.
A new study published this week in the journal Nature, Digital Medicine investigated a novel combination of Swarm AI technology developed by Unanimous AI, and deep-learning technology developed at Stanford University. The results showed for the first time that by combining Swarm AI technology with deep-learning, predictive accuracy could be achieved that outperformed either method alone. This is a significant milestone in the development of super-intelligent systems that keep humans in the loop.
.
.
Swarm AI technology is designed to amplify the intelligence of networked human groups by forming real-time systems modeled on biological swarms. Using small groups of networked human doctors, the current study applied Swarm AI to the diagnosis of pneumonia on chest x-rays and compared against human experts alone, as well as two state-of-the-art deep learning AI models. The published work, which was a collaboration between researchers at Stanford University Medical School and Unanimous AI, demonstrates that both the swarm-based technology and deep-learning technology achieved superior diagnostic accuracy than the human experts alone. The work further demonstrates that when used in combination, the Swarm AI technology and deep-learning technology outperformed either method alone. The superior diagnostic accuracy of the combined solution compared to radiologists and AI alone has broad implications for the use of AI in medicine as well as for AI-powered collective intelligence technologies in other professional settings.
.
Swarm AI technology connects networked human groups into super-intelligent systems using AI algorithms modeled after swarms in nature. Often referred to as artificial “hive minds” these super-intelligent networks of human participants have been shown to significantly amplify the forecasting abilities of human groups. Recent research has shown that Swarm AI technology to be highly effective in forecasting financial markets, sporting events, political races, and product sales. This new study is the first to show that Swarm AI technology, when combined with sophisticated deep learning systems, can enable groups of human doctors to achieve super-intelligent levels of diagnostic accuracy.
.
“The results of this study were extremely exciting,” said Dr Louis Rosenberg, Founder and Chief Scientist of Unanimous AI. “It demonstrated for the first time that combining human-in-the-loop Swarm AI technology with sophisticated deep learning technologies we could achieve diagnostic accuracy that significantly exceeded the accuracy of humans or AI alone.”
About Unanimous AI (http://unanimous.ai)
Unanimous AI is the maker of Swarm®, the world’s first forecasting platform that amplifies the intelligence of networked human teams, and Sportspicker™, a premier sports intelligence service. In 2018, Swarm AI technology from Unanimous was recognized as SXSW’s 2018 “AI Innovation of the Year.” Unanimous’ pioneering work in this area is funded by National Science Foundation (NSF) #NSFFUNDED.
Link to paper: Nature.com
