AI for Doctors / Practical / ENT (Otorhinolaryngology)

AI in ENT (Otorhinolaryngology)

ENT AI is spread across subspecialties: ear imaging and otoscopy, hearing devices, endoscopy, voice analysis and head and neck cancer imaging. An AI otoscope for eardrum bulging has FDA authorisation, and AI hearing aids are on sale. Most other uses are research, and clinical validation is thin.

What AI does in ENT (Otorhinolaryngology)

AI hearing aidsroutine

On-device networks reduce noise and sharpen speech.

Examples: Phonak Infinio

Eardrum image analysisearly adoption

AI reads otoscope video to flag acute otitis media signs such as a bulging drum.

Examples: TytoCare Tyto Insights for ENT, hearScope

Rhinology navigation and roboticsearly adoption

Image-guided and robotic aids for sinus and skull-base surgery.

Examples: Vendor navigation systems

Head and neck cancer imagingresearch

Detection and outlining of tumours on CT and MRI, and prediction of response.

Examples: Academic models

Laryngoscopy and voice analysisresearch

Detects lesions on endoscopy and voice pathology from recordings.

Examples: Academic models

Surgical skill assessmentresearch

Scores trainee technique from video. A 2025 systematic review covers this.

Examples: Academic tools

routine = in everyday use in many centres · early adoption = in use at some sites, evidence still building · research = studies only

Key ideas for this specialty

AI otoscopy: Software looks at eardrum images or video and suggests findings such as a bulging drum.
Deep neural network hearing aid: A hearing aid with a chip that separates speech from noise using a trained model.
Voice biomarker: Voice recordings analysed by a model to spot disease such as laryngeal pathology.
Radiomics: Extracting many numeric features from CT or MRI so a model can predict tumour behaviour.
Clinical validation: Showing the tool helps real patients. A scoping review of ENT deep learning notes this is often missing.

New to the basics? Start with the theory lessons.

Tools

AI analysis of otoscopy videos to detect eardrum bulging in patients aged six months and older.

Regulatory status: FDA De Novo

Digital video otoscope with AI image classification.

Regulatory status: Not listed

Hearing aids with onboard neural-network noise processing.

Regulatory status: Not listed

MedSAMfree

Open model for segmenting medical images; try it on CT of sinuses or neck.

Regulatory status: Not listed

OpenEvidencefreemium

Clinical question-answering tool for doctors.

Regulatory status: Not listed

A listing here is not an endorsement. Ask any vendor for its CDSCO licence and class before clinical use.

Where to learn

Cureusarticlefreebeginner

Subspecialty tour of current ENT AI.

DeepLearning.AI (Coursera)coursefree auditintermediate

Three courses on image diagnosis, prognosis and treatment models. Needs basic Python.

University of Helsinkicoursefreebeginner

No-maths introduction to what AI can and cannot do. Good first step.

ICMRguidelinefreebeginner

India's own ethics framework. Useful before you plan a thesis using AI.

Stanford AIMIvideo seriesfreeintermediate

Talks and symposium recordings on medical AI.

Otolaryngology-Head and Neck SurgeryguidelineNot listedintermediate

Task-force view on benefits, ethics and gaps in ENT AI.

Do it yourself

Test a chatbot on an ENT topic

Ask a chatbot five questions on a topic such as tympanoplasty. Mark each answer against your standard textbook. Keep a log of errors.

Open the dataset or tool →
Segment a sinus CT with MedSAM

Use a public, de-identified CT slice. Box the maxillary sinus and compare the outline with your own.

Open the dataset or tool →

Use public or properly de-identified data only, and get ethics approval before any project on your own patients.

Papers worth reading

Societies and guidance

Published a task-force report on AI in otolaryngology.

Links checked 3 October 2026. “Not listed” means we could not confirm the detail, not that it is absent. Educational material, not clinical advice.