From the prep work to the riding, Don Wexler loves everything about biking. 

Don's been riding 30 to 60 miles, three to four days a week, for the past four decades — even after being diagnosed with stage four pancreatic cancer.

Doctors found a tumor in his pancreas and another in his liver. Don was told he had 12 to 18 months to live.

“One of the reasons that there are so many deaths from pancreatic cancer is because it's often diagnosed at a late stage,” Brian Wolpin, an oncologist at the Dana-Farber Cancer Institute, said. 

Wolpin says another problem is that there's no regular screening for pancreatic cancer like there is for breast and colon cancers.

Wolpin said he believes harnessing the power of AI could change that. His team used artificial intelligence to find patterns in over nine million patients by looking at medical records, family history and genetic mutations. 

The algorithm was able to correctly predict pancreatic cancer in a high percent of cases.

“We've learned that if we screen patients who have genetic mutations or strong family histories, we can find pancreatic cancer early,” Wolpin said.

Don said he didn't know he had a genetic mutation that made him high risk, but with new medication, chemo and radiation, he beat the odds. He has been cancer free for eight years.

Wolpin said he believes AI will be an even more powerful tool for diagnosis when a patient's full medical record, including current medications and scans, vitals and medical history are included in looking at high risk patients.

Watch the video above for the full story.