Trained with 750,000 chest x-ray images and input from 148 experts, this is a breakthrough in ‘clinical decision support’ diagnostic tools
Approximately 30% of the world’s data volume is being generated by the healthcare industry, according to some studies; the annual compounded growth rate of such data for healthcare is expected 36% by 2025.
Realizing the urgent need to transform and future-prove their digital infrastructure to handle the exponential health data, healthcare organizations are at various stages of digital transformation and embracing AI and data analytics.
Today, one clinician-led research platform is tackling some of the biggest issues causing inequitable diagnosis and treatment in chest X-rays, brain CTs with rapidly developed AI products, with the aim of helping medical practitioners make the right diagnoses faster and treat patients sooner.
Using petabytes of diverse data and high-performance compute power, annalise.ai (a harrison.ai joint venture) builds solutions in the radiology sector, such as those that have the capability to detect up to 124 anomalies on a chest X-ray. This is claimed to be one of the most comprehensive ‘clinical decision support’ tools for chest X-rays.
To power their leading-edge research, the firm had to increase its data processing capability by a factor of eight, and upgrade to extremely fast storage. Training its AI model on over 750,000 chest x-ray images, and inputs from a group of 148 radiologists, the firm surmises that without AI power, it would take one radiologist roughly four decades working 40 hours a week to complete same task.
According to harrison.ai’s CEO and co-founder Aengus Tran: “By hosting our compute requirements in a secure and cost-effective way, we can quickly and efficiently deploy AI solutions worldwide, improve the standard of global healthcare and achieve our vision to impact one million lives per day.”
The firm’s chosen AI platform is runs by Equinix Inc running on AI infrastructure from Nvidia. Said Equinix Australia’s Managing Director, Guy Danskine: “Harrison.ai is a great example of the enormous opportunities for AI-based solutions to tackle some of the biggest challenges in healthcare. Each of these challenges is complex, multidimensional and requires critical digital infrastructure to develop its ground-breaking innovations. Equinix will support our customers to capture these opportunities and expand capabilities to effectively respond to dynamic trends.”