By Researchers Now Have AI Device to Sniff Out Cancer in Blood Samples With 95% Accuracy For Hard to Detect Types
An odor-based test that sniffs the vapors emanating from blood samples was able to distinguish between benign and pancreatic and ovarian cancer cells with up to 95 percent accuracy, according to a new study from researchers at the University of Pennsylvania and Penn Perelman School of Medicine. .
The findings suggest that the Penn-developed tool, which uses artificial intelligence and machine learning to decipher the mixture of volatile organic compounds (VOCs) emitted by cells in blood plasma samples, could serve as a non-invasive approach to detecting the compounds. more difficult to detect. -detect cancers, such as the pancreas and ovary.
The results of the study were presented at the annual meeting of the American Society for Clinical Oncology in June.
“It’s an early study, but the results are very promising,” Johnson said. “The data shows that we can identify these tumors in both the advanced and early stages, which is exciting. If properly developed for the clinical setting, this could be a test done on a standard blood draw that can be part of your annual physical exam. “
Penn’s research team is currently working with VOC Health to commercialize the device, along with others, for clinical and research applications.
The electronic smell system – “e-nose” – is equipped with nanosensors calibrated to detect the composition of the VOCs, which are emitted by all cells. Previous studies by researchers have shown that VOCs released from tissue and plasma from ovarian cancer patients are different from those released from samples from patients with benign tumors.
Among 93 patients, including 20 patients with ovarian cancer, 20 with benign ovarian tumors, and 20 age-matched controls without cancer, as well as 13 patients with pancreatic cancer, 10 patients with benign pancreatic disease, and 10 controls, the sensors Vapor discriminated VOCs from ovarian cancer with 95 percent accuracy and pancreatic cancer with 90 percent accuracy. The tool also correctly identified all patients (a total of eight) with early-stage cancers.
The technology’s pattern-recognition approach is similar to the way people’s sense of smell works, where a different mix of compounds tells the brain what it’s smelling. The tool was trained and tested to identify the VOC patterns most associated with cancer cells and those associated with cells from healthy blood samples in 20 minutes or less.
The team’s collaboration with Richard Postrel, CEO and Chief Innovation Officer at VOC Health, has also led to a 20x improvement in detection speed.
To accelerate the commercialization process, Postrel says that “initial prototypes of commercial devices capable of detecting cancer from liquids and vapors will be ready soon and will be provided to these Penn researchers to continue their work.”
In related news, researchers at McMaster and Brock Universities in Canada are developing a device that allows patients to monitor their own blood for the unique biomarkers of prostate cancer, shown below, courtesy of Georgia Kirkos of McMaster.
In a related effort with VOC Health, Johnson, along with his co-investigator Benjamin Abella, MD, professor of Emergency Medicine, received a two-year $ 2 million grant from the National Institutes of Health’s National Center for the Advancement of the Sciences. Translational for the development of a portable device that can detect the characteristic “smell” of people with COVID-19, which is based on the cancer detection technology applied in this study.
PUT this amazing development under the noses of your friends on social media …
