Hive AI outperforms in Stanford Medical Study
September 18, 2018
A "Hive Mind" of doctors, moderated by AI algorithms, makes more accurate diagnoses than the doctors or machine learning alone, according to a new study from Stanford and Unanimous AI. Carried out by Stanford University School of Medicine together with AI specialist Unanimous AI, the study shows that a small group of doctors, connected by intelligence algorithms that enable them to work together as a "hive mind," could achieve higher diagnostic accuracy than the individual doctors or machine learning algorithms alone.
The technology used is called Swarm AI and is designed to combine individual human professionals' insights in real-time within a workgroup, using AI algorithms to converge on optimal solutions.
As presented at the 2018 SIIM Conference on Machine Intelligence in Medical Imaging, the study tasked a group of experienced radiologists with diagnosing the presence of pneumonia in chest X-rays. This is one of the most widely performed imaging procedures in the US, with more than 1 million adults hospitalised with pneumonia each year. Despite this prevalence, accurately diagnosing X-rays is highly challenging with significant variability across radiologists. This makes it both an optimal task for applying new AI technologies, and an important problem to solve for the medical community.
When generating diagnoses using Swarm AI technology, the average error rate was reduced by 33% compared to traditional diagnoses by individual practitioners.
Swarm AI technology was also compared to modern automated diagnosis using software algorithms that do not employ human practitioners.
Currently, the best system in the world for the automated diagnosing of pneumonia from chest X-rays is the CheXNet system from Stanford University, which made headlines in 2017 by significantly outperforming individual practitioners using deep-learning derived algorithms.
The Swarm AI system was 22% more accurate in binary classification than the software-only CheXNet system.
This result shows that connecting a group of radiologists into a medical "hive mind" produces a hybrid human-machine system that is able to outperform individual human doctors as well as the state-of-the-art in deep-learning derived algorithms.
"Diagnosing pathologies like pneumonia from chest X-rays is extremely difficult, making it an ideal target for AI technologies," said Dr. Matthew Lungren, Assistant Professor of Radiology at Stanford University. "The results of this study are very exciting as they point towards a future where doctors and AI algorithms can work together in real-time, rather than human practitioners being replaced by automated algorithms."
In addition to improving the accuracy of radiological diagnoses, the potential benefits of Swarm AI technology also include generating more accurate "ground truth" datasets for the training of algorithmic systems like CheXNet. In this way, a combination of swarming technologies and deep learning may lead to future breakthroughs.
"Ground Truth datasets are always a challenge for training AI systems in radiology as they depend on human judgement," said Dr. Safwan Halabi," Clinical Associate Professor at Stanford University School of Medicine. "This new technology may enable us to generate more accurate datasets and increase the accuracy of all systems that use machine learning to train on medical datasets."
Swarm AI technology connects networked groups of human participants into real-time intelligent systems modelled after swarms in nature, emulating the way birds flock, fish school, and bees swarm to amplify their collective intelligence. The technology builds a "hive mind" of networked participants, moderated by AI algorithms, to combine the group's knowledge, wisdom, insights, and intuition into an optimised output. Swarm AI technology was recently named "Best AI technology" and "Best in Show" at the 2018 South by Southwest (SXSW) festival's prestigious Innovation Awards.
"We've seen Swarm AI amplify intelligence across many fields, from financial forecasting to business decision-making, but medical applications like the ones we're exploring with Stanford may be the most exciting," says Louis Rosenberg PhD, CEO and Chief Scientist of Unanimous AI. "We fundamentally believe that human wisdom, knowledge, and experience should never be fully replaced from critical decisions. This study helps demonstrate how 'humans-in-the-loop' add real value, even in the world of AI."