ENTtoday
  • Home
  • COVID-19
  • Practice Focus
    • Allergy
    • Facial Plastic/Reconstructive
    • Head and Neck
    • Laryngology
    • Otology/Neurotology
    • Pediatric
    • Rhinology
    • Sleep Medicine
  • Departments
    • Issue Archive
    • TRIO Best Practices
      • Allergy
      • Facial Plastic/Reconstructive
      • Head and Neck
      • Laryngology
      • Otology/Neurotology
      • Pediatric
      • Rhinology
      • Sleep Medicine
    • Career Development
    • Case of the Month
    • Everyday Ethics
    • Health Policy
    • Legal Matters
    • Letter From the Editor
    • Medical Education
    • Online Exclusives
    • Practice Management
    • Resident Focus
    • Rx: Wellness
    • Special Reports
    • Tech Talk
    • Viewpoint
    • What’s Your O.R. Playlist?
  • Literature Reviews
    • Allergy
    • Facial Plastic/Reconstructive
    • Head and Neck
    • Laryngology
    • Otology/Neurotology
    • Pediatric
    • Rhinology
    • Sleep Medicine
  • Events
    • Featured Events
    • TRIO Meetings
  • Contact Us
    • About Us
    • Editorial Board
    • Triological Society
    • Advertising Staff
    • Subscribe
  • Advertise
    • Place an Ad
    • Classifieds
    • Rate Card
  • Search

Artificial Intelligence and Machine Learning in Otolaryngology

February 6, 2019

  • Tweet
  • Email
Print-Friendly Version
The figure shows how AI can be implemented to support otolaryngology practices. A large amount of data is generated from clinical interactions (e.g., office visits, imaging studies, surgeries, pathology), which can then be used to build machine learning algorithms, which can in turn be used to provide clinical decision support. © Graphic by Selina Zapata Bur

(click for larger image) The figure shows how AI can be implemented to support otolaryngology practices. A large amount of data is generated from clinical interactions (e.g., office visits, imaging studies, surgeries, pathology), which can then be used to build machine learning algorithms, which can in turn be used to provide clinical decision support.

You Might Also Like

  • Mayo Clinic Maximizes Learning Through Social Media
  • COSM14: Case-Based Learning May Improve Medical Education
  • Adapt Medical School Curriculum to Residents’ Learning Style
  • Multispecialty Collaboration: Learning from Our Past to Shape Our Future
Explore This Issue
February 2019

© Graphic by Selina Zapata Bur

Applying AI and ML

AI relies on using large amounts of patient data to make accurate predictions, but because ML algorithms have no inherent knowledge about otolaryngology, they need data to “learn” to make predictions, Dr. Bur said. The amount of data required depends on several factors, including the problem’s complexity and the type of learning algorithm. The more data that is available, the better the ML will perform.

By analyzing how similar patients have responded to past treatments, machine learning can provide information based on many more patient experiences than any individual physician could incorporate into their medical decision making —Andrés Bur, MD

Elizabeth A. Blair, MD, professor of surgery in the section of otolaryngology-head and neck surgery at the University of Chicago, pointed out that using AI and ML requires the input and acumen of expert clinicians to determine where gaps exist and what information would help physicians. This could assist physicians in selecting the type of treatment for patients, finding alternative therapies that could be effective, or predicting and determining if they are at increased risk for complications for a certain treatment.

Dr. Moberly said some in radiology and pathology have considered the physician’s future role to be an “information specialist” responsible for managing the information extracted by AI in the clinical context of the patient (JAMA. 2016;316(22):2353-2354). In a field such as otolaryngology, however, the physician will need to remain much more than an information specialist; AI should be an aid to the physician, not a substitute (JAMA Otolaryngol Head Neck Surg. 2014;140:191).

Dr. Friedland agreed. “AI and ML will serve as another way to provide clinical information, but won’t replace physicians,” he said. “Physicians already integrate the results of radiographs, audiograms, and blood tests into the clinical picture to help formulate a diagnosis. AI will similarly provide more information to aid in such decision making.”

Possible Drawbacks

Despite its potential, AI raises new ethical concerns that remain unanswered. First, AI development and clinical implementation requires large amounts of patient data. How should the privacy of patient information be weighed against the need to leverage this data for medical innovation? Secondly, bias in the data used to train ML algorithms produces bias in the decisions of the algorithms themselves. How can we ensure that AI is generalizable and safe for all patients? And lastly, if medical decision making shifts from physicians to intelligent machines, how will the relationship between otolaryngologists and their patients change? Along these same lines, who is responsible when an AI system causes patient harm?

Another concern is that technology expansion of the kind that will occur through the use of AI and ML approaches can drive a wedge between patients and physicians (JAMA Otolaryngol Head Neck Surg. 2014;140:191). “They can’t serve as a replacement for careful history-taking and a physical exam,” Dr. Moberly said. “Astute clinicians are adept at considering the whole patient’s picture, which could be missed by relying solely on objective data points plugged into an AI algorithm. As in other medicine fields, it is essential to properly evaluate AI as well as appropriately train users.”

Pages: 1 2 3 4 | Single Page

Filed Under: Features, Home Slider Tagged With: artificial intelligence, machine learningIssue: February 2019

You Might Also Like:

  • Mayo Clinic Maximizes Learning Through Social Media
  • COSM14: Case-Based Learning May Improve Medical Education
  • Adapt Medical School Curriculum to Residents’ Learning Style
  • Multispecialty Collaboration: Learning from Our Past to Shape Our Future

The Triological SocietyENTtoday is a publication of The Triological Society.

The Laryngoscope
Ensure you have all the latest research at your fingertips; Subscribe to The Laryngoscope today!

Laryngoscope Investigative Otolaryngology
Open access journal in otolaryngology – head and neck surgery is currently accepting submissions.

Classifieds

View the classified ads »

TRIO Best Practices

View the TRIO Best Practices »

Top Articles for Residents

  • Do Training Programs Give Otolaryngology Residents the Necessary Tools to Do Productive Research?
  • Why More MDs, Medical Residents Are Choosing to Pursue Additional Academic Degrees
  • What Physicians Need to Know about Investing Before Hiring a Financial Advisor
  • Tips to Help You Regain Your Sense of Self
  • Should USMLE Step 1 Change from Numeric Score to Pass/Fail?
  • Popular this Week
  • Most Popular
  • Most Recent
    • The Dramatic Rise in Tongue Tie and Lip Tie Treatment
    • Vertigo in the Elderly: What Does It Mean?
    • Experts Delve into Treatment Options for Laryngopharyngeal Reflux
    • Weaning Patients Off of PPIs
    • Some Laryngopharyngeal Reflux Resists PPI Treatment
    • Vertigo in the Elderly: What Does It Mean?
    • New Developments in the Management of Eustachian Tube Dysfunction
    • Some Laryngopharyngeal Reflux Resists PPI Treatment
    • Eustachian Tuboplasty: A Potential New Option for Chronic Tube Dysfunction and Patulous Disease
    • The Dramatic Rise in Tongue Tie and Lip Tie Treatment
    • Did You Receive COVID-19 Relief? Here Are Reporting Considerations for 2021
    • Otolaryngology Experts Share Best Practices in Five Areas
    • How Climate Change May Be Affecting Sleep Patterns for Adults and Children
    • Laryngologists Discuss Tough Tracheostomy Choices During COVID-19 Era
    • Head and Neck Cancer: Experts Discuss How to Improve Surgery Quality and Value

Polls

Did you receive funding from the CARES Act or Paycheck Protection Program?

View Results

Loading ... Loading ...
  • Polls Archive
  • Home
  • Contact Us
  • Advertise
  • Privacy Policy
  • Terms of Use

Visit: The Triological Society • The Laryngoscope • Laryngoscope Investigative Otolaryngology

Wiley
© 2021 The Triological Society. All Rights Reserved.
ISSN 1559-4939

loading Cancel
Post was not sent - check your email addresses!
Email check failed, please try again
Sorry, your blog cannot share posts by email.
This site uses cookies: Find out more.