Scientists at the University of Pennsylvania (Penn) and its Perelman School of Medicine in the US have developed an odour-based test to precisely identify hard-to-detect cancers.

In a study, the test was able to detect and differentiate between benign and pancreatic or ovarian cancer cells with an accuracy of up to 95%.

Named e-nose, the test leverages artificial intelligence (AI) and machine learning to interpret the mixture of volatile organic compounds (VOCs) generated by cells in blood plasma samples.

The test could potentially become a non-invasive method to assess hard to identify cancers, the researchers said.

The electronic olfaction tool has nanosensors that can identify the composition of VOCs, which are emitted by all cells.

Earlier studies have shown that VOCs released from tissue and plasma from ovarian cancer patients are different from those released from samples of benign tumour patients.

How well do you really know your competitors?

Access the most comprehensive Company Profiles on the market, powered by GlobalData. Save hours of research. Gain competitive edge.

Company Profile – free sample

Thank you!

Your download email will arrive shortly

Not ready to buy yet? Download a free sample

We are confident about the unique quality of our Company Profiles. However, we want you to make the most beneficial decision for your business, so we offer a free sample that you can download by submitting the below form

By GlobalData

Penn physics and astronomy professor A T Charlie Johnson said: “It’s an early study but the results are very promising. The data shows we can identify these tumours at both advanced and the earliest stages, which is exciting.

“If developed appropriately for the clinical setting, this could potentially be a test that’s done on a standard blood draw that may be part of your annual physical.”

To analyse the accuracy, a total of 93 patients were assessed. It included 20 ovarian cancer patients, 20 people with benign ovarian tumours and 20 age-matched controls with no cancer.

In addition, the study involved 13 pancreatic cancer patients, ten people with benign pancreatic disease and ten controls.

The university noted that the vapour sensors were able to distinguish the VOCs from ovarian cancer and pancreatic cancer with an accuracy of 95% and 90%, respectively.

Furthermore, the device detected all patients with early-stage cancers.

The pattern recognition approach of this technology works similar to an individual’s sense of smell, where a particular combination of compounds informs the brain about the smell.

E-nose can detect the VOCs patterns linked to cancer cells and those related to cells from healthy blood specimens in under 20 minutes.

At present, the Penn research group has collaborated with VOC Health to market the device, along with others, for research and clinical purposes.