New AI tool can predict pancreatic cancer three years in advance

A new artificial intelligence tool may be able to successfully identify people at risk of pancreatic cancer up to three years in advance.

The breakthrough AI model used patients’ medical records and information from previous scans to detect those at risk of the deadly disease, which can be hard to catch early, difficult to treat, and kills more than half of sufferers within five years of diagnosis.

Research led by investigators at Harvard Medical School and the University of Copenhagen in collaboration with VA Boston Healthcare System, Dana-Farber Cancer Institute, and the Harvard TH Chan School of Public Health, suggests AI was able to determine a person’s risk of developing pancreatic cancer with astounding accuracy.

The findings published in Nature Medicine implies AI-based population screening could be valuable in finding those at elevated risk of developing the disease, which has an average age of diagnosis of 72 and affects both men and women.

Currently, there are no population-based tools to screen broadly for pancreatic cancer, which in its early stages can have no specific symptoms.

Those with a family history and certain genetic mutations that predispose them to the disease are screened in a targeted fashion. But such focused screenings can miss other cases that fall outside of those categories, the researchers said.

Study co-senior investigator Chris Sander, faculty member in the Department of Systems Biology in the Blavatnik Institute at Harvard Medical School, said: ” One of the most important decisions clinicians face day to day is who is at high risk for a disease, and who would benefit from further testing, which can also mean more invasive and more expensive procedures that carry their own risks.

“An AI tool that can zero in on those at highest risk for pancreatic cancer who stand to benefit most from further tests could go a long way toward improving clinical decision-making.”

Applied at scale, such an approach could expedite detection of pancreatic cancer, lead to earlier treatment, and improve outcomes and prolong patients’ life spans, Dr Sander added.

According to World Cancer Research, pancreatic cancer is the 12th most common in the world with nearly 500,000 new cases in 2020. Globally, the incidence of the disease is projected to increase to 18.6% per 100,000 by 2050, meaning it will pose a significant public health burden.

Søren Brunak, professor of disease systems biology and director of research at the Novo Nordisk Foundation Center for Protein Research at the University of Copenhagen, said: “Many types of cancer, especially those hard to identify and treat early, exert a disproportionate toll on patients, families and the healthcare system as a whole.

“AI-based screening is an opportunity to alter the trajectory of pancreatic cancer, an aggressive disease that is notoriously hard to diagnose early and treat promptly when the chances for success are highest.”

In the study the researchers applied an AI algorithm to clinical date from nine million patient records from the US and Denmark. They asked the AI model to look for tell tale signs based on the data contained in the records.

Based on combinations of disease codes and the timing of their occurrence, the model was able to predict which patients are likely to develop pancreatic cancer in the future. Notably, many of the symptoms and disease codes were not directly related to or stemming from the pancreas.

The researchers tested different versions of the AI models for their ability to detect people at elevated risk for disease development within different time scales — six months, one year, two years, and three years – and found their methods were “substantially more accurate at predicting who would develop pancreatic cancer than current population-wide estimates of disease incidence.”

Among 22 people with lung nodules that eventually were diagnosed with the cancer, the AI flagged 18 as having a high risk of developing the disease.

The researchers said they believe the model is at least as accurate in predicting disease occurrence as are current genetic sequencing tests that are usually available only for a small subset of patients in data sets.

Relatively simple screening tests have become common for many other cancers like breast, cervix, and prostate. By picking up signs of disease early, they have transformed the outcome for patients.

But pancreatic cancer is harder and more expensive to screen and test for.

Medics look mainly at family history and the presence of genetic mutations, which, while important indicators of future risk, often miss many patients.

The researchers say one particular advantage of the AI tool is that it could be used on any and all patients for whom health records and medical history are available – not just in those with a known family history or genetic predisposition for the disease.

This is especially important, the researchers add, because many patients at high risk may not even be aware of their genetic predisposition or family history.

In the absence of symptoms and without a clear indication that someone is at high risk for pancreatic cancer, clinicians may be cautious to recommend more sophisticated and  expensive testing, such as CT scans, MRI or endoscopic ultrasound.

When these tests are used and suspicious lesions discovered, the patient must undergo a procedure to obtain a biopsy. Positioned deep inside the abdomen, the organ is hard to access and easy to provoke and inflame. Its irritability has earned it the nickname ‘the angry organ.’

An AI tool that identifies those at the highest risk for pancreatic cancer would ensure that clinicians test the right population, while sparing others unnecessary testing and additional procedures, the researchers said.

About 44% of people diagnosed in the early stages of pancreatic cancer survive five years after diagnosis, but only 12% of cases are diagnosed that early. Researchers estimate the survival rate drops to between 2-9% in those whose tumours have grown beyond their site of origin.

Dr Sander said: “That low survival rate is despite marked advances in surgical techniques, chemotherapy, and immunotherapy. So, in addition to sophisticated treatments, there is a clear need for better screening, more targeted testing, and earlier diagnosis, and this is where the AI-based approach comes in as the first critical step in this continuum.”

AI has come in for criticism recently due to fears about privacy, intellectual property rights, bias and ethics.

Many scientists are also worried that the technology could soon outperform humans.

But it is being embraced in medicine where it is already being used to help develop new drugs, in surgery and for personalising treatment.

In March this year researchers in Canada announced that artificial intelligence had developed a treatment for the most common type of liver cancer, hepatocellular carcinoma, in just 30 days and could predict a patient’s survival rate.