Emily Kaiser

home

authors

emily-kaiser

At ARVO 2022, Carlos Quezada Ruiz, MD, senior medical director at Genentech, presented his talk entitled, “Predicting optimal treatment regimen for patients with neovascular age-related macular degeneration using machine learning.”

This transcript has been lightly edited for clarity.

This year at ARVO, we are presenting our data on a pilot study looking at machine learning and its ability to predict treatment regimen for patients with neovascular AMD. We believe that personalized health care and personalized treatment for patients with neovascular MD is the way that we are going to be treating patients and the retina in the future.

And at Genentech Roche, we are committed to better understanding how machine learning fits into this picture and how it can help us evolve into getting to that personalized approach for patient treatment and patient counseling as well, which is so important.

In this work, we evaluated 324 patients who were enrolled in the AVENUE and the STAIRWAY trial, and who received ranibizumab or faricimab for the treatment of neovascular AMD. We evaluated the baseline characteristics of those 324 patients, which included age, sex baseline BCVA, CSD treatment regimen arm. We also included image-derived characteristics from the spectral domain OCTs of all of those patients. We then implemented different machine learning algorithms. In the results, we actually realize that one of them, XG boost, was the one who came with the with the highest R square. This is basically the highest prediction rate for treatment interval for these patients.

Now, what this means for patients is basically that if this algorithm is able to work, in the future we may be able to predict at baseline during that initial visit how a patient might respond over time with regards to BCVA response, but also what would be the most appropriate treatment regimen, meaning the least frequent regimen that would give the best BCVA outcomes for that individual patient.

And while we recognize this is a pilot study of only a small proportion of patients, we do think that we need bigger datasets and more diverse datasets as well to better replicate these results and be able to extrapolate it to a broader population as well.

Videos

Carlos Quezada Ruiz, MD, senior medical director at Genentech, discusses “Predicting optimal treatment regimen for patients with neovascular age-related macular degeneration using machine learning.”

Machine learning may predict optimal treatment regimen for patients with nAMD

At Retina World Congress 2022, Karl Csaky, MD, presented a talk entitled, “Interpreting Reported GA Treatment Effects to Patient Care: Concept of Tissue Preservation.” He discussed how far research in geographic atrophy has come since he embarked on a project to determine provable endpoints for geographic atrophy (GA) in 2006 and 2007. Now that treatments in the pipeline are aiming to decrease the rate of GA expansion—the endpoint Dr. Csaky and Dr. Ferris identified in their research—he doubles down on the importance of preserving the central retinal tissue.

Dr. Karl Csaky serves as the T. Boone Pickens Director of the Molecular Ophthalmology Laboratory and Clinical Center of Innovation for Macular Degeneration. Additionally, Dr. Csaky is the Chief Executive and Medical Officer at Retina Foundation of the Southwest.

What we're trying to do is, you know, many years ago, I led with Rick Ferris, and a symposium with the Food and Drug Administration on endpoints for various trials and retinal diseases. And back in 2006-2007, we worked on and came to an agreement that the decrease in the rate of GA expansion could be a provable endpoint. And that's been now the gold standard in the community.

And here at this meeting, and throughout other meetings, we are hearing about treatments that may be achieving that endpoint. However, when we really think about what's critically important for patients, while reducing GA expansion is definitely a way to assess the therapy overall, what I was trying to focus this talk on is the what's critical for patients. And for patients. It's really the central retinal tissue within the macula and fovea that needs to be preserved.

So when we think about these therapies potentially coming to the clinic, we really need to be thinking about them in a slightly different, more focused approach. Which is trying to understand as we apply these treatments: How much truly important, critical tissue is being preserved? Which will allow for the patients to have better outcomes in terms of driving, seeing and reading. And so this talk is simply a focus on that subject.

Note: This transcript has been lightly edited for clarity.

As novel therapies in the pipeline are aiming to decrease the rate of GA expansion—the endpoint Karl Csaky, MD and Fredrick Ferris III, MD, identified in 2007—Dr. Csaky reinforces on the importance of preserving the central retinal tissue.

GA therapy endpoints: Should tissue preservation be considered?

At ARVO 2022 in Denver, Colorado, Timothy Blenkinsop, MD, presented “3D Eye Organoids with Distinct Cornea.” His presentation outlined how these organoids have developed sophisticated cornea structures.

Dr. Blenkinsop is an associate professor of ophthalmology, cell development and regenerative biology at the Black Family Stem Cell Institute at the Icahn School of Medicine at Mount Sinai.

Hi, my name is Timothy Blenkinsop. I'm an associate professor at the Icahn School of Medicine at Mount Sinai and we're here presenting some of our exciting work on eye organoids.

And so one of the organoids that we developed are these organoids that differentiate into sophisticated cornea structures. We have conducted single cell RNA-Seq analysis and identified a number of different subtypes of cells, which resemble — at least in terms of the gene expression — the cell types of the cornea, and now we're using these for modeling wound healing diseases and testing compounds to see whether we can mitigate those symptoms from wound healing.

One of the objectives of this research is to develop an eye drop that a patient can use or when they're injured, that could hopefully minimize the wound healing response after injury. 

The next step is really convincing the field at large that this is an effective model, and then moving into animals to then revalidate our proof of principle in animals.


RNA-Seq analysis identifies cell subtypes to use as models for corneal wound healing

David Brown, MD, of Retina Consultants of Texas, previews his ASRS poster with 44-week data for a four-times-higher dose of aflibercept in a real-world setting. “We're doing two phase three studies that are fully recruited, and we'll have the data next year,” Brown adds. He will present his poster during a reception on July 15 at this year’s American Society of Retina Specialists meeting in New York.

David Brown, MD, highlights his ASRS poster that includes 44-week data for a four-times-higher dose of aflibercept in a real-world setting. 

What the impact of 44-week aflibercept data may mean in a real-world setting

Rahul Khurana, MD, highlights the analysis illustrating that there's a lot of variability in clinicians’ management of age-related macular degeneration, and also the treatment needs. There are some patients who need to get treated every four weeks or every eight weeks, but there are also patients that can go longer. The analysis showed that nearly half of these patients could go about 12 weeks or greater. Khurana will present his poster during a reception on July 15 at this year’s American Society of Retina Specialists meeting in New York.

Rahul Khurana, MD, shares a preview of his ASRS poster based on an analysis of the second year of the VIEW 1 and VIEW 2 studies comparing aflibercept and ranibizumab treatment arms. 

VIEW 1 and VIEW 2 studies: taking a deeper dive

Oscar Otero-Marquez, MD, a research fellow with the New York Eye and Ear Infirmary of Mount Sinai, discusses his poster presentation titled, 

Retinal Blood Flow Measurements in Healthy Subjects with OCT Doppler, 

that was presented at the ARVO 2022 annual meeting held in Denver, Colorado.

This transcript has been lightly edited for clarity

Hello. So my name is Oscar Otero, I am a research fellow at New York Icahn Infirmary of Mount Sinai. I'm working at Dr. Rosen’s lab. My poster presentation is titled 

Retinal Blood Flow Measurements in Healthy Subjects with OCT Doppler.

The purpose of our study was to assess retinal blood biomarkers using a new prototype OCT. The idea is that we can measure retinal biomarkers such as blood flow volume, average velocity, and vessel diameter with new prototype.

What we found is that there is no difference in the supratemporal, infratemporal arcades in healthy human subjects. The idea of doing this study is that so far, we do have data available in the U.S. population. All the previous studies have been done on Asian populations. So this is the first time that we can measure retinal blood flow biomarkers in a U.S. population.

The next step is to image subjects with retinal diseases or with glaucoma. The idea is to use this prototype to image subjects with glaucoma, or CRVO. We think that these conditions might predispose to less blood flow within the eye. That means it is not proven yet that, for example, subjects with glaucoma have less blood flow within the eye. And that is a theory that still needs to be proven. So with this device, we can measure the blood flow within the large vessels that are different with OCT-A.

With this prototype, we are measuring the blood flow within large vessels close to the optic nerve. That way, we can see if there is a decrease in the blood flow in conditions such as glaucoma or, for example, in patients with CRVO, and retinal vein occlusions. There is a difference between the non-affected and the affected brain. One good thing is that we expect to measure if there is a difference within the same eye, for example, before and after treatment. If we see we are treating a patient with glaucoma, and we see that with one of our treatments the blood flow increases with medical or surgical therapy, we can reassure the patients that the treatment is good for them. And we can expect to use this as a clinical tool for our patients or for monitoring all kinds of diseases.

The study assess retinal blood biomarkers using a new prototype OCT, aiming to measure retinal biomarkers such as blood flow volume, average velocity, and vessel diameter with a new prototype. 