June 2022
Volume 63, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2022
Quantification of Fluid Compartment Changes in Patients with Limited Response to Anti-VEGF Treatment for Diabetic Macular Edema using a Machine Learning Algorithm in Routine Clinical Practice
Author Affiliations & Notes
  • Resya Chandra Sastry
    Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio, United States
  • Scott W Perkins
    Cleveland Clinic Lerner College of Medicine, Cleveland Clinic, Cleveland, Ohio, United States
  • Rishi P Singh
    Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio, United States
  • Footnotes
    Commercial Relationships   Resya Sastry None; Scott Perkins None; Rishi Singh Novartis, Genentech, Regeneron, Alcon, Bausch and Lomb, 41 Gyroscope, Code C (Consultant/Contractor), Aerie, Apellis, Graybug, Code F (Financial Support)
  • Footnotes
    Support  This study was supported in part by the NIH-NEI P30 Core Grant (IP30EY025585), Unrestricted Grants from The Research to Prevent Blindness, Inc., and Cleveland Eye Bank Foundation awarded to the Cole Eye Institute.
Investigative Ophthalmology & Visual Science June 2022, Vol.63, 2516 – F0242. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Resya Chandra Sastry, Scott W Perkins, Rishi P Singh; Quantification of Fluid Compartment Changes in Patients with Limited Response to Anti-VEGF Treatment for Diabetic Macular Edema using a Machine Learning Algorithm in Routine Clinical Practice. Invest. Ophthalmol. Vis. Sci. 2022;63(7):2516 – F0242.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Anti-VEGF treatment response is assessed anatomically by changes in the central retinal thickness (CRT) and by BCVA outcomes at 3 months after initial monthly injection. This study aims to characterize treatment outcomes of DME patients with limited early response to anti-VEGF at month (M) 3 using a machine learning (ML) algorithm to quantify fluid on optical coherence tomography (OCT) and analyze features of patients within subcategories.

Methods : A retrospective chart review of treatment naive patients ≥ 18 years diagnosed with DME was conducted. All patients had ≥ 12 months of follow-up after initial anti-VEGF treatment and available OCT scans at baseline (M0), M3, M6, and M12. A ML algorithm, Notal OCT Analyzer, quantified fluid volumes on OCTs of subretinal (SRF), intraretinal (IRF), and total retinal fluid (TRF) at each time point. Patients were categorized as limited early responders (LER) if they had ≤ 10% CST reduction and/or < 5 ETDRS letter gain at M3; the other were early responders (ER). BVA, CST, and fluid change at M12 and M0 were compared between groups. Analysis included the Welch’s t-test, Welch’s ANOVA, and one-way analysis of means.

Results : The study included 220 eyes (162 LER, 58 ER) then divided into those who satisfied the anatomic criteria (113 aLER, 107 aER), or VA criteria (134 vLER, 86 vER). At M12, BVA and CST outcomes were significant for aLER and aER. The aLER mean letter gain was 1.32 ETDRS and aER was 9.14. The aLER mean CST reduction was 24.94 mm and aER was 129.51 mm. There was no BVA, TRF, and IRF variance across time for LER (p > 0.1), while all ER groups varied between M0 and M3 (p < 0.001). SRF varied across time for all ER, vLER, and LER. CST had high variance across all groups (p = 0.008) except aLER with a low significance (p < 0.01).

Conclusions : The M12 outcomes between the LER and ER groups showed significant difference between the aLER and aER indicating worse BVA and CST outcomes for those with ≤ 10% CST reduction at M3. Furthermore, limited BVA improvement after M3 for all LER groups indicates vision is unlikely to improve after M3. Similarly, all ER groups showed minimal fluid, BVA, and CST changes after M3. Thus, the characterization of response type at 3 months of monthly anti-VEGF injections can predict anti-VEGF treatment outcomes in DME patients.

This abstract was presented at the 2022 ARVO Annual Meeting, held in Denver, CO, May 1-4, 2022, and virtually.

×
×

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.

×