Large data sets are essential in developing artificial intelligence (AI) algorithms and tools for use in healthcare. Presagen, an AI medical imaging company in Australia, is banking on crowdsourcing in hopes of connecting data from clinics globally to create AI solutions that are scalable and at low cost.
AI developers often rely on localised data, which may be a source of bias raising questions on the utility of the final product. To get around this problem, Presagen has launched its AI Open Projects platform that allows radiology practices worldwide to share images and help to build AI products that are “robust, scalable and unbiased.”
Building AI products for solving global problems requires the use of "a global dataset which is diverse and represents different types of people and clinical settings,” said Presagen CEO Michelle Perugini, PhD. "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."
You may also like: AI Improves Lab Workflow while Cutting Costs
Presagen notes that participating in its AI Open Projects is easy. Practices, regardless of size or location, only need to provide data access, expertise and clinical support. Presagen will be responsible for the AI build, obtaining regulatory approvals and commercialisation.
The company has already put out a call for participants in radiology, along with other specialities such as fertility care. Clinics receive royalties for their participation if the tech becomes successful for commercial use.
This co-development platform, according to Presagen, 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.
"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," said Dr Jonathan Hall, co-founder of Presagen.
The company says its first AI Open Project in radiology will focus on the detection of lung cancer. This will be a collaborative effort with Dr John MacLean, a clinician with experience in radiology, surgical pathology, and general practice and founder of Doclink.
Previously, Presagen used its crowdsourcing platform to build an AI app called Life Whisperer, which helps clinicians identify embryos likely to result in pregnancy for couples using in-vitro fertilisation. Life Whisperer has been shown to perform 25% better than clinicians using manual methods to predict pregnancy.
Source: Radiology Business