Amaros Inc. has closed on Series A financing—and expanded the company’s advisory board—as it seeks to advance product development of a unique artificial intelligence (AI)-based clinical data platform.
Let’s start with Amaros.
Launched in 2017 and based in Menlo Park, California, the biotechnology research company is using advanced analytics and neural network technology to “organize complex imaging data for a more detailed look at retinal diseases.”
Why it’s doing this: As CEO and co-founder Vartan Ghazarossian, PhD, noted, ophthalmology’s most "unutilized asset” is its own data. As such “too much critical information remains siloed—limiting how we study, diagnose, and treat eye diseases."
- And how: By “turning data into actionable intelligence for decision making” via the use of “the industry’s first dynamic real-world intelligence platform,” according to Dr. Ghazarossian.
Before we get into the platform, talk about this financing.
While the company did not disclose a specific amount for the company’s Series A financing, reports indicate the number to be just over $1.2 million.
The investors: Amaros shared that it was backed by both new and existing investors, but did not provide any names.
- Historically, however: The company’s lead investors have included SmartGateVC, Yoshimei, and Wilson Sonsini.
And that newly-formed advisory board?
The board is comprised seven leading ophthalmologists in posterior and anterior segment eye care, AI, and clinical trial design:
- David S. Boyer, MD
- David Eichenbaum, MD
- Peter K. Kaiser, MD
- T. Y. Alvin Liu, MD
- Sumit P. Shah, MD
- Michael A. Singer, MD
- Vance Thompson, MD
Their purpose: To play a key role in the commercialization of Amaros’s AI platform and shaping its application across ophthalmology.
Alrighty, now let’s talk more about this platform.
Amaros refers to its EvidenceEngine platform as an ophthalmic answer engine that leverages a proprietary amalgam neural network (NN)and ophthalmology expertise to generate longitudinal and de-identified data to enable insights.
Hold up: Explain what this amalgam NN is.
- Starting with NN: This is an AI-based method (deep learning, a type of machine learning process) that teaches computers to process data in a manner inspired by the human brain.
- Generally: NNs are utilized for such applications as:
- Image recognition
- Predictive modeling
- Decision-making
- Natural language processing
- Generally: NNs are utilized for such applications as:
- Amalgram indicates that a network isn’t your typical off-the-shelf NN—instead, it’s a customized or hybrid model that combines several elements from various NN types, or uses a unique training methodology.
And together: A proprietary amalgam NN refers to a company-owned, custom-built NN model that features a unique combination of various NN training techniques.
And in the context of EvidenceEngine?
The proprietary platform uses this AI-based method and cloud technology to collect, structure, and analyze large diverse datasets—such as electronic medical and health records; imaging; genomics; provider notes and claims— to:
- Accelerate clinical trial enrollment
- Generate real-world evidence (RWE)
- Identify market opportunities for life sciences companies
And as a reminder, the focus is on retinal disease.
Get into specifics on what it does.
Its capabilities also include providing:
- Image-based biomarker identification and monitoring
- Highly-intuitive analytics
- Direct access to financial and non-clinical metrics and reporting
- Cohort comparisons
- View clinically similar patient cohorts side-by-side
- RWE analysis outcomes
- Within specific patient populations
- Treatment pattern identification
- Among physicians and across eyecare clinic locations
- Key metric tracking
- Includes option to create custom metrics and evidence for specific institutions
So has this been tested in clinics yet?
It appears so.
In speaking on the use of this novel technology for making clinical trial enrollment “more efficient and successful,” Dr. Liu stated that “the time is right,” particularly as the “costs for clinical trials continue to increase and clinical sites are seeking to improve efficiency and decrease study cost and labor required.”
Noting the cost—and time—effectiveness, Neil Friedman, MD, an adjunct clinical professor of Ophthalmology at Stanford University School of Medicine, added that the software also has the “potential to make studies more successful in meeting endpoints.”
See here for more customer feedback from clinical professionals.