A Contemporary Review of Machine Learning in Otolaryngology–Head and Neck Surgery Matthew G. Crowson, MD, FRCSC ; Jonathan Ranisau, BASc; Antoine Eskander, MD, ScM, FRCSC; Aaron Babier, BSc, MASc; Bin Xu, MDCM, PhD, FRCPC; Russel R. Kahmke, MD, MMCi; Joseph M. Chen, MD, FRCSC; Timothy C. Y. Chan, PhD One of the key challenges with big data is leveraging the complex network of information to yield useful clinical insights. The confluence of massive amounts of health data and a desire to make inferences and insights on these data has produced a sub- stantial amount of interest in machine-learning analytic methods. There has been a drastic increase in the otolaryngology literature volume describing novel applications of machine learning within the past 5 years. In this timely contemporary review, we provide an overview of popular machine-learning techniques, and review recent machine-learning applications in otolaryngology–head and neck surgery including neurotology, head and neck oncology, laryngology, and rhinology. Investiga- tors have realized significant success in validated models with model sensitivities and specificities approaching 100%. Chal- lenges remain in the implementation of machine-learning algorithms. This may be in part the unfamiliarity of these techniques to clinician leaders on the front lines of patient care. Spreading awareness and confidence in machine learning will follow with further validation and proof-of-value analyses that demonstrate model performance superiority over established methods. We are poised to see a greater influx of machine-learning applications to clinical problems in otolaryngology–head and neck surgery, and it is prudent for providers to understand the potential benefits and limitations of these technologies. Key Words: Machine learning, artificial intelligence, neural networks, neurotology, head and neck oncology, laryngology, and rhinology. Laryngoscope, 00:1–7, 2019 INTRODUCTION The confluence of massive amounts of health data and a desire to make inferences and generate insights on these data has produced a substantial amount of interest in machine learning. Machine learning is a subset of arti- ficial intelligence that is concerned with prediction in novel situations from previous observations. Widely cited applications of machine learning in medicine include enhanced cancer diagnosis and prognosis prediction inte- grating clinical and genomic data, and adaptive clinical trial designs. 1–4 Another promising application includes computer vision algorithms that enable the rapid identifi- cation of radiographic anomalies, delineation of surgical anatomy, and classification of malignant tissues in patho- logic specimens (e.g., intraoperative frozen sections, fine- needle aspirate samples) at a speed comparable to if not better than human operators. 5–8 Otolaryngology–head and neck surgery is the oldest subspecialization in medicine, and harbors unique oppor- tunities for where modern machine-learning technologies show potential. 9 Amongst the earliest reports of machine learning applied to clinical topics within otolaryngology– head and neck surgery include automatic recognition of auditory brainstem response waveforms, genomic predic- tion of oral squamous cell carcinoma, and acoustic voice feature classification. 10–12 Since then, there has been a drastic increase in the otolaryngology literature volume describing novel applications of machine learning (Fig. 1). Given the rapid application and advances in machine learning for healthcare datasets, it is prudent for otolaryn- gologists and head and neck surgeons to have a working understanding of the capabilities and limitations of these analytic tools. Moreover, clinicians are uniquely posi- tioned to orient analyses toward the right questions, and occupy a key role on interdisciplinary teams as data-driven approaches to health data challenges are designed. The goal of this contemporary review was to provide an accessible overview of popular machine-learning tech- niques, and review recent machine-learning applications to otolaryngology–head and neck surgery. PRIMER ON MACHINE LEARNING Artificial intelligence (AI) is a diverse set of technolo- gies that aim to automate human intellectual processes From the Department of Otolaryngology–Head and Neck Surgery (M.G.C., A.E., J.M.C.) and Department of Pathology (B.X.), Sunnybrook Health Sciences Center, Toronto, Ontario, Canada; Department of Mechanical and Industrial Engineering (J.R., A.B., T.C.Y.C.), University of Toronto, Toronto, Ontario, Canada; Institute for Clinical Evaluative Sciences (A.E.), Toronto, Ontario, Canada; and the Division of Otolaryngology–Head and Neck Surgery (R.R.K.), Duke University Medical Center, Durham, North Carolina, U.S.A. Editor’s Note: This Manuscript was accepted for publication on January 11, 2019. The authors have no funding, financial relationships, or conflicts of interest to disclose. Send correspondence to Matthew G. Crowson, MD, Sunnybrook Health Sciences Center, 2075 Bayview Ave, Toronto, Ontario M4N 3M5, Canada. E-mail: matt.crowson@mail.utoronto.ca DOI: 10.1002/lary.27850 Laryngoscope 00: 2019 Crowson et al.: Machine Learning in Otolaryngology 1 The Laryngoscope © 2019 The American Laryngological, Rhinological and Otological Society, Inc.