PITTSBURGH — The best shot at curing cancer is catching it early, doctors say, but that doesn't always happen.

Between 80% and 85% of pancreatic cancer cases aren't diagnosed until the aggressive and lethal disease has already reached advanced stages, according to a 2023 study in the open access medical journal Cureus. Lung and liver cancer also have vague or mild symptoms that can mask the disease until it's too late.

Now, a Carnegie Mellon University spinout company aims to identify patients at high risk for lung, liver and pancreatic cancer by using artificial intelligence. Xlue Inc. is training its cancer prediction tool on millions of patient medical records, identifying signals that are associated with developing cancer in the future.

"The model is essentially mimicking the patient's trajectory," said Xlue cofounder and associate professor in CMU's School of Computer Science Chenyan Xiong. "The model will be able to predict which patients have a higher cancer risk," allowing treating doctors to recommend follow-up screening for early diagnosis.

Among patients with no history of cancer, Xlue's CATCH-FM tool achieved a prediction accuracy rate of 50%. For patients who've already had cancer, the tool's accuracy rate for a return bout reached 70%, Mr. Xiong said.

Medicine is among the most promising fields to benefit from the use of AI. Health care providers have been dipping a toe in the AI pool with applications in patient record charting and ambient listening during medical office visits, but Xlue's predictive technology offers a glimpse into AI's real potential to upend health care.

Xlue's approach could also save money: the average cost to insurers to treat one commercially insured patient with metastatic pancreatic cancer ranges between $95,000 and $116,000, according to a 2021 study in the American Health & Drug Benefit journal.

Screening for the three types of cancer could ultimately improve public health. Widespread mammography screening, for example, has helped reduce breast cancer mortality rates between 8% and 40%, according to the Centers for Disease Control and Prevention.

Xlue, which employs six people, was spun out of CMU in 2025. The Shadyside-based company, which is not yet profitable, has raised $1.5 million in an early friends and family round.

The company trained its predictive tool from electronic medical records for millions of patients spanning two decades, which were part of a large-scale Taiwanese national health care claims database, Mr. Xiong said. Talks are also underway to scan offline and de-identified medical records stored by hospital giant UPMC, Pennsylvania's biggest health care system.

Xlue's technology could be adapted to identify patients with a high risk of suffering a stroke or heart attack, Mr. Xiong said.

"Preventive care is our starting point," he said. "Intervention is pretty easy if you find it early enough."

©2026 PG Publishing Co. Visit at post-gazette.com. Distributed by Tribune Content Agency, LLC.