Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Efficient Glare Suppression Network for Nighttime Images with Lightweight Parallel Attention and Ghost Convolution.

Sensors (Basel, Switzerland)·2026
Same author

Trends and insights in non-syndromic craniosynostosis research globally: a bibliometric analysis of the Web of Science database (2005-2024).

Translational pediatrics·2026
Same author

Species and strain diversity in Staphylococcus drive divergent host responses in human skin.

bioRxiv : the preprint server for biology·2026
Same author

Structural atlas of Pakpunavirus P7-1 reveals determinants of virion stability and genome ejection.

Communications biology·2026
Same author

Machine Learning-Based Diagnostic Models for Early Gastric Cancer Using Clinical Laboratory Indicators.

International journal of general medicine·2026
Same author

Using Large Language Model Artificial Intelligence to Enhance Clinical Competency Committee Insight.

AEM education and training·2026

Related Experiment Video

Updated: Jan 12, 2026

Electroencephalographic Signal Acquisition Framework for Neurodiverse: A Case Study of Dolphin-Assisted Therapy
07:21

Electroencephalographic Signal Acquisition Framework for Neurodiverse: A Case Study of Dolphin-Assisted Therapy

Published on: June 27, 2025

427

Computer Vision-based Extraction of Structured Data From Scanned Audiograms in the Electronic Health Record.

Ruoyu Yang1, Dana Mae Salvador2, Carl Ehrett1

  • 1Watt Family Innovation Center, Clemson University, Clemson.

Otology & Neurotology : Official Publication of the American Otological Society, American Neurotology Society [And] European Academy of Otology and Neurotology
|November 5, 2025
PubMed
Summary

A new computer vision (CV) method accurately extracts hearing threshold data from scanned audiograms in electronic health records. This approach enables large-scale analysis of hearing loss for research and clinical support.

Keywords:
AudiogramClinical informaticsComputer visionElectronic health recordHearing lossImage processingPure-tone thresholds

More Related Videos

Computer-based Multitaper Spectrogram Program for Electroencephalographic Data
04:13

Computer-based Multitaper Spectrogram Program for Electroencephalographic Data

Published on: November 13, 2019

12.8K
Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

2.0K

Related Experiment Videos

Last Updated: Jan 12, 2026

Electroencephalographic Signal Acquisition Framework for Neurodiverse: A Case Study of Dolphin-Assisted Therapy
07:21

Electroencephalographic Signal Acquisition Framework for Neurodiverse: A Case Study of Dolphin-Assisted Therapy

Published on: June 27, 2025

427
Computer-based Multitaper Spectrogram Program for Electroencephalographic Data
04:13

Computer-based Multitaper Spectrogram Program for Electroencephalographic Data

Published on: November 13, 2019

12.8K
Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

2.0K

Area of Science:

  • Medical Informatics
  • Computer Vision
  • Audiology

Background:

  • Electronic health records (EHRs) contain valuable audiogram data, but it's often unstructured.
  • Extracting structured hearing threshold data from legacy audiograms is challenging.
  • Accurate data extraction is crucial for population-level hearing research and clinical decision support.

Purpose of the Study:

  • To develop and validate a computer vision (CV) method for extracting structured hearing threshold data from scanned audiograms.
  • To assess the accuracy of the CV method in estimating frequency and threshold values.
  • To provide a scalable solution for digitizing historical audiogram data.

Main Methods:

  • A contour-based CV pipeline was developed to process scanned audiograms in PDF format.
  • The pipeline included image cropping, symbol detection, axis label recognition (OCR), coordinate calibration, and symbol digitization.
  • A dataset of 907 audiograms was used for development, with 30 audiograms (618 thresholds) used for validation against manually extracted ground truth data.

Main Results:

  • The CV pipeline achieved a mean absolute error of 136 Hz for frequency and 1.3 dB HL for threshold.
  • Exact threshold accuracy exceeded 85% for unmasked air conduction symbols.
  • The method successfully extracted frequency and threshold values for pure-tone plots.

Conclusions:

  • Computer vision can accurately extract pure-tone threshold data from scanned audiograms without deep learning.
  • This method provides a scalable way to convert legacy audiograms into structured datasets.
  • The approach supports population-level hearing research, clinical decision support, and epidemiologic surveillance.