Researchers at Linköping University in Sweden have found a way to “smell” cancer. Their new method uses an electronic nose and machine learning to spot early signs of ovarian cancer in blood samples with 97% accuracy. According to the team, the technology is based on a tool that has been around for decades.

A Better Way to Screen Cancer

Ovarian cancer is notoriously hard to find. The symptoms are often vague, so doctors usually don’t catch it until it’s in a late stage, and by then, the chances of survival are slim. Current blood tests look for specific biomarkers, but they are often slow and not very precise.

“Unlike in breast cancer, there is currently no reliable ovarian cancer screening method,” said Jens Eriksson, associate professor at LiU and CTO at VOC Diagnostics AB. “These tests are often based on a single biomarker and lack the precision required to detect the disease at an early stage. Our method is therefore far ahead not only in terms of accuracy but also in the ability to identify early disease.”

How the “Nose” Works

The prototype used in the study has 32 sensors to pick up volatile substances that evaporate from blood plasma. Because different cancers have different chemical “scents,” the machine learning model can tell them apart. Rather than prioritizing one specific biomarker, it just looks for the overall pattern in the air.

“We’re trying to mimic the mammalian sense of smell artificially,” said Donatella Puglisi, associate professor at Linköping University. “We’ve now developed an algorithm that can distinguish ovarian cancer from endometrial cancer and healthy control groups, using data from an electronic nose.” 

The goal is to make screening much cheaper and easier to access. Since the test takes about 10 minutes, it could eventually be used in regular check-ups.

“It’s a simple test that takes 10 minutes and gives a clear result. Our method can test many people at a low cost and is much more accurate than what’s on the market today,” Eriksson added. “This study is a pilot, but we hope it will be used as part of cancer screening within three years. Right now, we’ve focused on detecting cancer, but the applications are endless.”