JF Healthcare’s AI Technology Is First to Beat Radiologists in Stanford Chest X-ray Diagnostic Competition

JF Healthcare, a medical diagnostic start-up based in Nanchang, China, is the first organization in the world to beat Stanford University radiologists in a competition designed by the Stanford Machine Learning group to compare the capability of artificial intelligence (AI) to human experts in interpreting chest x-rays.

The AI team from JF Healthcare recently achieved an average AUC score (a measure of diagnostic accuracy) of 0.926 and is currently ranked No. 1 in the world on Stanford’s CheXpert leaderboard. Significantly, the JF team outperforms all three Stanford radiologists on the test set, demonstrating the role that AI can play in providing precise medical diagnostics, especially in underserved areas of the world, with profound implications for the treatment of lung cancer, tuberculosis and other diseases of the thorax.

JF Healthcare was founded in 2015 by Frank Wu, who led the healthcare division of Siemens in Northeast Asia for more than 20 years. Through its cloud-based platform, JF offers remote diagnostic services, focusing on chest x-rays, for rural township hospitals in China where certified radiologists are often not available.  Its mobile screening truck is expected to screen more than ten provinces in China for tuberculosis by the end of 2019, offering a half-million people the possibility of early detection while preventing the spread of disease to broader populations.

Read More: AiThority Interview with Suman Mahalanabis, Director of Product Management at TCS Digital Software & Solutions Group

The company recently closed its first major financing round led by Concord, Massachusetts-based GreyBird Ventures, a boutique private investment firm that focuses on diagnostic technology.

“JF Healthcare has multiple advantages that allowed this small company from a mid-tier Chinese city to achieve this remarkable success,” said Tom Miller, Founder and Managing Partner of GreyBird Ventures. “But the key factor is that JF has its own team of radiologists that work closely with AI engineers to review thousands of x-ray annotations every week.  Adding human continuous learning to machine learning is an enormous advantage.  The fact that they are leveraging this benefit for a poor underserved population is a wonderful bonus.”

JF plans to develop a chest x-ray screening product to simultaneously screen for tuberculosis, lung cancer and pneumonia, covering the major thorax diseases based on more than 300,000 chest x-ray images with curated radiology reports collected from approximately 1,000 township hospitals. The team is hoping to fully leverage the clinical value of chest x-rays through AI and deliver it to the massive township hospital patient population in China where radiologists are most needed.

Read More: Law Firm Docketing Process Tastes New AI-Powered Automation

“The goal is to be better than the best human in making diagnoses and deliver low cost care with a level of quality that is equivalent to the best hospitals in the world. To do that, the secret is not math; it’s a huge volume of well-curated data,” said Wu, JF Healthcare’s Founder and CEO. “There are 3 billion people in the world without access to quality healthcare. The first step in remedying this problem is providing extremely accurate diagnostics, which is at the core of our strategy and mission.”

Read More: AiThority Interview with Igor Volzhanin, CEO at DataSine