Fetch.ai’s Shared Data Network Identifies COVID Cases In X-Rays With 97% Accuracy

Cambridge-based tech startup Fetch.ai has announced the launch of its CoLearn network, a decentralized AI collective data center that lives on the blockchain and aggregates learnings from private X-Ray images identifying differences between pneumonia and COVID-19 patients.

Fetch.ai has built an open access, tokenized, decentralized machine learning network to enable smart infrastructure built around a decentralized digital economy. Its network is based around an open-source technology that any user can run to connect to the network, giving access to the power of AI on a world-scale secure dataset, to carry out complex coordination tasks in the modern economy. One of the company’s key tools is a set of autonomous software agents that provide AI services, connecting suppliers and consumers of raw and processed data.

Fetch.ai’s CoLearn provides hospitals and doctors with a network in which they can use their own private data, in the form of chest X-rays, that have been labeled according to whether the patients with pneumonia have tested positive for COVID-19 serving as a rapid diagnostic tool. It can also be used to identify the severity of a patient’s condition including recognizing the need for intubation or the need for supplemental oxygen.

According to Fetch.ai, the CoLearn network will enable multiple participants from anywhere in the world to securely train a shared machine learning model on their private data which the network will then learn from. Utilizing blockchain technology and AI-smart learning capabilities, it supports and trains its network to learn from private data without having access to it.

“Currently, our machine learning algorithm can distinguish COVID-19 patients from those with pneumonia from other causes with an accuracy of 97%,” said Jonathan Ward, CTO of Fetch.ai. “In the context of the pandemic, with wider implementation of our CoLearn network, we have the ability to rapidly and efficiently combine information from hospitals across the globe to vastly improve prognostic predictions and ensure patients are given the right care.”

As of November 2020, CoLearn has reportedly correctly identified COVID-19 cases from a training set of chest X-ray images submitted from hospitals and private practices using a model trained across a distributed network with nodes in Los Angeles and London. As a result, it can give doctors a digital second opinion that confirms or questions their assessment of a patient’s condition.

“Machine learning is changing our everyday life in ways that were previously unimaginable,” said Humayun Sheikh, CEO of Fetch.ai. “These algorithms are everywhere; in your pocket, in traffic cameras, in the websites you visit, and they all share a common goal, to build models based on a given data set to make accurate predictions. Our goal with Fetch.ai’s collective learning module is to utilize otherwise unused and unknown data to solve complex coordination tasks, and in this case, create a database that will quickly identify the existence of COVID-19 in patients while allowing hospitals without experience in ML/AI to benefit from the collective models.”