Application of machine learning methods to bridge the gap between non-interventional studies and randomized controlled trials in ophthalmic patients with neovascular age-related macular degeneration

Alexandros Sagkriotis,Usha Chakravarthy,Ray Griner,Orla Doyle,Tim Wintermantel,Andreas Clemens

doi:10.1016/j.cct.2021.106364

Abstract

PurposeThe effectiveness of intravitreal anti-vascular endothelial growth factor agents is usually lower in real world settings compared with randomized clinical trials (RCTs), often limiting the use of real-world evidence (RWE) in regulatory and healthcare decisions. The current analysis aimed to develop and validate an algorithm to explain the difference in outcomes between RWE studies and RCTs in patients with neovascular age-related macular degeneration. MethodsThe algorithm was developed using ranibizumab real world data (RWD) from the US and validated on Australian and UK RWD. A decision model was developed using machine learning principles, in which the model learns how to partition the most influential factors (out of 59 variables) so that they maximally relate to the change in visual acuity (VA) over 12 months. ResultsThe algorithm identified baseline VA <73 Early Treatment Diabetic Retinopathy Study letters, presence of baseline subretinal fluid, and administration of three loading doses by Day 90 from drug initiation as the characteristics with the greatest impact on VA at month 12. When applying the different criteria, RWE outcomes became similar to those obtained in known RCTs. ConclusionMachine learning techniques can be used to classify real world cohorts and identify subsets of patients who benefit to the same extent as that reported in RCTs. This methodology may support the translation of clinical trial findings to treatment performance in the clinical practice setting.

Highlights

Randomized controlled trials (RCTs) are widely considered the ‘gold standard’ for providing evidence on the efficacy and safety of a phar maceutical agent and are clearly appropriate when robust evidence of treatment efficacy and favourable benefit/risk ratio is the goal of the investigation
Eyes treated for retinal vein occlusion (RVO), diabetic macular edema (DME), myopic choroidal neovascularization were ineligible for inclusion
Of the 10,916 eyes extracted from the electronic medical records (EMR) dataset with a diagnosis of neo vascular age-related macular degeneration (nAMD) treated with ranibizumab using a pro re nata (PRN) regimen with 12 months of follow-up, 9547 had both baseline and Month 12 visual acuity (VA) measurements

Summary

Introduction

Randomized controlled trials (RCTs) are widely considered the ‘gold standard’ for providing evidence on the efficacy and safety of a phar maceutical agent and are clearly appropriate when robust evidence of treatment efficacy and favourable benefit/risk ratio is the goal of the investigation. The data from routine clinical care may include patients with an extended level of disease severity than was permitted in clinical trials, and patients with comorbidities and low compliance to treatment; all of which are considered as exclusion criteria in the clinical trial setting. Such differences may lead to dis crepancies in clinical outcomes when RWE is compared to those ob tained from RCTs [4]. In this context the generalizability of data gained from an RCT can be challenged, because the findings of effectiveness of a specific drug demonstrated within the RCT is likely to be diluted when introduced into real world settings

Objectives

Methods

Results

Discussion

Conclusion