AI Software Learns to Identify Pancreatic Cancer Vs Cysts

Commentary
Video

A computational linguistics model designed to locate pancreatic cysts that started to locate pancreatic cancer has the potential to lead to more efficient treatment.

At the 2024 Annual Oncology Clinical Practice and Research Summit, CancerNetwork® spoke with Russell 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, where he discussed the computational linguistics model he enhanced with Eon Health is starting to identify pancreatic cancers in addition to the pancreatic cysts it was intended to locate.

Langan emphasized the significance of this, particularly because it has sped up the process of identifying patients with cancer. This, in turn, gets patients into treatment faster because after the software locates something abnormal, the patient is contacted through a letter and a phone call, and the person who ordered the imaging is also contacted.

According to Langan, a pilot analysis showed there is also the potential that the software is starting to locate cancer in earlier stages. He reiterated the fact that it has to be validated but was hopeful. He also spoke about other software that Eon has on the market that locates abnormalities in different parts of the body.

Transcript:

A non-intended finding that we have realized over the last year is that the program itself…was designed to identify patients with pancreatic cysts and those who are precancerous, but we are starting to realize that the software, which interprets risk because it’s a linguistics model that reads a radiology report…is starting to identify cancers in and around the pancreas. Now the software is not just finding patients with pancreatic cysts, [but] we are finding [patients with] cancer in a quicker way. Then those patients [are moved] into cancer care faster, because after the software identifies a patient, that patient is contacted with a letter; they are also contacted with a phone call, and the person who ordered the scan is contacted.

We’re hopeful that the software will move patients into cancer care pathways quicker, because many patients linger in the community looking for their cancer care, and the software potentially can do that. The other thing is, on a pilot analysis, we may be identifying cancers in their earlier stages. That has to be validated, but that’s one finding that I’ll be talking about tomorrow.

My focus is specific to the pancreas, but the company, Eon Health, does now have software on the market for [abnormalities in the] lung, pancreas, liver, thyroid, breast, and cardiovascular system, as well as other incidental findings in the human body. It has started to grow beyond just the lung and pancreas.

Recent Videos
Ablative technology may generate an immune response that can be enhanced via injected immunotherapy in patients with solid tumors.
Medical use of AI increases every day, and in the future, will be exponentially greater and many forms of treatment will be improved, according to Russell C. Langan, MD, FACS, FSSO.
Performing ablation and injecting tumor sites with immunotherapy may be “synergistic”, according to Jason R. Williams, MD, DABR.
Shubham Pant, MD, MBBS, highlights an “exciting time” in the treatment of patients with RAS-mutated pancreatic cancer.
Greater direct access to academic oncologists may help address challenges associated with a lack of CAR T education in the community setting.
Brett L. Ecker, MD, discusses the importance of multidisciplinary collaboration in improving patient outcomes in neuroendocrine tumors.
Related Content