SAN FRANCISCO, July 21, 2020 /PRNewswire/ -- AI Healthcare company Presagen has developed a novel technique called AI Select that allows selection of high-performing AI during training that is more generalizable and accurate, and thus scalable and reliable when used commercially in practice.
A recent VentureBeat article authored by prominent Silicon Valley VC Andreessen Horowitz, observed that AI companies typically fail to scale like traditional software companies. With limited generalizability to new data, users or edge cases, AI requires a slow and costly process of re-training with each new customer. AI companies can therefore operate more like traditional services companies.
Presagen Co-Founder and Chief Strategy Officer, Dr Don Perugini said, "Lack of scalability not only limits the commercial viability of AI products, but creates barriers for companies or medical clinics that want to adopt AI technology. Scalable out-of-the-box products can be implemented quickly, delivered at low cost, and can be relied upon to work as intended."
The patent-pending AI Select technique comprises a robustness metric which allows evaluation of AI that is both accurate and robust.
Dr Jonathan Hall, Presagen's Co-Founder and Chief Scientist said, "The AI community is obsessed with accuracy, assuming that products with greater accuracy will be commercially superior. However, accuracy is biased to the dataset used to test the AI. For the medical industry, it may not be representative of the general performance of the AI globally for all patients and all clinics."
Presagen has shown that higher general accuracy can be achieved by focusing on AI robustness, making AI products less fragile or brittle. Selecting AI during training that is less accurate but more robust has been shown to create AI that is more accurate and performs better generally, and thus makes the AI more scalable and reliable.
Presagen's first AI medical product, Life Whisperer, is in use globally by IVF clinics. Life Whisperer uses AI to identify which embryos in IVF are likely to lead to a successful pregnancy. The assessment is conducted on single static images of embryos. In a published international clinical study Life Whisperer was shown to be 25% better than current manual embryo assessment methods. Presagen's AI Select is one of a suite of techniques used to ensure scalability of the technology into different global clinics using different cameras systems.
Presagen has recently developed a range of patent-pending AI technologies which drives a fundamental paradigm shift in developing commercially scalable AI products for real-world problems, that apply beyond healthcare and to AI more generally.
Presagen CEO and Co-Founder Dr Michelle Perugini said, "We are excited that over the coming weeks and months we will present to the world the suite of technologies which we believe advance the field of AI. These technologies will allow Presagen to build scalable AI products that are more commercially viable and technically superior, and thus market dominating. This is vital in Presagen's journey to become world-leaders in AI Enhanced Healthcare and a dominant player in the AI in Femtech market globally. More importantly we see it as an opportunity to change, lead, and dominate the AI industry more broadly."