Rad AI: Transforming Radiology with Machine Learning

Doctors are some of the most needed, heralded and respected professionals in the world. However, physician burnout is increasing at an alarming rate. Almost half of all doctors in the US report feeling burnt out, and about 70 percent would not recommend the profession to their children.

“Awareness of physician burnout has increased dramatically over the past few years,” Dr Nisha Mehta, a musculoskeletal and breast imaging radiologist in Charlotte, North Carolina, said in an interview with Radiology Business. “The challenge now is how to address it. Across specialties, we haven’t done a great job at finding solutions to burnout that actually move the needle.”

Dr Jeff Cheng, co-founder of Rad AI, is the youngest radiologist and the second youngest doctor in the US, graduating medical school at age 16. Amidst a national shortage of radiologists, he noticed and was concerned by high error rates, increasing imaging demand and radiologist burnout rates that plagued the country.

“The amount of imaging being done goes up by about two or three percent per year, while the number of radiologists in the US stays flat, or goes down slightly,” he told VatorNews. “Also, CMS, and other private insurance, reimbursements go down every year, so there’s really this question of how to use technology to become more efficient, in order to continue to allow radiologists to do what they do best.”

He decided to go to graduate school to learn about machine learning and then partnered with serial entrepreneur Doktor Gurson to found Rad AI in 2018—an artificial intelligence company for radiologists, by radiologists. With a decade of experience in the medical field, he is well equipped to find ways to use technology to best assist radiology specialists and automate specific aspects of the job—a difficult feat in machine learning.

Teams with just an engineering background tend to find solutions to easily solvable problems, Dr Chang explained, so they don’t end up adding much value. He also said that many startups add additional images or steps that disrupt radiologists’ workflow, slowing them down.

“Given that we, as radiologists, need to read 100 to 200 studies a day, it’s really hard to add anything into your workflow that slows you down,” he explained.” So, the key for us is to make sure, as we roll out our product, that it makes you more efficient, while maintaining or improving clinical quality.”

Rad AI uses state-of-the-art machine learning technology to automate tasks to help radiologists focus on diagnosing their patients. The company’s first product automatically generates the impression sections of radiology reports, customising them to fit the preferred language of each physician.

Dr Chang explained that the impression is considered to be the key part of the report. It’s the section where physicians summarise and synthesise the conclusions of what they’ve seen in the findings as well as the appropriate follow-up recommendations. However, he admitted that it’s “sort of repetitive,” so Rad AI automatically generates the impressions based on the rest of the report, the findings and the indication.

So far, customers have reported a reduction in radiologist burnout, error rates, and turnaround time, improving their wellbeing and the treatment their patients receive.

“We help radiology groups significantly increase productivity, while reducing radiologist burnout and improving report accuracy,” Dr Chang said in a statement. “By working closely with radiologists, we can make a positive impact on patient care.”

Rad AI has raised $4 million in a seed round led by Gradient Ventures with participation by UP2398, Precursor Ventures, GMO Venture Partners, Array Ventures, Hike Ventures, Fifty Years VC and several angel investors.

“The team at Rad AI is uniquely suited to apply innovative technology to this field, with strong radiology and AI experts and firsthand knowledge of this market,” said Zachary Bratun-Glennon, partner at Gradient Ventures. “It’s exciting to see the quantitative benefits and positive feedback from their radiology customers, and we’re looking forward to the impact of their future products.”

Leave a Reply

Your email address will not be published. Required fields are marked *