AI tool can estimate cancer patient’s chances for surviving long term

The new machine learning tool can estimate a patient-specific prognosis for breast, thyroid and pancreatic cancers.

New York: Researchers have developed an artificial intelligence (AI)–based tool for estimating a newly-diagnosed cancer patient’s chances for surviving long term.

The new machine learning tool can estimate a patient-specific prognosis for breast, thyroid and pancreatic cancers.

---

A cancer survival calculator prototype developed with machine learning showed that for each of three cancer types tested, more factors than cancer stage significantly influenced patients’ survival.

Currently, estimating survival rates for patients with cancer primarily depends on their cancer stage, said lead study author Lauren Janczewski, a general surgical resident at Northwestern University McGaw Medical Center, Chicago.

“There is a multitude of other factors that may influence a patient’s survival beyond just their staging criteria,” Dr Janczewski said. “We sought to develop this Cancer Survival Calculator to provide a more personalized estimate of what patients can expect regarding their cancer prognosis.”

Using a type of AI known as machine learning, the team created a prototype tool called the Cancer Survival Calculator and tested it on a nationwide cancer dataset. Initial tests estimated five-year survival for patients with cancers of the breast, thyroid, and pancreas.

The study aimed to identify the patient, tumor, and treatment characteristics that most greatly influence patient survival for each cancer type.

After cancer experts recommended characteristics to study, the researchers collected relevant information from patients diagnosed in 2015 and 2017 with breast, thyroid, and pancreatic cancers.

Three-fourths of the collected data were used to train the machine learning algorithms to recognize patterns between characteristics at diagnosis and patients’ survival at five years, and then to rank the factors with the greatest influence on survival.

With the remaining data, the researchers used statistical methods to test the prototype’s accuracy in estimating survival.

The team included data from 259,485 breast cancer patients, 76,624 thyroid cancer patients, and 84,514 pancreatic cancer patients.

The test showed that the calculator was “highly accurate” for all three cancer sites at estimating cancer survival rates – within nine to 10 months of actual survival.

The novel calculator includes specific tumour biomarkers and treatment variables that are known to affect a patient’s estimated prognosis, which Dr Janczewski said many prior survival calculators lack.

The next steps are to finalise a user interface that will allow the use of the Cancer Survival Calculator in clinical practice, followed by pilot testing the calculator at selected cancer centers.

The study was presented at the American College of Surgeons (ACS) Clinical Congress 2023.