Related Experiment Video
Updated: Nov 12, 2025
Author Spotlight: Ex Vivo OCT-Based Multimodal Imaging of Human Donor Eyes for Research into Age-Related Macular Degeneration
Published on: May 26, 2023
Application of machine learning methods to bridge the gap between non-interventional studies and randomized
Alexandros Sagkriotis1, Usha Chakravarthy2, Ray Griner3
1Novartis Pharma AG, Switzerland.
Purpose:
The 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.
Methods:
The 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.
Results:
The 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.
Conclusion:
Machine 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.
Insights
An algorithm using machine learning can identify patient subgroups in real-world data (RWD) that mirror outcomes from clinical trials for neovascular age-related macular degeneration. This helps bridge the gap between trial findings and clinical practice.
Area of Science:
- Ophthalmology
- Medical Informatics
- Health Services Research
Background:
- Real-world evidence (RWE) effectiveness for anti-VEGF agents often lags behind randomized clinical trials (RCTs).
- This discrepancy limits RWE's utility in regulatory and healthcare decision-making.
- Neovascular age-related macular degeneration (nAMD) treatment outcomes are a key area of concern.
Purpose of the Study:
- To develop and validate an algorithm explaining outcome differences between RWE and RCTs in nAMD patients.
- To identify key factors influencing visual acuity (VA) changes over 12 months in RWE.
Main Methods:
- Developed a machine learning decision model using ranibizumab RWD from the US.
- Validated the model on Australian and UK RWD, analyzing 59 variables.
- Focused on predicting 12-month change in visual acuity.
Main Results:
- Identified baseline VA <73 ETDRS letters, subretinal fluid, and three loading doses by Day 90 as critical factors.
- Applying these criteria aligned RWE outcomes with those from RCTs.
- Demonstrated that specific patient subsets in RWE mirror RCT results.
Conclusions:
- Machine learning can classify RWE cohorts to identify patient subsets matching RCT benefits.
- This methodology aids in translating clinical trial findings to real-world clinical practice.
- Enhances the reliability of RWE for nAMD treatment evaluations.
More Related Videos
05:14Author Spotlight: Overcoming Anti-VEGF Resistance Through Advanced Vascular Morphology Assessment in Choroidal Neovascularization
Published on: August 11, 2023
10:24Regenerative Therapy by Suprachoroidal Cell Autograft in Dry Age-related Macular Degeneration: Preliminary In Vivo Report
Published on: February 12, 2018
Related Concept Videos
01:27Open Angle Glaucoma: Treatment
Drugs such as carbonic anhydrase inhibitors, α2- and...
01:28Angle Closure Glaucoma: Treatment