June 2015
Volume 56, Issue 7
Free
ARVO Annual Meeting Abstract  |   June 2015
Dealing with inter-expert variability in Retinopathy of Prematurity through machine learning
Author Affiliations & Notes
  • Deniz Erdogmus
    Northeastern University, Boston, MA
  • Veronica Bolon-Canedo
    University of A Coruña, A Coruña, Spain
  • Esra Ataer-Cansizoglu
    Northeastern University, Boston, MA
  • Jayashree Kalpathy-Cramer
    Massachusetts General Hospital, Charlestown, MA
  • Oscar Fontenla-Romero
    University of A Coruña, A Coruña, Spain
  • Amparo Alonso-Betanzos
    University of A Coruña, A Coruña, Spain
  • Michael F Chiang
    Oregon Health & Science University, Portland, OR
  • Footnotes
    Commercial Relationships Deniz Erdogmus, None; Veronica Bolon-Canedo, None; Esra Ataer-Cansizoglu, None; Jayashree Kalpathy-Cramer, None; Oscar Fontenla-Romero, None; Amparo Alonso-Betanzos, None; Michael Chiang, Scientific Advisory Board for Clarity Medical Systems (S)
  • Footnotes
    Support None
Investigative Ophthalmology & Visual Science June 2015, Vol.56, 5251. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to Subscribers Only
      Sign In or Create an Account ×
    • Get Citation

      Deniz Erdogmus, Veronica Bolon-Canedo, Esra Ataer-Cansizoglu, Jayashree Kalpathy-Cramer, Oscar Fontenla-Romero, Amparo Alonso-Betanzos, Michael F Chiang; Dealing with inter-expert variability in Retinopathy of Prematurity through machine learning. Invest. Ophthalmol. Vis. Sci. 2015;56(7 ):5251.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose: Understanding the causes of disagreement among experts in clinical decision making has been a challenge for decades. In particular, diagnosis of retinopathy of prematurity (ROP) shows a high amount of variability. Computer-based image analysis is one approach to improving diagnostic variability. However, a critical unanswered question is to understand discrepancies in the sets of retinal vascular features considered by different experts during diagnosis. We propose a methodology that makes use of machine learning to understand the underlying causes of inter-expert variability.

Methods: A set of 34 retinal images were diagnosed by 22 independent experts. Feature selection (FS) is applied to discover the most important features considered by a given expert. These are compared in turn with those of the rest of experts by applying similarity measures. Finally, an automated classification system with the most relevant features is built to check if this approach can be helpful in ROP diagnosis.

Results: The experimental results reveal that the top selected features regardless of the considered expert are: mean of venous and arterial tortuosity (for 100% and 47% of experts), mean of venous acceleration (42% of experts), and maximum main branch leaf node factor in arteries (68% or experts). For pairs of experts with high percentage of inter-agreement, the FS methods also select similar features. These findings suggest that besides taking into account the standard features (arterial tortuosity and venous dilation), the experts may be considering other features, and that this may be a source of disagreement. Finally, we built an automatic system using the relevant selected features, with which the classification accuracy was improved from 68% to 80% when distinguishing plus, pre-plus and neither; and maintained when classifying into plus or not plus, showing 88% accuracy. The high Williams’ indices obtained by our system (greater than 1) reinforce the idea that it shows a behavior similar to that of expert clinicians.

Conclusions: We provide a handy framework to identify important features for experts and check whether selected features reflect the pairwise disagreements. These findings may lead to improved ROP diagnostic accuracy and standardization among clinicians, and may be generalizable to other clinical problems.

×
×

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.

×