Skip to main content
Type 2 Diabetes And Pancreatic Cancer

Type 2 Diabetes And Pancreatic Cancer

Monday, August 8, 2016

A staggering 94% of pancreatic cancer patients will die within five years of diagnosis, and 74% of patients die just within the first year. Multiple factors contribute to the low survival rate. It’s not only incredibly aggressive, but also difficult to detect early and, once detected, poorly responsive to treatment. It’s a perfect storm of factors that make it one of the more deadly forms of cancer.

Data+ groupSome recent studies have shed light on the disease, showing a connection between diabetes and pancreatic cancer. Though what exactly that connection may be is yet to be defined, researchers have found evidence that it could be a risk factor and/or a cause. With approximately 80% of pancreatic cancer patients having glucose intolerance or diabetes, the connection is well worth further investigation.

For Lisa Satterwhite, assistant research professor in the Department of Biomedical Engineering, electronic medical records (EMRs) could be the key to defining this relationship. Her Data+ team comprising Shaobo Han, Zidi Xiu and Albert Antar has spent the last ten weeks processing data and making connections between symptoms in the medical record and eventual diagnoses.

“What we’re trying to do is find pancreatic cancer before they diagnose it, which is typically stage 4, and try to see if there are symptoms that are present that haven’t been noticed prior to the cancer spreading,” Satterwhite said.

If it’s found early enough, treatment has a better chance of working, so making connections to the earliest symptoms could give patients a fighting chance.

Discussing each team member’s strengths and how they contributed to the overall project, it’s clear that Satterwhite couldn’t be more enthusiastic about their work together and her team’s results.

“We’ve managed to apply several interesting statistical machine learning approaches to this EMR data,” she said. “And this was because Shaobo, an expert in machine learning, was managing the team. But Zidi has this hidden super power of programming. Pre-processing is everything and what should have taken months took days.”

Antar, with his goal of attending medical school after completing his undergraduate degree, was a constant force pushing for medical relevance according to Satterwhite. Everything the team generated was put through this lens so that their work could make a difference as quickly as possible.

significant topics for Data+ team

“A couple things we found is that the earliest significant symptoms occur about a year and a half before a stage 4 diagnosis and rapid progression of type 2 diabetes seems to be common with a lot of patients,” Antar said. “A lot of patients, in our dataset it was 42%, went from type 2 diabetes to uncontrolled type 2 diabetes, which seems like a really high percentage of people developing uncontrolled type 2 diabetes.”

Describing the data they used, Xiu outlines their approach and methodology as well. The team looked at diagnosis codes from the past ten years in electronic medical records and identified several highly discriminative groups of codes relevant to the disease through machine learning techniques Han suggested.

“We’ve been trying to identify patterns from the data and visualize each patient on a similarity map,” Xiu said. “We think some diabetes patients might already be on their way to developing pancreatic cancer.”

In the last few weeks with her team, Xiu tested the predictive performance of their working prototype developed to find pancreatic cancer in the medical record and found patients without a diagnosis that surrounded patients with a known diagnosis.

While the result is preliminary, it illustrates the power of the team's approach. It’s horrible suffering and any edge on it is worth pursuing. That said, Satterwhite’s team is confident that their work is more than just a chance correlation.

Thinking about her time with the team, Satterwhite is both grateful and optimistic. It’s a major step in identifying the factors involved in the development of pancreatic cancer, and her team is hopeful the results will be published shortly. “It’s been one of the most fun and amazing things I’ve done here. Working with them, it’s just been a few weeks, but it’s been incredible,” she concluded.

Duke SSRI

Durham, NC 27708 | 919.681.6019

SSRI

Gross Hall, 2nd Floor
140 Science Drive
Durham, NC 27708

SSRI

Erwin Mill Building
2024 W. Main St.
Durham, NC 27705

Social Media

Follow @dukessri on twitter