Investigative Ophthalmology & Visual Science Cover Image for Volume 65, Issue 7
June 2024
Volume 65, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2024
Classification of Gender and Systemic Disease from External Eye Photographs using Deep Learning
Author Affiliations & Notes
  • Paul Chong
    Campbell University School of Osteopathic Medicine, Buies Creek, North Carolina, United States
  • Harry Kunze
    Fortem Genus Inc, North Carolina, United States
  • Judy Feeney
    Fortem Genus Inc, North Carolina, United States
  • Robert Enzenauer
    University of Colorado Anschutz Medical Campus School of Medicine, Aurora, Colorado, United States
  • Footnotes
    Commercial Relationships   Paul Chong None; Harry Kunze Fortem Genus Inc, Code E (Employment); Judy Feeney Fortem Genus Inc, Code O (Owner); Robert Enzenauer None
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2024, Vol.65, 1586. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Paul Chong, Harry Kunze, Judy Feeney, Robert Enzenauer; Classification of Gender and Systemic Disease from External Eye Photographs using Deep Learning. Invest. Ophthalmol. Vis. Sci. 2024;65(7):1586.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

Purpose : Artificial intelligence (AI) and machine learning (ML) have been explored in the realm of diagnostics utilizing an array of ophthalmic imaging including fundus photography and optical coherence tomography. We investigated the utility of AI/ML in the diagnosis of health conditions by developing deep learning models to train on external eye photographs taken using a smartphone camera.

Methods : A dataset of over 25,000 external eye images and corresponding clinical data points collected in various locations throughout India was utilized. The images and clinical data were used in the training and testing of deep learning models for the classification of gender and detection of systemic diseases including hypertension, diabetes, and COVID-19. External eye images were captured via smartphone camera by trained technicians. The collection of data complied with relevant research ethics regulations. Explainability techniques, including saliency maps, were employed in an effort to provide insight on the deep learning models.

Results : The developed ML models had an 81.0% accuracy (75.0% sensitivity, 84.7% specificity) in classifying gender and an 80.2% accuracy (47.4% sensitivity, 84.0% specificity) in detecting hypertension. Models showed a 92.0% accuracy (18.7% sensitivity, 96.3% specificity) in detecting diabetes and 83.3% accuracy (52.9% sensitivity, 85.5% specificity) in detecting COVID-19. Explainability analysis demonstrated that the developed ML models made classifications based on relevant regions of external ocular anatomy.

Conclusions : Deep learning models were developed for the diagnosis of health conditions using external eye images taken by a smartphone camera, exhibiting moderate accuracy. Our findings represent a novel diagnostic approach with the potential for development into a remote and highly-accessible diagnostic screening alternative for healthcare professionals and patients.

This abstract was presented at the 2024 ARVO Annual Meeting, held in Seattle, WA, May 5-9, 2024.

 

Shown are saliency maps that were the result of explainability analysis, demonstrating that the developed deep learning models utilized relevant regions of the external eye images in classifying gender and detecting systemic disease.

Shown are saliency maps that were the result of explainability analysis, demonstrating that the developed deep learning models utilized relevant regions of the external eye images in classifying gender and detecting systemic disease.

 

The developed ML models showed moderate accuracy, with the model classifying gender displaying the best diagnostic performance. The models detecting hypertension, diabetes, and COVID-19 suffered from dataset imbalance and subsequent overfitting.

The developed ML models showed moderate accuracy, with the model classifying gender displaying the best diagnostic performance. The models detecting hypertension, diabetes, and COVID-19 suffered from dataset imbalance and subsequent overfitting.

×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×