Guest Post: "AI's Impact on Ophthalmic Drug Discovery" By Altris.AI 🧿
Guest Post: "AI's Impact on Ophthalmic Drug Discovery" By Altris.AI 🧿
Revolutionizing Drug Development
Hi everyone 👋.
Today’s guest post is offered to you by Altris.AI (Substack:
) a company digitalizing the world of eye care practice and transforming one of the most common diagnostic methods, the Optical Coherence Tomography (OCT), to a more efficient and accurate method with the help of AI.The article is written by Natalka Chekh, Content Marketing Manager at
, for a deep dive on eye drug development and biomarkers. But first a brief introduction of Altris.💠✴️ Altris.AI in the Media ✴️💠
✴️ The Ophthalmologist: “Altris AI is a helping hand. How AI models alleviate the pressure on global healthcare.”
💠 Optometry Today: “My wish for all eye care specialists is not to be afraid of using new technology in their everyday practice.”
✴️ The New Optometrist: “Where does AI-enabled automated analysis fit into the clinical picture? One of the reasons is better patient triage. AI algorithms can help triage patients by analyzing OCT images and identifying those who require urgent attention. For example, AI can identify signs of macular edema – a serious condition requiring immediate treatment.”
💠 The Ophthalmology Times: “The company’s AI cloud-based platform is available via a browser to any eye care professional in the world. The artificial intelligence algorithm was trained on millions of graphically labeled OCT scans collected from ophthalmic clinics.”
✴️ Optician covers the potential benefits of AI, current AI-powered platforms for AI scan analysis, limitations of AI, and the thoughts on the future of AI in the eye care industry: “AI is here to stay and will likely become more accurate and be able to work with a larger range of biomarkers.”
💠 Eyewire on Altris AI “Altris Inc. announced the launch of Altris AI, an AI-powered software platform designed to automate OCT examination. The secure, cloud-based platform provides fast analysis and visualization of 70+ pathologies and pathological signs, including rare ones, according to Altris.”
✴️ Optical Prism (the oldest Canadian printed media on eye care and eyewear): “Artificial intelligence is revolutionizing the way diagnostics works.”
💠 Silicon Canals: “Altris AI Is All Set to Transform the Global Eye Care Market After Raising $1 Million”
Altris.AI
Altris.AI is an emerging eye AI imaging company applying computer vision and deep learning algorithms to build innovative ophthalmology diagnosis and real-time support, for automatic, structural and quantitative analysis, as well as detection of retinal diseases on Optical Coherence Tomography (OCT) scans.
Founded by Maria Znamenska—the owner of an ophthalmic clinic 👩⚕️ in Kyiv, Ukraine and a PhD 👩🎓 in Ophthalmology—and Andrey Kuropyatnyk—an MBA and IT consultant 🏗️ in Greater Málaga Metropolitan Area in Spain—Altris AI improves the diagnostic process in ophthalmology by automating the detection of more than 70+ pathologies on OCT images utilizing AI. The system is based on the biggest dataset of clinical cases.
Their first prototype for the detection of two pathological conditions and a normal retina was developed in November 2017. In April 2018, Altris.AI was among the winners of the Global New Venture Challenge, a global startup competition of the University of Chicago Booth School of Business. In April 2018, the company Altris Inc. was incorporated, and is now headquartered in the USA with R&D centers located in Kyiv, Ukraine and Malaga, Spain.
Altris Inc. is an ecosystem of products that includes:
⏺ Altris AI (a standalone web platform that improves diagnostic decision-making among eye care 👁️ specialists) and
⏺ Altris Education OCT (a free mobile app for OCT education interpretation).
⏺ The Altris AI system is already installed in more than 300 + optometry centers and ophthalmic clinics around the world and helps hundreds of optometrists and ophthalmologists in diagnostics.
⏺ The Altris Education OCT is used by 17000+ ophthalmologists and optometrists as an education tool. The number of satisfied customers is growing steadily.
In May 2019, the company signed the first partnership agreement with Huvitz Corporation, a South Korean ophthalmic equipment manufacturer aiming to develop AI solutions for OCT interpretation. In July 2019, Altris.AI received a CE-mark certificate as medical software for OCT interpretation with AI. In September 2019, the company released Altris AI, the first commercially available AI solution for OCT interpretation at the EURETINA conference getting positive feedback from the ophthalmology community. In February 2020, the company signed a partnership agreement with Topcon Healthcare—a manufacturer offering the latest integrated solutions including advanced multimodal imaging, vendor-neutral data management and groundbreaking remote diagnostic technology—and Optopol—the manufacturer of the world's first Spectral Domain OCT.
OCT
✔ Optical coherence tomography (OCT) is an imaging technique that uses interferometry with short-coherence-length light to obtain micrometer-level depth resolution and uses transverse scanning of the light beam to form two- and three-dimensional images from light reflected from within biological tissue or other scattering media.
✔ OCT and optical coherence tomography angiography (OCTA) are non-invasive imaging tests. They use light waves to take cross-section pictures of your retina.
With OCT, your ophthalmologist can see each of the retina’s distinctive layers. This allows your ophthalmologist to map and measure their thickness for diagnosis and eventually guide treatment for glaucoma as well as retinal diseases, like age-related macular degeneration (AMD) and diabetic eye disease.
In May 2020, Altris.AI started R&D activities in OCT structural analysis for early retina neurodegeneration detection (Glaucoma, Multiple sclerosis, Alzheimer’s disease, Parkinson’s disease). In the first half of 2023, they were featured in the Ophthalmology Times, Eyes on Eyecase, the Eyewire, the Ophthalmologist, and the New Optometrist, and Optometry Today as one of the promising AI startups in the eye care industry.
In September 2023, the US Food and Drug Administration (FDA) granted 510(k) clearance of Altris IMS platform, the company’s image and data management platform. In February 2024, they added the Early Glaucoma Risk Assessment module, which will be a game changer for the eye care industry.
Let’s move now to Natalka Chekh’s guest post 📯, for a deep dive on eye drug development and biomarkers.
“The real voyage of discovery consists not in seeking new landscapes, but in having new eyes.”
By Marcel Proust
AI's Impact on Ophthalmic Drug Discovery
By Natalka Chekh 👱♀️
Despite increased research and development spending, fewer novel drugs and biologics are reaching the market today. Pharmaceutical companies invest over $5 billion and 12+ years in research for each new drug. The high failure rate of drug candidates—only 10-15% of Phase I drugs reach approval—does not improve the situation. This risk often leads drug companies to favor lower-risk investments. They choose a safer path—biosimilars or generic drugs—over new therapies.
But today we are going to see how AI is revolutionizing the way we approach clinical trials for eye drugs.
Ophthalmic Drug Challenges 🌀
While a marvel of biological engineering, the eye presents unique challenges for drug delivery. Its anatomy is complex. It has many tissues with distinct properties and functions that create difficult barriers to drugs. The cornea, a multi-layered transparent tissue at the front of the eye, acts as a protective shield but hinders the passage of many drugs. The blood-ocular barrier is similar. It is a network of tightly knit cells lining the eye's blood vessels that block many systemic medications.
Different ocular diseases target different tissues, further complicating drug delivery. Topical administration is often preferred for anterior segment diseases like glaucoma—a group of eye diseases that can cause vision loss and blindness by damaging a nerve in the back of your eye called the optic nerve—due to its non-invasive nature and ease of use. However, the tear film, constant blinking, and drug-metabolizing enzymes in the eye contribute to rapid drug clearance, limiting its effectiveness.
The challenges are even greater for posterior segment diseases, such as those affecting the retina. Common retinal diseases include:
Retinal tear, Retinal detachment, Diabetic retinopathy, Epiretinal membrane, Macular hole, Macular degeneration and Retinitis pigmentosa.
In this case, the drugs that reach the back of the eye must traverse additional barriers: the vitreous humor, retinal pigment epithelium and Bruch's membrane. This often requires painful injections for patients, a process that is already inconvenient and the frequent repetition often worsens the experience.
Even seemingly simple formulations like eye drops face obstacles. Tear turnover, drainage through the nasolacrimal duct, and blinking all washout drugs quickly. This requires frequent dosing and increases the risk of side effects. And if that was not enough, the eye has specific enzymes and efflux transporters that limit drug absorption and efficacy.
Scan, Analyze, Discover: search for biomarkers in clinical trials 🔎
An ophthalmologist's report noting the presence of edema on an OCT scan is not the same as quantifying a central macular thickness of 450 μm, indicating significant diffuse edema. Similarly, confirming the presence of diabetic retinopathy—in diabetes the tiny blood vessels in the back of your eye can deteriorate and leak fluid into and under the retina, causing the retina to swell, which may blur or distort your vision—is not the same as precisely measuring the area of intraretinal fluid, providing a detailed assessment of disease severity and potential treatment response. Finally, stating that there are no apparent retinal abnormalities on OCT is not the same as quantifying a 20% decrease in retinal nerve fiber layer thickness, possibly indicating early glaucoma.
Traditionally, medical image interpretation has relied heavily on visual assessment. Experts recognize patterns and deviations from normal anatomy based on their knowledge. Semi-quantitative scoring systems offer some objectivity. However, the field is quickly moving to more quantitative and automated approaches. This shift is driven by improvements in standardization, advanced image analysis techniques and the rise of machine and deep learning.
In ophthalmology, AI-powered analysis of biomarkers like
can provide precise, quantitative measurements of retinal thickness, fluid volume and other signs relevant to diseases like diabetic retinopathy and age-related macular degeneration. These measurements can aid in diagnosis, disease staging, treatment monitoring and prediction of treatment response.
Automatic macular retinal layer thickness segmentation: potential imaging biomarkers
According to this study, the RNFL, GCL, and IPL levels out of all the retinal layers, the inner-most layers of the retina: the retinal nerve fiber layer (RNFL), ganglion cell layer (GCL), and inner plexiform layer (IPL) show the best discriminative power for glaucoma detection. Among these, the RNFL around the circumpapillary region has shown great potential for discrimination. The automatic detection and segmentation of these layers can be approached with different classical digital image processing techniques.
This first population-based study on spectral-domain optical coherence tomography-derived retinal layer thicknesses in a total of ∼1,000 individuals provides insights into the reliability of auto-segmentation and layer-specific reference values for an older population.
The findings showed a difference in thicknesses between early AMD and no AMD for some retinal layers, suggesting these as potential imaging biomarkers.
Lets’ move now from the in silico part to the in vitro part of the eye drug development in Natalka’s story.
From Algorithms to Eye-on-Chips 🧫
Developing ophthalmic drugs relies on animal models. This process can be long and may not always apply well to human patients. Researchers have turned to "Eye-on-a-Chip" (EOC) technology to address this. It is a promising in vitro approach that mimics the eye's physiology and anatomy on a small scale.
EOCs offer a more efficient and human-relevant way to study eye diseases and evaluate potential treatments. They have already proven valuable in recreating choroidal neovascularization in age-related macular degeneration, retinal microvascular occlusions and the effects of high intraocular pressure in glaucoma. These models have also been used to investigate drug responses and toxicity in a controlled environment.
Models focused on the retina have replicated the development of Choroidal neovascularization (CNV) (that is abnormal growth of vessels from the choroidal vasculature to the neurosensory retina through the Bruch's membrane) and its response to anti-VEGF treatment, which is common for Age-related Macular Degeneration (AMD) (aging-caused damage to the macula, the part of the eye that controls sharp, straight-ahead vision). EOCs have also helped researchers understand how changes in glucose and oxygen levels affect the retina and how retinal cells respond to damaging pressure in glaucoma. These models are also used to screen potential neuroprotective agents and study retinal regeneration, including migrating transplanted cells and forming new synapses.
Organoids and organ chips in ophthalmology
Organoids are 3D structures grown from stem cells with organ-level functions.
Organ chips have microfluidic channels lined by living human organ-specific cells.
Organoids and organ chips have been used to understand eye physiology and model ophthalmic disease.
Organoids and organ chips can facilitate the evaluation of therapeutics, e.g. drug screening or gene therapy vectors.
Beyond the retina, EOC models have also been developed for the cornea. These models help us understand how drugs on the eye's surface are absorbed and moved. A recent breakthrough in EOC technology is creating a blinking model that mimics the natural movement of the eyelid. Now, researchers study this model to analyze dry eye disease and test the effects of treatments, including drugs, contact lenses and allergens.
Corneal EOCs have also been used to study wound healing. They study the potential of electrical stimulation (electrotaxis) to guide cell movement and promote tissue repair. These models can help screen drugs for corneal wound healing and give insights into the biological mechanisms.
To make a long story short, EOCs are Here to Stay.
To sum up 💮
Artificial intelligence has the potential to significantly impact drug discovery by enabling more creative and efficient experimentation. It can also reduce the cost and time associated with failures throughout the drug development process. By identifying promising leads earlier and eliminating less viable options, AI can streamline each stage, potentially halving the total cost of a single project.
The future of ophthalmic drug trials is here, and it's powered by AI.
Thank you for reading Metaphysicalcells 🌸🌿
For more about eye drug development and innovation:
All human science is but the increment of the power of the eye..🧿
By John Fiske (philosopher)
And for today’s newsletter on TechBio and AI Drug Discovery innovation: