AI nose detects ovarian cancer early

An electronic nose using machine learning can detect early signs of ovarian cancer in blood samples with 97 per cent accuracy, according to researchers.

The device uses 32 sensors that react to volatile substances released from blood plasma.

Different cancers emit different substances, meaning each effectively has a distinct chemical pattern.

Rather than searching for a single biomarker, the system analyses a wide range of signals using machine-learning models trained to identify ovarian cancer.

The models are trained on known samples from a biobank, a collection of biological specimens used for research.

The approach was developed by researchers in Sweden.

Donatella Puglisi, associate professor at Linköping University, said: “We’re trying to mimic the mammalian sense of smell artificially.

“We’ve now developed an algorithm that can distinguish ovarian cancer from endometrial cancer and healthy control groups, using data from an electronic nose.

“More and more people are being diagnosed with cancer, especially young adults, and this is alarming.

“If screening were more accessible, both in terms of cost and location, it would be possible to improve early diagnosis.

“Our approach could facilitate the adoption of new screening protocols and the development of new diagnostic methods, improving survival rates, quality of life, and overall clinical outcomes.”

Electronic nose technology has existed for around 60 years.

The sensors used in the prototype are relatively simple models already available on the market, but recent advances in artificial intelligence and machine learning have enabled the technology to be used in new ways.

Current blood-based cancer screening typically involves searching for biomarkers specific to the suspected cancer.

However, researchers say these tests are often slow and lack accuracy.

Jens Eriksson, associate professor at Linköping University and chief technology officer at VOC Diagnostics AB, the company developing the electronic nose, said: “Unlike in breast cancer, there is currently no reliable ovarian cancer screening method.

“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.

“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.

“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.

Ovarian cancer often causes vague symptoms similar to those of more common conditions, meaning it is frequently diagnosed at a late stage when survival outcomes are poor.

In 2022, about 325,000 new cases and more than 200,000 deaths were reported globally, with estimates suggesting these figures will rise sharply by 2050.