Kyong JS, Suh MW, Han JJ, et al. Cross-modal cortical activity in the brain can predict cochlear implantation outcome in adults: a machine learning study. J Int Adv Otol. 2021; 17(5): 380-386.
- 30Skidmore J, Xu L, Chao X, et al. Prediction of the functional status of the cochlear nerve in individual cochlear implant users using machine learning and electrophysiological measures. Ear Hear. 2021; 42(1): 180-192.
- 31Shafieibavani E, Goudey B, Kiral I, et al. Predictive models for cochlear implant outcomes: performance, generalizability, and the impact of cohort size. Trends Hear. 2021; 25: 1-14.
- 32Tan L, Holland SK, Deshpande AK, Chen Y, Choo DI, Lu LJ. A semi-supervised support vector machine model for predicting the language outcomes following cochlear implantation based on pre-implant brain fMRI imaging. Brain Behav. 2015; 5(12): 1-25.
- 33Grimm R, Pettinato M, Gillis S, Daelemans W. Simulating speech processing with cochlear implants: how does channel interaction affect learning in neural networks? PloS One. 2019; 14(2):e0212134.
- 34Gurgel RK, Jackler RK, Dobie RA, Popelka GR. A new standardized format for reporting hearing outcome in clinical trials. Otolaryngol Head Neck Surg. 2012; 147(5): 803-807.
- 35Skarzynski H, van de Heyning P, Agrawal S, et al. Towards a consensus on a hearing preservation classification system. Acta Otolaryngol Suppl. 2013; 133(564): 3-13.
10.3109/00016489.2013.869059 Google Scholar
- 36Assmann G, Cullen P, Schulte H. Simple scoring scheme for calculating the risk of acute coronary events based on the 10-year follow-up of the prospective cardiovascular Münster (PROCAM) study. Circulation. 2002; 105(3): 310-315.
- 37Buchlak QD, Yanamadala V, Leveque JC, Edwards A, Nold K, Sethi R. The Seattle spine score: predicting 30-day complication risk in adult spinal deformity surgery. J Clin Neurosci. 2017; 43: 247-255.
- 38Stoltzfus JC. Logistic regression: a brief primer. Acad Emerg Med. 2011; 18(10): 1099-1104.
- 39Friedman JH. Greedy function approximation: a gradient boosting machine. Ann Stat. 2001; 29(5): 1189-1232.
- 40Freund Y, Schapire RE. A decision-theoretic generalization of on-line learning and an application to boosting. J Comput Syst Sci. 1997; 55(1): 119-139.
- 41Breiman L. Random forests. Mach Learn. 2001; 45: 5-32.
- 42Chang C-C, Lin C-J. LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol. 2011; 2(3): 1-27.
- 43Zhang H. The optimality of naive Bayes. In: Proceedings of the 17th International Florida Artificial Intelligence Research Society Conference. Menlo Park. 2004 562–567.
- 44Chicco D, Jurman G. The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics. 2020; 21(1): 6.
- 45Chincor N, Sundheim BM. MUC-5 evaluation metrics. In: fifth message understanding conference (MUC-5): proceedings of a confererence held in Baltimore, Maryland. Baltimore. 1993.
- 46Seabold S, Perktold J. Statsmodels: econometric and statistical modeling with python. Proc Python Sci Conf. 2010; 92-96.
10.25080/Majora-92bf1922-011 Google Scholar
- 47Jones E, Oliphant T, Peterson P. SciPy: Open Source Scientific Tools for Python. 2001.
- 48Abraham A, Pedregosa F, Eickenberg M, et al. Machine learning for neuroimaging with scikit-learn. Front Neuroinform. 2014; 21(8): 14.
- 49Hunter JD. Matplotlib: a 2D graphics environment. Comput Sci Eng. 2007; 9(3): 90-95.
- 50van der Walt S, Colbert SC, Varoquaux G. The NumPy Array: a structure for efficient numerical computation. Comput Sci Eng. 2011; 13(2): 22-30.
- 51McKinney W. Pandas: a foundational python library for data analysis and statistics. Python High Perform Sci Comput. 2011; 1-9.
- 52Buchlak QD, Esmaili N, Bennett C, Wang YY, King J, Goldschlager T. Predictors of improvement in quality of life at 12-month follow-up in patients undergoing anterior endoscopic skull base surgery. Mockridge J, ed. PloS One. 2022; 17(7):e0272147.
- 53Esmaili N, Buchlak QD, Piccardi M, Kruger B, Girosi F. Multichannel mixture models for time-series analysis and classification of engagement with multiple health services: an application to psychology and physiotherapy utilization patterns after traffic accidents. Artif Intell Med. 2021; 111:101997.
- 54Perkins EL, Labadie RF, O'Malley M, et al. The relation of Cochlear implant electrode Array type and position on continued hearing preservation. Otol Neurotol. 2022; 43(6): e634-e640.
- 55Lee G, Lee S, Chung JH, Choi JW. Preimplant hearing threshold: an important predictor of hearing preservation in cochlear implantation with lateral wall electrodes. Otol Neurotol. 2021; 42(2): e145-e152.
- 56Wanna GB, O'Connell BP, Francis DO, et al. Predictive factors for short- and long-term hearing preservation in cochlear implantation with conventional-length electrodes. Laryngoscope. 2018; 128(2): 482-489.
- 57Eshraghi AA. Prevention of cochlear implant electrode damage. Curr Opin Otolaryngol Head Neck Surg. 2006; 14(5): 323-328.
- 58Kamakura T, Nadol JB. Correlation between word recognition score and intracochlear new bone and fibrous tissue after cochlear implantation in the human. Hear Res. 2016; 339: 132-141.
- 59Rajan GP, Kuthubutheen J, Hedne N, Krishnaswamy J. The role of preoperative, intratympanic glucocorticoids for hearing preservation in cochlear implantation: a prospective clinical study. Laryngoscope. 2012; 122(1): 190-195.
- 60van Loon MC, Hensen EF, de Foer B, Smit CF, Witte B, Merkus P. Magnetic resonance imaging in the evaluation of patients with sensorineural hearing loss caused by meningitis: implications for cochlear implantation. Otol Neurotol. 2013; 34(5): 845-854.
- 61Kopelovich JC, Reiss LAJ, Etler CP, et al. Hearing loss after activation of hearing preservation cochlear implants might Be related to afferent cochlear innervation injury. Otol Neurotol. 2015; 36(6): 1035-1044.
- 62Henderson D, Bielefeld EC, Harris KC, Hu BH. The role of oxidative stress in noise-induced hearing loss. Ear Hear. 2006; 27(1): 1-19.
- 63Gul F, Muderris T, Yalciner G, et al. A comprehensive study of oxidative stress in sudden hearing loss. Eur Arch Otorhinolaryngol. 2017; 274(3): 1301-1308.
- 64Zhang C, Li Q, Chen M, Lu T, Min S, Li S. The role of oxidative stress in the susceptibility of noise-impaired cochleae to synaptic loss induced by intracochlear electrical stimulation. Neuropharmacology. 2021; 196:108707.
- 65Jimenez JE, Govil N, Shaffer AD, Ledonne JC, Chi DH. Hearing preservation with a slim modiolar cochlear implant in a pediatric cohort. Int J Pediatr Otorhinolaryngol. 2021; 140:110479.
- 66Hollis ES, Canfarotta MW, Dillon MT, et al. Initial hearing preservation is correlated with cochlear duct length in fully-inserted long flexible lateral wall arrays. Otol Neurotol. 2021; 42(8): 1149-1155.
- 67Paquette ST, Dawes RP, Sundar IK, Rahman I, Brown EB, White PM. Chronic cigarette smoke exposure drives spiral ganglion neuron loss in mice. Sci Rep. 2018; 8(1): 5746.
- 68Carlson ML, Patel NS, Tombers NM, et al. Hearing preservation in pediatric cochlear implantation. Otol Neurotol. 2017; 38(6): e128-e133.
Citing Literature
