Adapting a Computation Linguistics Model to Surveil for Pancreatic Cancer

Commentary
Video

An advanced computation linguistics model that can detect pancreatic cysts can help patients prevent pancreatic tumors from forming.

Russell C. Langan, MD, FACS, FSSO, associate chief of Surgical Officer for System Integration and Quality and director of Surgical Oncology at Northern Region, RWJBarnabas Health and Rutgers Cancer Institute of New Jersey stated that many pancreatic cyst detection programs were “antiquated” and offered a new solution for early surveillance of pancreatic cysts.

Langan, who spoke with CancerNetwork® during the 2024 Annual Oncology Clinical Practice and Research Summit, said that he, in partnership with Eon Health, helped build a computation linguistics model that streamlined and simplified the process of surveillance for potential patients with pancreatic cancer. The model recognizes patients at risk of developing pancreatic cancer, contacts them, and works to begin the intervention process.

Langan was clear about the need for more technologically advanced means of pancreatic cyst surveillance. Prior to the model, patients were required to seek out these surveillance programs or be seen by a physician who had the requisite knowledge to refer them to a cyst program. The new model is intended to take much of the responsibility away from the patients.


Transcript:

In around 2017 or 2018, our institution, the Cooperman Barnabas Medical Center, and the health care system chose to start investing in preventative medicine. At that point in time, they partnered with a company that had an artificial intelligence software called a computational linguistics model that could identify incidental lung nodules, which are pre-cancerous, [and then] contact those patients and make sure that they receive the necessary surveillance so that intervention could potentially prevent lung cancer. I then approached that company and asked them about the pancreas because pancreatic cysts are similar to pulmonary nodules. They are the most common identifiable precursor to pancreatic cancer.

These patients deserve lifelong surveillance when the cysts are mucinous and most of the surveillance programs, in my opinion, were antiquated. They, one, required patients to have some level of health literacy to find a pancreas cyst surveillance program, make an appointment, and get there, or they required a primary care [physician] or gastroenterologist to have knowledge about the risk of pancreatic cysts and refer them into a cyst program. Then the patient also had to follow up over time.

On top of that, the individuals running the programs are running them off Excel spreadsheets. That is all just antiquated. I helped Eon [Health] build a computation linguistics model that’s specific to [the] pancreas to: one, improve the quality for a patient population that is living at risk for the development of pancreatic cancer, to ensure that they receive evidence-based guidelines surveillance, and receive the appropriate intervention to, at times, prevent the development of pancreatic cancer.

Recent Videos
Using bispecific antibodies before or after CAR T-cell therapy in multiple myeloma is an area of education for community oncologists.
Bulkiness of disease did not appear to impact PFS outcomes with ibrutinib plus venetoclax in the phase 2 CAPTIVATE study.
Optimal cancer survivorship care may entail collaboration between a treating oncologist and a cancer survivorship expert.
Survivors of cancer may experience an increased risk of having organ, cardiac, or lung disease following prior anti-cancer therapy.
Only a few groups of patients get screened for pancreatic cancer, those with a genetic risk or pancreatic cysts among them, which can increase lethality for unidentified populations.
The development of RAS-directed vaccines may help decrease the likelihood of disease recurrence in patients undergoing treatment for pancreatic cancer.
Related Content