June 2021
Volume 62, Issue 8
Open Access
ARVO Annual Meeting Abstract  |   June 2021
Interpretable, feature-based predictive modeling of low and high treatment requirements in nAMD using SD-OCT
Author Affiliations & Notes
  • Ales Neubert
    Roche Pharma Research and Early Development Informatics, Basel, Switzerland
  • Andreas Thalhammer
    Roche Pharma Research and Early Development Informatics, Basel, Switzerland
  • Andreas Maunz
    Roche Pharma Research and Early Development Informatics, Basel, Switzerland
  • Jian Dai
    Genentech Inc, South San Francisco, California, United States
  • Footnotes
    Commercial Relationships   Ales Neubert, F. Hoffmann-La Roche Ltd. (E); Andreas Thalhammer, F. Hoffmann-La Roche Ltd. (E); Andreas Maunz, F. Hoffmann-La Roche Ltd. (E); Jian Dai, Genentech, Inc. (E)
  • Footnotes
    Support  F. Hoffmann-La Roche Ltd., Basel, Switzerland, provided support for the study and participated in the study design; conducting the study; and data collection, management, and interpretation
Investigative Ophthalmology & Visual Science June 2021, Vol.62, 2140. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Ales Neubert, Andreas Thalhammer, Andreas Maunz, Jian Dai; Interpretable, feature-based predictive modeling of low and high treatment requirements in nAMD using SD-OCT. Invest. Ophthalmol. Vis. Sci. 2021;62(8):2140.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : To develop an interpretable machine learning (ML) model to predict anti-VEGF treatment requirements for patients with neovascular age-related macular degeneration (nAMD).

Methods : Patients from the ranibizumab 0.5 and 2.0 mg as-needed arms of HARBOR (NCT00891735) who received monthly anti-VEGF injections during a 3-month initiation phase were included. Boundaries of five retinal layers, intra- and subretinal fluid, subretinal hyperreflective material (SHRM), and pigment epithelial detachment (PED) were automatically segmented using ML-based algorithms from spectral-domain optical coherence tomography (SD-OCT) volume scans acquired at each visit. Segmentation results were used to extract quantitative features of layer and fluid features (69 layer and 36 fluid features). BCVA and central subfield thickness (CST) measured at the 3 visits were also included. Low and high treatment groups were defined as requirement of ≤5 or ≥16 injections, respectively, in the 21 months after the initiation phase. Extreme gradient-boosting ML model was used for binary classification (low or high treatment) using stratified 5-fold cross-validation. Feature importance was analyzed using SHapley Additive exPlanations (SHAP).

Results : Data from 363 patients were analyzed. Low and high treatment groups included 82 and 83 patients, respectively, with mean (±SD) area under the receiver operating characteristic curve scores of 0.81±0.06 and 0.80±0.08 (Fig 1). Low treatment need was most strongly associated with low presence of detected PED at month 2. High treatment need was most strongly associated with low presence of SHRM at month 1, low presence of IRF at day 0 and presence of IRF at month 1 (Fig 2).

Conclusions : This exploratory study showed the feasibility of identifying low or high treatment needs for patients with nAMD using predefined imaging features from automated fluid and layer SD-OCT segmentations. Further confirmation of model performance will contribute to future development of personalized healthcare algorithms.

This is a 2021 ARVO Annual Meeting abstract.

 

Fig 1. 5-fold cross-validation for (top) low and (bottom) high requirement

Fig 1. 5-fold cross-validation for (top) low and (bottom) high requirement

 

Fig 2. Feature importance using SHAP for (top) low and (bottom) high requirement. Feature names reflect the measurement (height, volume, or minimum or maximum thickness) and ETDRS radius (0.5, 1.5, or 3 mm)

Fig 2. Feature importance using SHAP for (top) low and (bottom) high requirement. Feature names reflect the measurement (height, volume, or minimum or maximum thickness) and ETDRS radius (0.5, 1.5, or 3 mm)

×
×

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.

×