Medopad startup uses large populations in China to train AI

The healthcare technology startup Medopad, which developed a tool for clinicians to track the vital signs, has used large populations from China to improve the predictive analytics of their artificial intelligence (AI).

Training AI involves machine learning of factors taken from samples of patients, but large amounts of participants are difficult to find in most countries. In response, Dan Vahdat, CEO of Medopad, traveled to China where large populations are easier to access.

“We started going there nearly four years ago,” said Vahdat. “We wanted to get there simply because of the scale of numbers. If you have scale you have access to an asset that nobody has. It gives you an edge against other companies in terms of the predictions you can do.”

Medopad can collect data through wearable fitness trackers or glucose monitors. The information it collects is then analyzed to predict and suggest diagnoses to physicians. However, the AI must be trained with machine learning on actual samples of patients to gain its knowledge of predictive analytics.

“Depending what kind of studies we want to run we can target 10,000 or 100,000 [people],” Vahdat adds. “I don’t think anyone can access 100,000 [people] outside of China.”

""
Cara Livernois, News Writer

Cara joined TriMed Media in 2016 and is currently a Senior Writer for Clinical Innovation & Technology. Originating from Detroit, Michigan, she holds a Bachelors in Health Communications from Grand Valley State University.

Around the web

Compensation for heart specialists continues to climb. What does this say about cardiology as a whole? Could private equity's rising influence bring about change? We spoke to MedAxiom CEO Jerry Blackwell, MD, MBA, a veteran cardiologist himself, to learn more.

The American College of Cardiology has shared its perspective on new CMS payment policies, highlighting revenue concerns while providing key details for cardiologists and other cardiology professionals. 

As debate simmers over how best to regulate AI, experts continue to offer guidance on where to start, how to proceed and what to emphasize. A new resource models its recommendations on what its authors call the “SETO Loop.”