Presagen’s AI Open Projects for Clinics Enables Scalable Unbiased AI Medical Products to Be Built from Globally Diverse Datasets
Presagen has launched a new AI product for clinics at the HLTH conference in Las Vegas, aimed at revolutionizing the way AI is applied to healthcare.
Presagen’s AI Open Projects in an online platform that connects clinics from around the world to safely crowdsource globally diverse datasets needed to build AI medical products that are robust, scalable and unbiased.
The financial value that is created from economies of scale can then be shared amongst contributing clinics via royalties. This enables clinics, particularly small and medium sized clinics, to benefit and unlock the value of their data with AI without wearing the technical or commercial cost and risk.
Participating in Presagen’s AI Open Projects is easy, regardless of clinic size or location. Clinics only need to provide data access, expertise and clinical support. Presagen does the rest, including AI build, regulatory approvals and commercialization.
Presagen already has a call out for AI Open Projects in a range of healthcare sectors, including radiology, retinal, and fertility.
Presagen’s CEO Dr Michelle Perugini said, “To build AI products that solve global problems, you need a global dataset which is diverse and represents different types of people and clinical settings. This is challenging because data privacy laws can prevent private medical data leaving the country of origin. As a result, many focus on building AI from local datasets that are not diverse, creating AI that will be biased and simply will not scale.”
Presagen Co-Founder Dr Jonathan Hall said, “Collectively a globally diverse dataset has the potential to create the world’s most powerful and globally scalable AI, and ultimately improve healthcare outcomes for patients around the globe.”
Presagen’s AI Open Projects was used to launch Life Whisperer, an AI application that helps clinicians identify which embryos will likely lead to a pregnancy for couples undergoing IVF treatment. Life Whisperer has shown to perform 25% better than clinicians’ current manual methods and has also demonstrated ability to non-invasively predict down-syndrome just by using images of embryos.
Presagen’s first AI Open Project in radiology will focus on the detection of lung cancer, in partnership with Dr John MacLean, a clinician with experience in radiology, surgical pathology, and general practice and founder of Doclink. Presagen expects to grow the list of projects to all areas of healthcare, with a vision of collectively becoming world-leaders in AI enhanced healthcare.
A core technology that facilitates AI Open Projects is Presagen’s patent-pending Decentralized AI Training technique. The technique allows AI to be trained on medical data distributed globally without having to move or centralize the data.
Rather than move private data to a central location, Presagen’s technique moves the AI to the data for training. Only the AI which is general knowledge derived from the data is shared and moved between data sources, and never the private data itself.
The technology was led by Dr Jonathan Hall and Co-Founder Dr Don Perugini. Dr Don Perugini has spent over 20 years in AI research and commercialization. He started his career as a Defense scientist in Australia working in IoT and distributed AI systems, and worked collaboratively with international agencies including US Defense Research agency DARPA. Dr Hall is an AI specialist and has dual PhD’s in physics and nanotechnology.
Presagen Co-Founder Dr Don Perugini said, “Presagen’s decentralized AI training technique overcomes significant issues around data sharing to create globally scalable AI. We believe this is a necessary paradigm shift and will revolutionize the way the healthcare industry will build AI products.”
Although currently targeting the healthcare industry, Presagen’s technology is solving a more general and critical underlying problem in AI – building robust, scalable and unbiased AI products.
This was demonstrated with Presagen’s recently announced cyber security partnership with U.S.’s MITRE Corporation, that operate U.S. federally funded R&D centers to solve problems for a safer world; the newly announced Australian Cyber Collaboration Centre in South Australia; and global cybersecurity company DTEX. The collaboration will initially focus on detection of insider threats, and Presagen will apply it unique artificial intelligence (AI) technology to existing detection and investigation capabilities.
Dr Michelle Perugini said, “Building AI products requires a global collaborative effort and dataset. Together, we can grow value for patients with new levels of efficiency while delivering superior healthcare outcomes.”