June 2021
Volume 62, Issue 8
Open Access
ARVO Annual Meeting Abstract  |   June 2021
Using the What-if Tool to perform nearest counterfactual analysis on an AutoML model that predicts visual acuity outcomes in patients receiving treatment for wet age-related macular degeneration
Author Affiliations & Notes
  • Abdallah Abbas
    Division of Medicine, University College London, London, London, United Kingdom
  • Sara Beqiri
    Division of Medicine, University College London, London, London, United Kingdom
  • Siegfried Wagner
    Moorfields Eye Hospital NHS Foundation Trust, London, London, United Kingdom
  • Edward Korot
    Byers Eye Institute, Stanford University, Stanford, California, United States
    Moorfields Eye Hospital NHS Foundation Trust, London, London, United Kingdom
  • Ritvij Singh
    School of Medicine, Imperial College London, London, London, United Kingdom
  • Robbert Struyven
    University College London, London, London, United Kingdom
  • Pearse Keane
    Moorfields Eye Hospital NHS Foundation Trust, London, London, United Kingdom
  • Footnotes
    Commercial Relationships   Abdallah Abbas, None; Sara Beqiri, None; Siegfried Wagner, None; Edward Korot, None; Ritvij Singh, None; Robbert Struyven, None; Pearse Keane, Allergan (R), Apellis (C), Bayer (R), Big Picture Medical (I), DeepMind (C), Heidelberg Engineering (R), Novartis (C), Roche (C), Topcon (R)
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2021, Vol.62, 291. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Abdallah Abbas, Sara Beqiri, Siegfried Wagner, Edward Korot, Ritvij Singh, Robbert Struyven, Pearse Keane; Using the What-if Tool to perform nearest counterfactual analysis on an AutoML model that predicts visual acuity outcomes in patients receiving treatment for wet age-related macular degeneration. Invest. Ophthalmol. Vis. Sci. 2021;62(8):291.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Machine Learning (ML) models suffer from a lack of interpretability, particularly in healthcare settings. We used Google Brain’s What-if Tool (WIT) in a retrospective cohort study to analyse the decision boundaries of a multi-classification model that predicts visual acuity (VA) outcomes for patients with wet age-related macular degeneration (AMD).

Methods : Our AMD dataset consisted of 3961 eyes from patients who had attended Moorfields Eye Hospital in the UK and were undergoing anti-vascular endothelial growth factor treatment. For each patient, VA was measured at the start of treatment and one year later using Early Treatment Diabetic Retinopathy Study charts. VA after one year of treatment was binned to labels of “Good” for scores of 70+, “Neutral” for scores of 36-69, and “Poor” for scores of 35 or below. A Google Cloud AutoML Tables model was then trained on this data to predict these VA outcome labels based on VA at baseline, age, ethnicity and gender.

We report the AUROC, precision and recall performance of the model. To explore decision boundaries, nearest counterfactual analysis using L1 distance was performed using the WIT – a model-agnostic explainable artificial intelligence tool - as a Jupyter notebook extension.

Results : The trained AutoML model performed with an AUROC of 0.892, a precision of 73.1% and a recall of 71.9%. We present a case study of an 84-year-old British male patient with an initial VA of 70, and his nearest counterfactual, an 84-year-old British female patient, also with an initial VA of 70. The ground truth for both patients was “Good”; this was correctly predicted in the male patient, whilst the model predicted a “Neutral” outcome for the female.

Conclusions : We present a novel way in which clinicians can easily view nearest counterfactuals using the WIT, allowing for a greater understanding into how ML models arrive at their decisions at the level of an individual patient. In our example, there is no clinically strong evidence to support the model’s prediction of a “Neutral” outcome in the female patient in comparison to the male patient. Importantly, minimal coding experience is required in both the training of the model on AutoML Tables and the analysis using the WIT. This approach could therefore contribute to the democratisation of ML in healthcare.

This is a 2021 ARVO Annual Meeting abstract.

×
×

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.

×