Scientists at the University of Pennsylvania have designed an artificial intelligence system equipped with nanosensors to identify vapors from blood samples of benign or non-cancerous pancreatic and ovarian cancer cells. The tool correctly identified all patients with early-stage cancer and did so in less than 20 minutes, while traditional methods may take days or weeks to achieve results.
And according to the British newspaper “Daily Mail”, an electric nose capable of smelling hard-to-detect cancers with 95% accuracy may change the way specialists diagnose the deadly disease.
For the electrical nasal test, the team analyzed samples from 93 patients, including nearly 20 with ovarian cancer, 20 with benign ovarian tumors, 20 with matched ovarian tumors with no cancer, as well as 13 patients with pancreatic cancer, and 10 with ovarian cancer. With benign pancreatic disease, 10 other patients are under examination.
The system showed that patients with ovarian cancer could be identified with 95% accuracy and pancreatic cancer with 90% accuracy. The technology uses pattern recognition that has a similar approach to the way people's sense of smell works, in which a distinct mixture of compounds tells the brain what to smell. Conventional methods of detecting cancer in patients have required specialists to take a biopsy, which may come from the abdomen, bone marrow, or other parts of the body.
Also, once the sample is collected, it is then sent to a laboratory where it is analyzed by a pathologist who determines whether and what type of tissue the removed tissue has. This could take as little as two to three days or seven to 10 days, depending on the complexity of the situation, while innovation from the University of Pennsylvania will make the whole process faster and easier to perform.